2023
Belinda Agyapong; Charles Chishimba; Yifeng Wei; Raquel Luz Dias; Ejemai Eboreime; Eleanor Msidi; Syed Sibte Raza Abidi; Maryn Mutaka-Loongo; James Mwansa; Rita Orji; John Mathias Zulu; Vincent Israel Opoku Agyapong
In: JMIR Res Protoc, 12 , pp. e44370, 2023, ISSN: 1929-0748.
Abstract | Links | BibTeX | Tags: burnout; stress; Zambia; Africa; teacher; educator; school; anxiety; wellness; depression; e-mental health; intervention; health literacy; mental health; depressive; psychological issue; psychological problem; text message; messaging; decision-making
@article{info:doi/10.2196/44370,
title = {Improving Mental Health Literacy and Reducing Psychological Problems Among Teachers in Zambia: Protocol for Implementation and Evaluation of a Wellness4Teachers Email Messaging Program},
author = {Belinda Agyapong and Charles Chishimba and Yifeng Wei and Raquel Luz Dias and Ejemai Eboreime and Eleanor Msidi and Syed Sibte Raza Abidi and Maryn Mutaka-Loongo and James Mwansa and Rita Orji and John Mathias Zulu and Vincent Israel Opoku Agyapong},
url = {http://www.ncbi.nlm.nih.gov/pubmed/36877571},
doi = {10.2196/44370},
issn = {1929-0748},
year = {2023},
date = {2023-03-06},
urldate = {2023-03-06},
journal = {JMIR Res Protoc},
volume = {12},
pages = {e44370},
abstract = {Background: Primary, basic, secondary, and high school teachers are constantly faced with increased work stressors that can result in psychological health challenges such as burnout, anxiety, and depression, and in some cases, physical health problems. It is presently unknown what the mental health literacy levels are or the prevalence and correlates of psychological issues among teachers in Zambia. It is also unknown if an email mental messaging program (Wellness4Teachers) would effectively reduce burnout and associated psychological problems and improve mental health literacy among teachers. Objective: The primary objectives of this study are to determine if daily supportive email messages plus weekly mental health literacy information delivered via email can help improve mental health literacy and reduce the prevalence of moderate to high stress symptoms, burnout, moderate to high anxiety symptoms, moderate to high depression symptoms, and low resilience among school teachers in Zambia. The secondary objectives of this study are to evaluate the baseline prevalence and correlates of moderate to high stress, burnout, moderate to high anxiety, moderate to high depression, and low resilience among school teachers in Zambia. Methods: This is a quantitative longitudinal and cross-sessional study. Data will be collected at the baseline (the onset of the program), 6 weeks, 3 months, 6 months (the program midpoint), and 12 months (the end point) using web-based surveys. Individual teachers will subscribe by accepting an invitation to do so from the Lusaka Apex Medical University organizational account on the ResilienceNHope web-based application. Data will be analyzed using SPSS version 25 with descriptive and inferential statistics. Outcome measures will be evaluated using standardized rating scales. Results: The Wellness4Teachers email program is expected to improve the participating teachers' mental health literacy and well-being. It is anticipated that the prevalence of stress, burnout, anxiety, depression, and low resilience among teachers in Zambia will be similar to those reported in other jurisdictions. In addition, it is expected that demographic, socioeconomic, and organizational factors, class size, and grade teaching will be associated with burnout and other psychological disorders among teachers, as indicated in the literature. Results are expected 2 years after the program's launch. Conclusions: The Wellness4Teachers email program will provide essential insight into the prevalence and correlates of psychological problems among teachers in Zambia and the program's impact on subscribers' mental health literacy and well-being. The outcome of this study will help inform policy and decision-making regarding psychological interventions for teachers in Zambia. International Registered Report Identifier (IRRID): PRR1-10.2196/44370},
keywords = {burnout; stress; Zambia; Africa; teacher; educator; school; anxiety; wellness; depression; e-mental health; intervention; health literacy; mental health; depressive; psychological issue; psychological problem; text message; messaging; decision-making},
pubstate = {published},
tppubtype = {article}
}
Background: Primary, basic, secondary, and high school teachers are constantly faced with increased work stressors that can result in psychological health challenges such as burnout, anxiety, and depression, and in some cases, physical health problems. It is presently unknown what the mental health literacy levels are or the prevalence and correlates of psychological issues among teachers in Zambia. It is also unknown if an email mental messaging program (Wellness4Teachers) would effectively reduce burnout and associated psychological problems and improve mental health literacy among teachers. Objective: The primary objectives of this study are to determine if daily supportive email messages plus weekly mental health literacy information delivered via email can help improve mental health literacy and reduce the prevalence of moderate to high stress symptoms, burnout, moderate to high anxiety symptoms, moderate to high depression symptoms, and low resilience among school teachers in Zambia. The secondary objectives of this study are to evaluate the baseline prevalence and correlates of moderate to high stress, burnout, moderate to high anxiety, moderate to high depression, and low resilience among school teachers in Zambia. Methods: This is a quantitative longitudinal and cross-sessional study. Data will be collected at the baseline (the onset of the program), 6 weeks, 3 months, 6 months (the program midpoint), and 12 months (the end point) using web-based surveys. Individual teachers will subscribe by accepting an invitation to do so from the Lusaka Apex Medical University organizational account on the ResilienceNHope web-based application. Data will be analyzed using SPSS version 25 with descriptive and inferential statistics. Outcome measures will be evaluated using standardized rating scales. Results: The Wellness4Teachers email program is expected to improve the participating teachers' mental health literacy and well-being. It is anticipated that the prevalence of stress, burnout, anxiety, depression, and low resilience among teachers in Zambia will be similar to those reported in other jurisdictions. In addition, it is expected that demographic, socioeconomic, and organizational factors, class size, and grade teaching will be associated with burnout and other psychological disorders among teachers, as indicated in the literature. Results are expected 2 years after the program's launch. Conclusions: The Wellness4Teachers email program will provide essential insight into the prevalence and correlates of psychological problems among teachers in Zambia and the program's impact on subscribers' mental health literacy and well-being. The outcome of this study will help inform policy and decision-making regarding psychological interventions for teachers in Zambia. International Registered Report Identifier (IRRID): PRR1-10.2196/44370
William Van Woensel; Samina Abidi; Syed Sibte Raza Abidi
Decentralized Web-based Clinical Decision Support using Semantic GLEAN Workflows Inproceedings Forthcoming
In: 21th International Conference on Artificial Intelligence in Medicine (AIME 2023), June 12-15, 2023, Portoroz, Slovenia, Forthcoming.
BibTeX | Tags:
@inproceedings{nokey,
title = {Decentralized Web-based Clinical Decision Support using Semantic GLEAN Workflows},
author = {William Van Woensel and Samina Abidi and Syed Sibte Raza Abidi},
year = {2023},
date = {2023-00-00},
urldate = {2023-00-00},
booktitle = {21th International Conference on Artificial Intelligence in Medicine (AIME 2023), June 12-15, 2023, Portoroz, Slovenia},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
Samina Abidi; Tracey Rickards; William Van Woensel; Syed Sibte Raza Abidi
Digital Therapeutics for COPD Patient Self-Management: Needs Analysis and Design Study Inproceedings Forthcoming
In: 19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia, Forthcoming.
BibTeX | Tags:
@inproceedings{nokey,
title = {Digital Therapeutics for COPD Patient Self-Management: Needs Analysis and Design Study},
author = {Samina Abidi and Tracey Rickards and William Van Woensel and Syed Sibte Raza Abidi},
year = {2023},
date = {2023-00-00},
urldate = {2023-00-00},
booktitle = {19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
Syed Sibte Raza Abidi; Kranthi Jalakam; Syed Hani Raza Abidi; Karthik Tennankore
Ensemble Clustering to Generate Phenotypes of Kidney Transplant Donors and Recipients Inproceedings Forthcoming
In: 19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia, Forthcoming.
BibTeX | Tags:
@inproceedings{Abidi2023,
title = {Ensemble Clustering to Generate Phenotypes of Kidney Transplant Donors and Recipients},
author = { Syed Sibte Raza Abidi and Kranthi Jalakam and Syed Hani Raza Abidi and Karthik Tennankore},
year = {2023},
date = {2023-00-00},
urldate = {2023-00-00},
booktitle = {19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
Sheida Majouni; Karthik Tennankore; Syed Sibte Raza Abidi
Predicting Urgent Dialysis at Ambulance Transport to the Emergency Department Using Machine Learning Methods Inproceedings Forthcoming
In: 19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia, Forthcoming.
BibTeX | Tags:
@inproceedings{nokey,
title = {Predicting Urgent Dialysis at Ambulance Transport to the Emergency Department Using Machine Learning Methods},
author = {Sheida Majouni and Karthik Tennankore and Syed Sibte Raza Abidi},
year = {2023},
date = {2023-00-00},
urldate = {2023-00-00},
booktitle = {19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
Syed Hani Raza Abidi; Nur Zincir-Heywood; Syed Sibte Raza Abidi; Kranthi Jalakam; Samina Abidi; L. Gunaratnam; R. Suri; H. Cardinale; A. Vinson; B. Prasad; M. Walsh; S. Yohanna; George Worthen; Karthik Tennankore
Characterizing Cluster-Based Frailty Phenotypes in a Multicenter Prospective Cohort of Kidney Transplant Candidates Inproceedings Forthcoming
In: 19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia, Forthcoming.
BibTeX | Tags:
@inproceedings{nokey,
title = {Characterizing Cluster-Based Frailty Phenotypes in a Multicenter Prospective Cohort of Kidney Transplant Candidates},
author = {Syed Hani Raza Abidi and Nur Zincir-Heywood and Syed Sibte Raza Abidi and Kranthi Jalakam and Samina Abidi and L. Gunaratnam and R. Suri and H. Cardinale and A. Vinson and B. Prasad and M. Walsh and S. Yohanna and George Worthen and Karthik Tennankore},
year = {2023},
date = {2023-00-00},
urldate = {2023-00-00},
booktitle = {19th World Congress on Medical and Health Informatics (MEDINFO 2023), 8–12 July 2023, Sydney, Australia},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
2022
William Van Woensel; Floriano Scioscia; Giuseppe Loseto; Oshani Seneviratne; Evan Patton; Samina Abidi; Lalana Kagal
Explainable Clinical Decision Support: Towards Patient-Facing Explanations for Education and Long-term Behavior Change Inproceedings
In: 20th International Conference on Artificial Intelligence in Medicine (AIME 2022): Demo Track, June 14-17, Halifax, 2022, Springer, 2022.
BibTeX | Tags: Explainability, Semantic Web reasoning
@inproceedings{explain_2022,
title = {Explainable Clinical Decision Support: Towards Patient-Facing Explanations for Education and Long-term Behavior Change},
author = {William Van Woensel and Floriano Scioscia and Giuseppe Loseto and Oshani Seneviratne and Evan Patton and Samina Abidi and Lalana Kagal},
year = {2022},
date = {2022-06-17},
urldate = {2022-06-17},
booktitle = {20th International Conference on Artificial Intelligence in Medicine (AIME 2022): Demo Track, June 14-17, Halifax, 2022},
publisher = {Springer},
keywords = {Explainability, Semantic Web reasoning},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Samina Abidi; Karthik Tennankore; George Worthen; Syed Sibte Raza Abidi
Clinical Guidelines as Executable and Interactive Workflows with FHIR-Compliant Health Data Input using GLEAN Inproceedings
In: 20th International Conference on Artificial Intelligence in Medicine (AIME 2022): Demo Track, June 14-17, Halifax, 2022, Springer, 2022.
BibTeX | Tags: Clinical Decision Support Systems, Clinical guidelines, Notation3, Semantic Web reasoning, Task Network Models
@inproceedings{glean-demo,
title = {Clinical Guidelines as Executable and Interactive Workflows with FHIR-Compliant Health Data Input using GLEAN},
author = {William Van Woensel and Samina Abidi and Karthik Tennankore and George Worthen and Syed Sibte Raza Abidi},
year = {2022},
date = {2022-06-17},
urldate = {2022-06-17},
booktitle = {20th International Conference on Artificial Intelligence in Medicine (AIME 2022): Demo Track, June 14-17, Halifax, 2022},
publisher = {Springer},
keywords = {Clinical Decision Support Systems, Clinical guidelines, Notation3, Semantic Web reasoning, Task Network Models},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Samina Abidi; Karthik Tennankore; George Worthen; Syed Sibte Raza Abidi
Explainable Decision Support using Task Network Models in Notation3: Computerizing Lipid Management Clinical Guidelines as Interactive Task Networks Inproceedings
In: 20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax, Springer, 2022.
BibTeX | Tags: Clinical Decision Support Systems, Clinical guidelines, Notation3, Semantic Web reasoning, Task Network Models
@inproceedings{glean_2022,
title = {Explainable Decision Support using Task Network Models in Notation3: Computerizing Lipid Management Clinical Guidelines as Interactive Task Networks},
author = {William Van Woensel and Samina Abidi and Karthik Tennankore and George Worthen and Syed Sibte Raza Abidi},
year = {2022},
date = {2022-06-17},
urldate = {2022-06-17},
booktitle = {20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax},
publisher = {Springer},
keywords = {Clinical Decision Support Systems, Clinical guidelines, Notation3, Semantic Web reasoning, Task Network Models},
pubstate = {published},
tppubtype = {inproceedings}
}
Kathryn Young-Shand; Patrice C. Roy; Michael Dunbar; Syed Sibte Raza Abidi; J. Wilson
Assessing Knee Osteoarthritis Severity and Biomechanical Changes After Total Knee Arthroplasty Using Self-Organizing Maps Inproceedings
In: 20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax, Springer, 2022.
BibTeX | Tags: Self-Organizing Maps, Total knee arthroplasty
@inproceedings{nokey,
title = {Assessing Knee Osteoarthritis Severity and Biomechanical Changes After Total Knee Arthroplasty Using Self-Organizing Maps},
author = {Kathryn Young-Shand and Patrice C. Roy and Michael Dunbar and Syed Sibte Raza Abidi and J. Wilson},
year = {2022},
date = {2022-06-14},
urldate = {2022-06-14},
booktitle = {20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax},
publisher = {Springer},
keywords = {Self-Organizing Maps, Total knee arthroplasty},
pubstate = {published},
tppubtype = {inproceedings}
}
Ali Daowd; Samina Abidi; Syed Sibte Raza Abidi
Knowledge Graph Completion Method Applied to Literature-Based Discovery for Predicting Missing Links Targeting Cancer Drug Repurposing Inproceedings
In: 20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax, Springer, 2022.
BibTeX | Tags: Knowledge Graphs, Link Prediction, Literature-Based Discovery
@inproceedings{nokey,
title = {Knowledge Graph Completion Method Applied to Literature-Based Discovery for Predicting Missing Links Targeting Cancer Drug Repurposing},
author = {Ali Daowd and Samina Abidi and Syed Sibte Raza Abidi},
year = {2022},
date = {2022-06-14},
urldate = {2022-06-14},
booktitle = {20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax},
publisher = {Springer},
keywords = {Knowledge Graphs, Link Prediction, Literature-Based Discovery},
pubstate = {published},
tppubtype = {inproceedings}
}
Jaber Rad; Karthik Tennankore; Amanda Vinson; Syed Sibte Raza Abidi
Extracting Surrogate Decision Trees from Black-box Models to Explain the Temporal Importance of Clinical Features in Predicting Kidney Graft Survival Inproceedings
In: 20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax, Springer, 2022.
BibTeX | Tags: Explainability, Kidney Disease, Machine Learning
@inproceedings{nokey,
title = {Extracting Surrogate Decision Trees from Black-box Models to Explain the Temporal Importance of Clinical Features in Predicting Kidney Graft Survival},
author = {Jaber Rad and Karthik Tennankore and Amanda Vinson and Syed Sibte Raza Abidi
},
year = {2022},
date = {2022-06-14},
urldate = {2022-06-14},
booktitle = {20th International Conference on Artificial Intelligence in Medicine (AIME 2022), June 14-17, 2022, Halifax},
publisher = {Springer},
keywords = {Explainability, Kidney Disease, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Brett Taylor; Syed Sibte Raza Abidi
Towards an Adaptive Clinical Transcription System for In-Situ Transcribing of Patient Encounter Information Inproceedings
In: Studies in Health Technology and Informatics, pp. 158–162, 2022, ISSN: 1879-8365.
Abstract | Links | BibTeX | Tags: Dictaphone, Machine Learning
@inproceedings{pmid35672991,
title = {Towards an Adaptive Clinical Transcription System for In-Situ Transcribing of Patient Encounter Information},
author = {William Van Woensel and Brett Taylor and Syed Sibte Raza Abidi},
doi = {10.3233/SHTI220052},
issn = {1879-8365},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
booktitle = {Studies in Health Technology and Informatics},
journal = {Stud Health Technol Inform},
volume = {290},
pages = {158--162},
abstract = {Electronic patient charts are essential for follow-up and multi-disciplinary care, but either take up an exorbitant amount of time during the patient encounter using a key-stroke entry system, or suffer from poor recall when made long after the encounter. Transcribing in-situ, natural dictations by the clinician, recorded during the encounter, with minimal workflow impact, is a promising solution. However, human transcription requires significant manual resources, whereas automated transcription currently lacks the accuracy for specialized clinical language. Our ultimate goal is to automate clinical transcription, particularly for Emergency Departments, with as an end-result a structured SOAP report. Towards this goal, we present the Adaptive Clinical Transcription System (ACTS). We compare the accuracy and processing times of state-of-the-art speech recognition tools, studying the feasibility of streaming-style dynamic transcription and opportunities of incremental learning.},
keywords = {Dictaphone, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Electronic patient charts are essential for follow-up and multi-disciplinary care, but either take up an exorbitant amount of time during the patient encounter using a key-stroke entry system, or suffer from poor recall when made long after the encounter. Transcribing in-situ, natural dictations by the clinician, recorded during the encounter, with minimal workflow impact, is a promising solution. However, human transcription requires significant manual resources, whereas automated transcription currently lacks the accuracy for specialized clinical language. Our ultimate goal is to automate clinical transcription, particularly for Emergency Departments, with as an end-result a structured SOAP report. Towards this goal, we present the Adaptive Clinical Transcription System (ACTS). We compare the accuracy and processing times of state-of-the-art speech recognition tools, studying the feasibility of streaming-style dynamic transcription and opportunities of incremental learning.
S. Majouni; JC. Kim; E. Sweeny; E. Keltie; Syed Sibte Raza Abidi
Applying Machine Learning to Arsenic Species and Metallomics Profiles of Toenails to Evaluate Associations of Environmental Arsenic with Incident Cancer Cases Inproceedings
In: International Conference on Medical Informatics in Europe (MIE2022), May 26-30, 2022, Nice, France, Springer, 2022.
BibTeX | Tags: Environmental Arsenic, Incident Cancer Cases, Machine Learning
@inproceedings{nokey,
title = {Applying Machine Learning to Arsenic Species and Metallomics Profiles of Toenails to Evaluate Associations of Environmental Arsenic with Incident Cancer Cases},
author = {S. Majouni and JC. Kim and E. Sweeny and E. Keltie and Syed Sibte Raza Abidi},
year = {2022},
date = {2022-05-26},
urldate = {2022-05-26},
booktitle = {International Conference on Medical Informatics in Europe (MIE2022), May 26-30, 2022, Nice, France},
publisher = {Springer},
keywords = {Environmental Arsenic, Incident Cancer Cases, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
Kathryn L. Young-Shand; Patrice C. Roy; Michael J. Dunbar; Syed S. R. Abidi; Janie L. Astephen Wilson
Gait biomechanics phenotypes among total knee arthroplasty candidates by machine learning cluster analysis Journal Article
In: Journal of Orthopaedic Research, 2022.
Abstract | Links | BibTeX | Tags: gait analysis, knee biomechanics, Machine Learning, phenotypes, Total knee arthroplasty
@article{https://doi.org/10.1002/jor.25363,
title = {Gait biomechanics phenotypes among total knee arthroplasty candidates by machine learning cluster analysis},
author = {Kathryn L. Young-Shand and Patrice C. Roy and Michael J. Dunbar and Syed S. R. Abidi and Janie L. Astephen Wilson},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/jor.25363},
doi = {https://doi.org/10.1002/jor.25363},
year = {2022},
date = {2022-05-10},
urldate = {2022-05-10},
journal = {Journal of Orthopaedic Research},
abstract = {Abstract Knee osteoarthritis patient phenotyping is relevant to developing targeted treatments and assessing the treatment efficacy of total knee arthroplasty (TKA). This study aimed to identify clusters among TKA candidates based on demographic and knee mechanic features during gait, and compare gait changes between clusters postoperatively. TKA patients underwent 3D gait analysis 1-week pre (n = 134) and 1-year post-TKA (n = 105). Principal component analysis was applied to frontal and sagittal knee angle and moment waveforms, extracting major patterns of variability. Age, sex, body mass index, gait speed, and frontal and sagittal pre-TKA angle and moment PC scores previously identified as relevant to TKA outcomes were standardized (mean = 0},
keywords = {gait analysis, knee biomechanics, Machine Learning, phenotypes, Total knee arthroplasty},
pubstate = {published},
tppubtype = {article}
}
Abstract Knee osteoarthritis patient phenotyping is relevant to developing targeted treatments and assessing the treatment efficacy of total knee arthroplasty (TKA). This study aimed to identify clusters among TKA candidates based on demographic and knee mechanic features during gait, and compare gait changes between clusters postoperatively. TKA patients underwent 3D gait analysis 1-week pre (n = 134) and 1-year post-TKA (n = 105). Principal component analysis was applied to frontal and sagittal knee angle and moment waveforms, extracting major patterns of variability. Age, sex, body mass index, gait speed, and frontal and sagittal pre-TKA angle and moment PC scores previously identified as relevant to TKA outcomes were standardized (mean = 0
Benjamin Rose-Davis; William Van Woensel; Samina Raza Abidi; Elizabeth Stringer; Syed Sibte Raza Abidi
In: International Journal of Medical Informatics, 2022.
Links | BibTeX | Tags: Argument Theory, Knowledge Graphs, Patient Education, Semantic Web
@article{davis2022,
title = {Semantic Knowledge Modeling and Evaluation of Argument Theory to Develop Dialogue based Patient Education Systems for Chronic Disease Self-Management},
author = {Benjamin Rose-Davis and William Van Woensel and Samina Raza Abidi and Elizabeth Stringer and Syed Sibte Raza Abidi},
url = {https://www.sciencedirect.com/science/article/abs/pii/S1386505622000077},
year = {2022},
date = {2022-01-19},
urldate = {2022-01-18},
journal = {International Journal of Medical Informatics},
keywords = {Argument Theory, Knowledge Graphs, Patient Education, Semantic Web},
pubstate = {published},
tppubtype = {article}
}
2021
D O'Sullivan; W Van Woensel; S Wilk; S W Tu; W Michalowski; S Abidi; M Carrier; R Edry; I Hochberg; S Kingwell; K Kogan; M Michalowski; H O'Sullivan; M Peleg
Towards a framework for comparing functionalities of multimorbidity clinical decision support: A literature-based feature set and benchmark cases Inproceedings
In: AMIA 2021 Annual Symposium, San Diego, CA, 2021.
BibTeX | Tags: Clinical Decision Support Systems, Comorbidity
@inproceedings{OSullivan2021,
title = {Towards a framework for comparing functionalities of multimorbidity clinical decision support: A literature-based feature set and benchmark cases},
author = {D O'Sullivan and W Van Woensel and S Wilk and S W Tu and W Michalowski and S Abidi and M Carrier and R Edry and I Hochberg and S Kingwell and K Kogan and M Michalowski and H O'Sullivan and M Peleg},
year = {2021},
date = {2021-10-30},
urldate = {2021-01-01},
booktitle = {AMIA 2021 Annual Symposium},
address = {San Diego, CA},
keywords = {Clinical Decision Support Systems, Comorbidity},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Samina Abidi; Syed Sibte Raza Abidi
Towards Model-Driven Semantic Interfaces for Electronic Health Records on Multiple Platforms Using Notation3 Inproceedings
In: 4th International Workshop on Semantic Web Meets Health Data Management (SWH’21) co-located with 20th International Semantic Web Conference (ISWC’21), 2021.
Links | BibTeX | Tags: Electronic Medical Record, Model-driven Engineering, Semantic Web
@inproceedings{wvw_swh_21,
title = {Towards Model-Driven Semantic Interfaces for Electronic Health Records on Multiple Platforms Using Notation3},
author = {William Van Woensel and Samina Abidi and Syed Sibte Raza Abidi},
url = {http://ceur-ws.org/Vol-3055/paper4.pdf},
year = {2021},
date = {2021-10-24},
urldate = {2021-10-24},
booktitle = {4th International Workshop on Semantic Web Meets Health Data Management (SWH’21) co-located with 20th International Semantic Web Conference (ISWC’21)},
keywords = {Electronic Medical Record, Model-driven Engineering, Semantic Web},
pubstate = {published},
tppubtype = {inproceedings}
}
Evan Patton; William Van Woensel; Oshani Seneviratne; Giuseppe Loseto; Floriano Scioscia; Lalana Kagal
The Punya Platform: Building Mobile Research Apps with Linked Data and Semantic Features Inproceedings
In: 20th International Semantic Web Conference (ISWC '21), 2021.
BibTeX | Tags: Mobile Computing, Mobile Health, Semantic Web
@inproceedings{Patton2021,
title = {The Punya Platform: Building Mobile Research Apps with Linked Data and Semantic Features},
author = {Evan Patton and William Van Woensel and Oshani Seneviratne and Giuseppe Loseto and Floriano Scioscia and Lalana Kagal},
year = {2021},
date = {2021-10-24},
urldate = {2021-01-01},
booktitle = {20th International Semantic Web Conference (ISWC '21)},
keywords = {Mobile Computing, Mobile Health, Semantic Web},
pubstate = {published},
tppubtype = {inproceedings}
}
Oshani Seneviratne; William Van Woensel; Giuseppe Loseto; Floriano Scioscia; Evan Patton; Lalana Kagal
Rapid Prototyping of Mobile Apps for Clinical Research using Semantic Web Technologies Inproceedings
In: 20th International Semantic Web Conference: Demo Track (ISWC '21), 2021.
BibTeX | Tags: Mobile Computing, Mobile Health, Semantic Web
@inproceedings{Seneviratne2021,
title = {Rapid Prototyping of Mobile Apps for Clinical Research using Semantic Web Technologies},
author = {Oshani Seneviratne and William Van Woensel and Giuseppe Loseto and Floriano Scioscia and Evan Patton and Lalana Kagal},
year = {2021},
date = {2021-10-24},
urldate = {2021-01-01},
booktitle = {20th International Semantic Web Conference: Demo Track (ISWC '21)},
keywords = {Mobile Computing, Mobile Health, Semantic Web},
pubstate = {published},
tppubtype = {inproceedings}
}
G Loseto; E Patton; O Seneviratne; W Van Woensel; F Scioscia; L Kagal
Mobile App Development for the Semantic Web of Things with Punya Inproceedings
In: 20th International Semantic Web Conference: Demo Track (ISWC '21), 2021.
BibTeX | Tags: Internet of Things, Mobile Computing, Semantic Web
@inproceedings{Loseto2021,
title = {Mobile App Development for the Semantic Web of Things with Punya},
author = {G Loseto and E Patton and O Seneviratne and W Van Woensel and F Scioscia and L Kagal},
year = {2021},
date = {2021-10-24},
urldate = {2021-01-01},
booktitle = {20th International Semantic Web Conference: Demo Track (ISWC '21)},
keywords = {Internet of Things, Mobile Computing, Semantic Web},
pubstate = {published},
tppubtype = {inproceedings}
}
Syed Asil Ali Naqvi; Karthik Tennankore; Amanda Vinson; Patrice C Roy; Syed Sibte Raza Abidi
Predicting Kidney Graft Survival Using Machine Learning Methods: Prediction Model Development and Feature Significance Analysis Study Journal Article
In: Journal of Medical Internet Research, 23 (8), pp. e26843, 2021, ISSN: 1438-8871.
Abstract | Links | BibTeX | Tags: dimensionality reduction, feature sensitivity analysis, survival prediction
@article{Naqvi2021b,
title = {Predicting Kidney Graft Survival Using Machine Learning Methods: Prediction Model Development and Feature Significance Analysis Study},
author = {Syed Asil Ali Naqvi and Karthik Tennankore and Amanda Vinson and Patrice C Roy and Syed Sibte Raza Abidi},
url = {https://www.jmir.org/2021/8/e26843},
doi = {10.2196/26843},
issn = {1438-8871},
year = {2021},
date = {2021-08-27},
journal = {Journal of Medical Internet Research},
volume = {23},
number = {8},
pages = {e26843},
publisher = {Journal of Medical Internet Research},
abstract = {Background: Kidney transplantation is the optimal treatment for patients with end-stage renal disease. Short- and long-term kidney graft survival is influenced by a number of donor and recipient factors. Predicting the success of kidney transplantation is important for optimizing kidney allocation.
Objective: The aim of this study was to predict the risk of kidney graft failure across three temporal cohorts (within 1 year, within 5 years, and after 5 years following a transplant) based on donor and recipient characteristics. We analyzed a large data set comprising over 50,000 kidney transplants covering an approximate 20-year period.
Methods: We applied machine learning–based classification algorithms to develop prediction models for the risk of graft failure for three different temporal cohorts. Deep learning–based autoencoders were applied for data dimensionality reduction, which improved the prediction performance. The influence of features on graft survival for each cohort was studied by investigating a new nonoverlapping patient stratification approach.
Results: Our models predicted graft survival with area under the curve scores of 82% within 1 year, 69% within 5 years, and 81% within 17 years. The feature importance analysis elucidated the varying influence of clinical features on graft survival across the three different temporal cohorts.
Conclusions: In this study, we applied machine learning to develop risk prediction models for graft failure that demonstrated a high level of prediction performance. Acknowledging that these models performed better than those reported in the literature for existing risk prediction tools, future studies will focus on how best to incorporate these prediction models into clinical care algorithms to optimize the long-term health of kidney recipients.},
keywords = {dimensionality reduction, feature sensitivity analysis, survival prediction},
pubstate = {published},
tppubtype = {article}
}
Background: Kidney transplantation is the optimal treatment for patients with end-stage renal disease. Short- and long-term kidney graft survival is influenced by a number of donor and recipient factors. Predicting the success of kidney transplantation is important for optimizing kidney allocation.
Objective: The aim of this study was to predict the risk of kidney graft failure across three temporal cohorts (within 1 year, within 5 years, and after 5 years following a transplant) based on donor and recipient characteristics. We analyzed a large data set comprising over 50,000 kidney transplants covering an approximate 20-year period.
Methods: We applied machine learning–based classification algorithms to develop prediction models for the risk of graft failure for three different temporal cohorts. Deep learning–based autoencoders were applied for data dimensionality reduction, which improved the prediction performance. The influence of features on graft survival for each cohort was studied by investigating a new nonoverlapping patient stratification approach.
Results: Our models predicted graft survival with area under the curve scores of 82% within 1 year, 69% within 5 years, and 81% within 17 years. The feature importance analysis elucidated the varying influence of clinical features on graft survival across the three different temporal cohorts.
Conclusions: In this study, we applied machine learning to develop risk prediction models for graft failure that demonstrated a high level of prediction performance. Acknowledging that these models performed better than those reported in the literature for existing risk prediction tools, future studies will focus on how best to incorporate these prediction models into clinical care algorithms to optimize the long-term health of kidney recipients.
Objective: The aim of this study was to predict the risk of kidney graft failure across three temporal cohorts (within 1 year, within 5 years, and after 5 years following a transplant) based on donor and recipient characteristics. We analyzed a large data set comprising over 50,000 kidney transplants covering an approximate 20-year period.
Methods: We applied machine learning–based classification algorithms to develop prediction models for the risk of graft failure for three different temporal cohorts. Deep learning–based autoencoders were applied for data dimensionality reduction, which improved the prediction performance. The influence of features on graft survival for each cohort was studied by investigating a new nonoverlapping patient stratification approach.
Results: Our models predicted graft survival with area under the curve scores of 82% within 1 year, 69% within 5 years, and 81% within 17 years. The feature importance analysis elucidated the varying influence of clinical features on graft survival across the three different temporal cohorts.
Conclusions: In this study, we applied machine learning to develop risk prediction models for graft failure that demonstrated a high level of prediction performance. Acknowledging that these models performed better than those reported in the literature for existing risk prediction tools, future studies will focus on how best to incorporate these prediction models into clinical care algorithms to optimize the long-term health of kidney recipients.
William Van Woensel; Manal Elnenaei; Syed Sibte Raza Abidi; David B Clarke; Syed Ali Imran
Staged Reflexive Artificial Intelligence Driven Testing Algorithms for Early Diagnosis of Pituitary Disorders Journal Article
In: Clinical Biochemistry, 2021.
Links | BibTeX | Tags: Clinical Decision Support Systems, Health Informatics, Reflex Protocols
@article{VanWoensel2021b,
title = {Staged Reflexive Artificial Intelligence Driven Testing Algorithms for Early Diagnosis of Pituitary Disorders},
author = {William Van Woensel and Manal Elnenaei and Syed Sibte Raza Abidi and David B Clarke and Syed Ali Imran},
url = {https://www.sciencedirect.com/science/article/pii/S0009912021002265},
year = {2021},
date = {2021-08-20},
urldate = {2021-08-20},
journal = {Clinical Biochemistry},
keywords = {Clinical Decision Support Systems, Health Informatics, Reflex Protocols},
pubstate = {published},
tppubtype = {article}
}
Ali Daowd; Michael Barrett; Samina Abidi; Syed Sibte Raza Abidi
In: 2021 IEEE International Conference on Healthcare Informatics (ICHI), Victoria, BC, Canada, IEEE, 2021, ISBN: 978-1-6654-0132-6.
Links | BibTeX | Tags: Causal relations, Chronic Illness, Knowledge Graphs
@inproceedings{daowd_ichi_21,
title = {A Framework To Build A Causal Knowledge Graph for Chronic Diseases and Cancers By Discovering Semantic Associations from Biomedical Literature},
author = {Ali Daowd and Michael Barrett and Samina Abidi and Syed Sibte Raza Abidi},
doi = {10.1109/ICHI52183.2021.00016},
isbn = {978-1-6654-0132-6},
year = {2021},
date = {2021-08-09},
urldate = {2021-08-09},
booktitle = {2021 IEEE International Conference on Healthcare Informatics (ICHI), Victoria, BC, Canada},
publisher = {IEEE},
keywords = {Causal relations, Chronic Illness, Knowledge Graphs},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Syed Sibte Raza Abidi; Samina Raza Abidi
In: Artificial Intelligence in Medicine, 118 , pp. 102127, 2021, ISSN: 0933-3657.
Abstract | Links | BibTeX | Tags: Clinical guidelines, Comorbidity, Decision Support Systems
@article{VANWOENSEL2021102127,
title = {Decision support for comorbid conditions via execution-time integration of clinical guidelines using transaction-based semantics and temporal planning},
author = {William Van Woensel and Syed Sibte Raza Abidi and Samina Raza Abidi},
url = {https://www.sciencedirect.com/science/article/pii/S0933365721001202},
doi = {https://doi.org/10.1016/j.artmed.2021.102127},
issn = {0933-3657},
year = {2021},
date = {2021-08-01},
journal = {Artificial Intelligence in Medicine},
volume = {118},
pages = {102127},
abstract = {In case of comorbidity, i.e., multiple medical conditions, Clinical Decision Support Systems (CDSS) should issue recommendations based on all relevant disease-related Clinical Practice Guidelines (CPG). However, treatments from multiple comorbid CPG often interact adversely (e.g., drug-drug interactions) or introduce operational inefficiencies (e.g., redundant scans). A common solution is the a-priori integration of computerized CPG, which involves integration decisions such as discarding, replacing or delaying clinical tasks (e.g., treatments) to avoid adverse interactions or inefficiencies. We argue this insufficiently deals with execution-time events: as the patient's health profile evolves, acute conditions occur, and real-time delays take place, new CPG integration decisions will often be needed, and prior ones may need to be reverted or undone. Any realistic CPG integration effort needs to further consider temporal aspects of clinical tasks—these are not only restricted by temporal constraints from CPGs (e.g., sequential relations, task durations) but also by CPG integration efforts (e.g., avoid treatment overlap). This poses a complex execution-time challenge and makes it difficult to determine an up-to-date, optimal comorbid care plan. We present a solution for dynamic integration of CPG in response to evolving health profiles and execution-time events. CPG integration policies are formulated by clinical experts for coping with comorbidity at execution-time, with clearly defined integration semantics that build on Description and Transaction Logics. A dynamic planning approach reconciles temporal constraints of CPG tasks at execution-time based on their importance, and continuously updates an optimal task schedule.},
keywords = {Clinical guidelines, Comorbidity, Decision Support Systems},
pubstate = {published},
tppubtype = {article}
}
In case of comorbidity, i.e., multiple medical conditions, Clinical Decision Support Systems (CDSS) should issue recommendations based on all relevant disease-related Clinical Practice Guidelines (CPG). However, treatments from multiple comorbid CPG often interact adversely (e.g., drug-drug interactions) or introduce operational inefficiencies (e.g., redundant scans). A common solution is the a-priori integration of computerized CPG, which involves integration decisions such as discarding, replacing or delaying clinical tasks (e.g., treatments) to avoid adverse interactions or inefficiencies. We argue this insufficiently deals with execution-time events: as the patient's health profile evolves, acute conditions occur, and real-time delays take place, new CPG integration decisions will often be needed, and prior ones may need to be reverted or undone. Any realistic CPG integration effort needs to further consider temporal aspects of clinical tasks—these are not only restricted by temporal constraints from CPGs (e.g., sequential relations, task durations) but also by CPG integration efforts (e.g., avoid treatment overlap). This poses a complex execution-time challenge and makes it difficult to determine an up-to-date, optimal comorbid care plan. We present a solution for dynamic integration of CPG in response to evolving health profiles and execution-time events. CPG integration policies are formulated by clinical experts for coping with comorbidity at execution-time, with clearly defined integration semantics that build on Description and Transaction Logics. A dynamic planning approach reconciles temporal constraints of CPG tasks at execution-time based on their importance, and continuously updates an optimal task schedule.
William Van Woensel; Manal Elnenaei; Syed Ali Imran; Syed Sibte Raza Abidi
Semantic Web Framework to Computerize Staged Reflex Testing Protocols to Mitigate Underutilization of Pathology Tests for Diagnosing Pituitary Disorders Inproceedings
In: International Conference on Artificial Intelligence in Medicine (AIME), 2021.
BibTeX | Tags: Clinical Decision Support Systems, Reflex Protocols, Semantic Web
@inproceedings{wvw_aime_21,
title = {Semantic Web Framework to Computerize Staged Reflex Testing Protocols to Mitigate Underutilization of Pathology Tests for Diagnosing Pituitary Disorders},
author = {William Van Woensel and Manal Elnenaei and Syed Ali Imran and Syed Sibte Raza Abidi},
year = {2021},
date = {2021-06-16},
urldate = {2021-06-16},
booktitle = {International Conference on Artificial Intelligence in Medicine (AIME)},
keywords = {Clinical Decision Support Systems, Reflex Protocols, Semantic Web},
pubstate = {published},
tppubtype = {inproceedings}
}
Michael Barrett; Ali Daowd; Samina Raza Abidi; Syed Sibte Raza
A Knowledge Graph of Mechanistic Associations Between COVID-19, Diabetes Mellitus and Kidney Diseases Inproceedings
In: 31st Medical Informatics Europe (MIE2021), 2021.
BibTeX | Tags: CoVid-19, Knowledge Graphs
@inproceedings{barrett2021,
title = {A Knowledge Graph of Mechanistic Associations Between COVID-19, Diabetes Mellitus and Kidney Diseases},
author = {Michael Barrett and Ali Daowd and Samina Raza Abidi and Syed Sibte Raza},
year = {2021},
date = {2021-05-29},
booktitle = {31st Medical Informatics Europe (MIE2021)},
keywords = {CoVid-19, Knowledge Graphs},
pubstate = {published},
tppubtype = {inproceedings}
}
Aditi Nair; Syed Sibte Raza Abidi; William Van Woensel; Samina Raza Abidi
Ontology-based Personalized Cognitive Behavioural Plans for Patients with Mild Depression Inproceedings
In: 31st Medical Informatics Europe (MIE2021), pp. 729-733, 2021.
Links | BibTeX | Tags: Behavioural Change Theory, Ontology Engineering
@inproceedings{nair2021,
title = {Ontology-based Personalized Cognitive Behavioural Plans for Patients with Mild Depression},
author = {Aditi Nair and Syed Sibte Raza Abidi and William Van Woensel and Samina Raza Abidi},
url = {https://doi.org/10.3233/shti210268},
year = {2021},
date = {2021-05-29},
urldate = {2021-05-29},
booktitle = {31st Medical Informatics Europe (MIE2021)},
pages = {729-733},
keywords = {Behavioural Change Theory, Ontology Engineering},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Chad Armstrong; Malavan Rajaratnam; Vaibhav Gupta; Syed Sibte Raza Abidi
Using Knowledge Graphs to Plausibly Infer Missing Associations in EMR Data Inproceedings
In: 31st Medical Informatics Europe (MIE2021), pp. 417-421, 2021.
Links | BibTeX | Tags: Clinical Decision Support Systems, Knowledge Graphs, Plausible reasoning, Semantic Similarity
@inproceedings{wvw_mie21_1,
title = {Using Knowledge Graphs to Plausibly Infer Missing Associations in EMR Data},
author = {William Van Woensel and Chad Armstrong and Malavan Rajaratnam and Vaibhav Gupta and Syed Sibte Raza Abidi},
url = {https://doi.org/10.3233/shti210192},
year = {2021},
date = {2021-05-29},
urldate = {2021-05-29},
booktitle = {31st Medical Informatics Europe (MIE2021)},
pages = {417-421},
keywords = {Clinical Decision Support Systems, Knowledge Graphs, Plausible reasoning, Semantic Similarity},
pubstate = {published},
tppubtype = {inproceedings}
}
Ali Daowd; Michael Barrett; Samina Raza Abidi; Syed Sibte Raza Abidi
Building a Knowledge Graph Representing Causal Associations between Risk Factors and Incidence of Breast Cancer Inproceedings
In: 31st Medical Informatics Europe (MIE2021), 2021.
BibTeX | Tags: Knowledge Graphs, Risk Factors
@inproceedings{daowd2021,
title = {Building a Knowledge Graph Representing Causal Associations between Risk Factors and Incidence of Breast Cancer},
author = {Ali Daowd and Michael Barrett and Samina Raza Abidi and Syed Sibte Raza Abidi},
year = {2021},
date = {2021-05-29},
booktitle = {31st Medical Informatics Europe (MIE2021)},
keywords = {Knowledge Graphs, Risk Factors},
pubstate = {published},
tppubtype = {inproceedings}
}
Jaber Rad; Jason Quinn; Calvino Cheng; Robert Liwski; Samina Raza Abidi; Syed Sibte Raza Abidi
Using Interactive Visual Analytics to Optimize in Real-Time Blood Products Inventory at a Blood Bank Inproceedings
In: 31st Medical Informatics Europe (MIE2021), 2021.
BibTeX | Tags: Blood Inventory Management, Clinical Decision Support Systems, Visual analytics
@inproceedings{rad2021,
title = {Using Interactive Visual Analytics to Optimize in Real-Time Blood Products Inventory at a Blood Bank},
author = {Jaber Rad and Jason Quinn and Calvino Cheng and Robert Liwski and Samina Raza Abidi and Syed Sibte Raza Abidi},
year = {2021},
date = {2021-05-29},
urldate = {2021-05-29},
booktitle = {31st Medical Informatics Europe (MIE2021)},
keywords = {Blood Inventory Management, Clinical Decision Support Systems, Visual analytics},
pubstate = {published},
tppubtype = {inproceedings}
}
Syed Asil Ali Naqvi; Karthik Tennankore; Amanda Vinson; Syed Sibte Raza Abidi
Analyzing Association Rules for Graft Failure Following Deceased and Live Donor Kidney Transplantation Inproceedings
In: 31st Medical Informatics Europe (MIE2021), 2021.
BibTeX | Tags: Association Rules, Machine Learning
@inproceedings{naqvi2021,
title = {Analyzing Association Rules for Graft Failure Following Deceased and Live Donor Kidney Transplantation},
author = {Syed Asil Ali Naqvi and Karthik Tennankore and Amanda Vinson and Syed Sibte Raza Abidi},
year = {2021},
date = {2021-05-29},
booktitle = {31st Medical Informatics Europe (MIE2021)},
keywords = {Association Rules, Machine Learning},
pubstate = {published},
tppubtype = {inproceedings}
}
2020
Azra Naseem; Kiran Qasim Ali; Audrey Juma; Afroz Sajwani; Basnama Ayaz Khan; Saleem Sayani; Syed Sibte Raza Abidi
Factors enabling and hindering an eLearning programme for nurses and midwives in Afghanistan Journal Article
In: Scholarship of Teaching and Learning in the South, 4 (2), pp. 80, 2020, ISSN: 2523-1154.
Abstract | Links | BibTeX | Tags: eLearning, Learning technology
@article{Naseem2020,
title = {Factors enabling and hindering an eLearning programme for nurses and midwives in Afghanistan},
author = {Azra Naseem and Kiran {Qasim Ali} and Audrey Juma and Afroz Sajwani and Basnama Ayaz Khan and Saleem Sayani and Syed Sibte Raza Abidi},
url = {https://sotl-south-journal.net/?journal=sotls&page=article&op=view&path%5B%5D=106},
doi = {10.36615/sotls.v4i2.106},
issn = {2523-1154},
year = {2020},
date = {2020-09-01},
journal = {Scholarship of Teaching and Learning in the South},
volume = {4},
number = {2},
pages = {80},
abstract = {textlessptextgreaterAfghanistan faces an acute shortage of trained healthcare providers. To build capacity of nurses and midwives, in 2014 a private hospital in Afghanistan initiated an eLearning programme to enhance their knowledge and skills. The study was conducted to identify facilitating and hindering factors for the successful implementation of eLearning. Data collection took place between June and September 2016, when seven Maternal and Child Health (MNCH) related eLearning sessions were conducted. The participants were nurses and midwives working in MNCH wards at the research sites in Bamyan, Faizabad and Kandahar, along with the programme planners and facilitators. Data was collected through pre/post and delayed post-tests, observations and questionnaires, semi-structured interviews and documents analysis. The results highlight four major factors as important for the successful implementation of eLearning, namely: curriculum, context, technology and individual. The needs assessment ensured relevance of the sessions to the needs of the participants. However, pedagogy was lecture-based with limited focus on skills development. Poor connectivity and language of instruction posed challenges. eLearning has shown the potential for developing knowledge and skills of nurses and midwives. Clear communication between teams involved in planning and implementation of the programme, technology infrastructure, design of online pedagogy and facilitator readiness are critical for the success of eLearning in low and middle income countries.
Keywords: Health care providers/system, eLearning Programme, Nurses, Midwives, Maternal and child careHow to cite this article:Naseem, A., Ali, K.Q., Juma, A., Sajwani, A., Khan, B.A., Sayani, A. & Abidi, S.S.R. 2020. Factors enabling and hindering an eLearning programme for nurses and midwives in Afghanistan. Scholarship of Teaching and Learning in the South. 4(2): 80-99. https://doi.org/10.36615/sotls.v4i2.106.This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/textless/ptextgreater},
keywords = {eLearning, Learning technology},
pubstate = {published},
tppubtype = {article}
}
textlessptextgreaterAfghanistan faces an acute shortage of trained healthcare providers. To build capacity of nurses and midwives, in 2014 a private hospital in Afghanistan initiated an eLearning programme to enhance their knowledge and skills. The study was conducted to identify facilitating and hindering factors for the successful implementation of eLearning. Data collection took place between June and September 2016, when seven Maternal and Child Health (MNCH) related eLearning sessions were conducted. The participants were nurses and midwives working in MNCH wards at the research sites in Bamyan, Faizabad and Kandahar, along with the programme planners and facilitators. Data was collected through pre/post and delayed post-tests, observations and questionnaires, semi-structured interviews and documents analysis. The results highlight four major factors as important for the successful implementation of eLearning, namely: curriculum, context, technology and individual. The needs assessment ensured relevance of the sessions to the needs of the participants. However, pedagogy was lecture-based with limited focus on skills development. Poor connectivity and language of instruction posed challenges. eLearning has shown the potential for developing knowledge and skills of nurses and midwives. Clear communication between teams involved in planning and implementation of the programme, technology infrastructure, design of online pedagogy and facilitator readiness are critical for the success of eLearning in low and middle income countries. Keywords: Health care providers/system, eLearning Programme, Nurses, Midwives, Maternal and child careHow to cite this article:Naseem, A., Ali, K.Q., Juma, A., Sajwani, A., Khan, B.A., Sayani, A. & Abidi, S.S.R. 2020. Factors enabling and hindering an eLearning programme for nurses and midwives in Afghanistan. Scholarship of Teaching and Learning in the South. 4(2): 80-99. https://doi.org/10.36615/sotls.v4i2.106.This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/textless/ptextgreater
Jaber Rad; Calvino Cheng; Jason G Quinn; Samina Abidi; Robert Liwski; Syed Sibte Raza Abidi
An AI-Driven Predictive Modelling Framework to Analyze and Visualize Blood Product Transactional Data for Reducing Blood Products’ Discards Inproceedings
In: International Conference on Artificial Intelligence in Medicine (AIME 2020), 2020.
Abstract | BibTeX | Tags: Big Data, Blood Inventory Management, Blood product wastage, Data visualization, Machine Learning, Sequence prediction, Visual analytics
@inproceedings{JRAD2020,
title = {An AI-Driven Predictive Modelling Framework to Analyze and Visualize Blood Product Transactional Data for Reducing Blood Products’ Discards},
author = {Jaber Rad and Calvino Cheng and Jason G Quinn and Samina Abidi and Robert Liwski and Syed Sibte Raza Abidi},
year = {2020},
date = {2020-08-01},
urldate = {2020-08-01},
booktitle = {International Conference on Artificial Intelligence in Medicine (AIME 2020)},
abstract = {Maintaining an equilibrium between shortage and wastage in blood inventories is challenging due to the perishable nature of blood products. Re-search in blood product inventory management has predominantly focused on reducing wastage due to outdates (i.e. expiry of the blood product), whereas wast-age due to discards, related to the lifecycle of a blood product, is not well investigated. In this study, we investigate machine learning methods to analyze blood product transition sequences in a large real-life transactional dataset of Red Blood Cells (RBC) to predict potential blood product discard. Our prediction models are able to predict with 79% accuracy potential discards based on the blood product’s current transaction data. We applied advanced data visualizations methods to develop an interactive blood inventory dashboard to help laboratory managers to probe blood units’ lifecycles to identify discard causes.},
keywords = {Big Data, Blood Inventory Management, Blood product wastage, Data visualization, Machine Learning, Sequence prediction, Visual analytics},
pubstate = {published},
tppubtype = {inproceedings}
}
Maintaining an equilibrium between shortage and wastage in blood inventories is challenging due to the perishable nature of blood products. Re-search in blood product inventory management has predominantly focused on reducing wastage due to outdates (i.e. expiry of the blood product), whereas wast-age due to discards, related to the lifecycle of a blood product, is not well investigated. In this study, we investigate machine learning methods to analyze blood product transition sequences in a large real-life transactional dataset of Red Blood Cells (RBC) to predict potential blood product discard. Our prediction models are able to predict with 79% accuracy potential discards based on the blood product’s current transaction data. We applied advanced data visualizations methods to develop an interactive blood inventory dashboard to help laboratory managers to probe blood units’ lifecycles to identify discard causes.
William Van Woensel; Samina Abidi; Borna Jafarpour; Syed Sibte Raza Abidi
A CIG Integration Framework to Provide Decision Support for Comorbid Conditions using Transaction-based Semantics and Temporal Planning Inproceedings
In: International Conference on Artificial Intelligence in Medicine (AIME 2020), 2020.
Abstract | BibTeX | Tags: Clinical Decision Support Systems, Clinical Practice Guidelines, Comorbidities, Ontology, Semantic Web
@inproceedings{VANWOENSEL2020-COCIG1,
title = {A CIG Integration Framework to Provide Decision Support for Comorbid Conditions using Transaction-based Semantics and Temporal Planning},
author = {William Van Woensel and Samina Abidi and Borna Jafarpour and Syed Sibte Raza Abidi},
year = {2020},
date = {2020-08-01},
urldate = {2020-08-01},
booktitle = {International Conference on Artificial Intelligence in Medicine (AIME 2020)},
abstract = {Managing comorbid conditions, i.e., patients with multiple medical conditions, is quite challenging for Clinical Decision Support Systems (CDSS) based on computerized Clinical Practice Guidelines (CPG). In case of comorbidity, CDSS will need to recommend treatments from multiple different CPG, which may adversely interact (e.g., drug-disease interactions), or introduce inefficiencies. A-priori, static integration of computerized comorbid CPG is insufficient for clinical practice. In this paper, we present a solution for dynamic integration of CPG in response to evolving health profiles. Using Description and Transaction Logics, we define a set of CIG integration semantics for encoding integration decisions that cope with comorbidity issues at execution-time. These dynamic, transaction-based semantics are well-suited to roll back prior decisions when no longer safe or efficient; or, inversely, apply new decisions when relevant. Moreover, comorbid CIG integration should consider temporal properties of CIG tasks—at execution-time, these properties will be influenced by a range of temporal constraints. Given all temporal constraints, optimal task schedules will be calculated that will determine the feasibility of CIG integration decisions.},
keywords = {Clinical Decision Support Systems, Clinical Practice Guidelines, Comorbidities, Ontology, Semantic Web},
pubstate = {published},
tppubtype = {inproceedings}
}
Managing comorbid conditions, i.e., patients with multiple medical conditions, is quite challenging for Clinical Decision Support Systems (CDSS) based on computerized Clinical Practice Guidelines (CPG). In case of comorbidity, CDSS will need to recommend treatments from multiple different CPG, which may adversely interact (e.g., drug-disease interactions), or introduce inefficiencies. A-priori, static integration of computerized comorbid CPG is insufficient for clinical practice. In this paper, we present a solution for dynamic integration of CPG in response to evolving health profiles. Using Description and Transaction Logics, we define a set of CIG integration semantics for encoding integration decisions that cope with comorbidity issues at execution-time. These dynamic, transaction-based semantics are well-suited to roll back prior decisions when no longer safe or efficient; or, inversely, apply new decisions when relevant. Moreover, comorbid CIG integration should consider temporal properties of CIG tasks—at execution-time, these properties will be influenced by a range of temporal constraints. Given all temporal constraints, optimal task schedules will be calculated that will determine the feasibility of CIG integration decisions.
Ignacio Miralles; Carlos Granell; Laura Díaz-Sanahuja; William Van Woensel; Juana Bretón-López; Adriana Mira; Diana Castilla; Sven Casteleyn
Smartphone Apps for the Treatment of Mental Disorders: Systematic Review Journal Article
In: JMIR Mhealth Uhealth, 8 (4), pp. e14897, 2020, ISSN: 2291-5222.
Abstract | Links | BibTeX | Tags: mental health; mental disorders; treatment; intervention; mHealth; smartphone; mobile phone; mobile apps; systematic review
@article{info:doi/10.2196/14897,
title = {Smartphone Apps for the Treatment of Mental Disorders: Systematic Review},
author = {Ignacio Miralles and Carlos Granell and Laura Díaz-Sanahuja and William Van Woensel and Juana Bretón-López and Adriana Mira and Diana Castilla and Sven Casteleyn},
url = {http://www.ncbi.nlm.nih.gov/pubmed/32238332},
doi = {10.2196/14897},
issn = {2291-5222},
year = {2020},
date = {2020-04-02},
journal = {JMIR Mhealth Uhealth},
volume = {8},
number = {4},
pages = {e14897},
abstract = {Background: Smartphone apps are an increasingly popular means for delivering psychological interventions to patients suffering from a mental disorder. In line with this popularity, there is a need to analyze and summarize the state of the art, both from a psychological and technical perspective. Objective: This study aimed to systematically review the literature on the use of smartphones for psychological interventions. Our systematic review has the following objectives: (1) analyze the coverage of mental disorders in research articles per year; (2) study the types of assessment in research articles per mental disorder per year; (3) map the use of advanced technical features, such as sensors, and novel software features, such as personalization and social media, per mental disorder; (4) provide an overview of smartphone apps per mental disorder; and (5) provide an overview of the key characteristics of empirical assessments with rigorous designs (ie, randomized controlled trials [RCTs]). Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for systematic reviews were followed. We performed searches in Scopus, Web of Science, American Psychological Association PsycNET, and Medical Literature Analysis and Retrieval System Online, covering a period of 6 years (2013-2018). We included papers that described the use of smartphone apps to deliver psychological interventions for known mental disorders. We formed multidisciplinary teams, comprising experts in psychology and computer science, to select and classify articles based on psychological and technical features. Results: We found 158 articles that met the inclusion criteria. We observed an increasing interest in smartphone-based interventions over time. Most research targeted disorders with high prevalence, that is, depressive (31/158,19.6%) and anxiety disorders (18/158, 11.4%). Of the total, 72.7% (115/158) of the papers focused on six mental disorders: depression, anxiety, trauma and stressor-related, substance-related and addiction, schizophrenia spectrum, and other psychotic disorders, or a combination of disorders. More than half of known mental disorders were not or very scarcely (<3%) represented. An increasing number of studies were dedicated to assessing clinical effects, but RCTs were still a minority (25/158, 15.8%). From a technical viewpoint, interventions were leveraging the improved modalities (screen and sound) and interactivity of smartphones but only sparingly leveraged their truly novel capabilities, such as sensors, alternative delivery paradigms, and analytical methods. Conclusions: There is a need for designing interventions for the full breadth of mental disorders, rather than primarily focusing on most prevalent disorders. We further contend that an increasingly systematic focus, that is, involving RCTs, is needed to improve the robustness and trustworthiness of assessments. Regarding technical aspects, we argue that further exploration and innovative use of the novel capabilities of smartphones are needed to fully realize their potential for the treatment of mental health disorders.},
keywords = {mental health; mental disorders; treatment; intervention; mHealth; smartphone; mobile phone; mobile apps; systematic review},
pubstate = {published},
tppubtype = {article}
}
Background: Smartphone apps are an increasingly popular means for delivering psychological interventions to patients suffering from a mental disorder. In line with this popularity, there is a need to analyze and summarize the state of the art, both from a psychological and technical perspective. Objective: This study aimed to systematically review the literature on the use of smartphones for psychological interventions. Our systematic review has the following objectives: (1) analyze the coverage of mental disorders in research articles per year; (2) study the types of assessment in research articles per mental disorder per year; (3) map the use of advanced technical features, such as sensors, and novel software features, such as personalization and social media, per mental disorder; (4) provide an overview of smartphone apps per mental disorder; and (5) provide an overview of the key characteristics of empirical assessments with rigorous designs (ie, randomized controlled trials [RCTs]). Methods: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for systematic reviews were followed. We performed searches in Scopus, Web of Science, American Psychological Association PsycNET, and Medical Literature Analysis and Retrieval System Online, covering a period of 6 years (2013-2018). We included papers that described the use of smartphone apps to deliver psychological interventions for known mental disorders. We formed multidisciplinary teams, comprising experts in psychology and computer science, to select and classify articles based on psychological and technical features. Results: We found 158 articles that met the inclusion criteria. We observed an increasing interest in smartphone-based interventions over time. Most research targeted disorders with high prevalence, that is, depressive (31/158,19.6%) and anxiety disorders (18/158, 11.4%). Of the total, 72.7% (115/158) of the papers focused on six mental disorders: depression, anxiety, trauma and stressor-related, substance-related and addiction, schizophrenia spectrum, and other psychotic disorders, or a combination of disorders. More than half of known mental disorders were not or very scarcely (<3%) represented. An increasing number of studies were dedicated to assessing clinical effects, but RCTs were still a minority (25/158, 15.8%). From a technical viewpoint, interventions were leveraging the improved modalities (screen and sound) and interactivity of smartphones but only sparingly leveraged their truly novel capabilities, such as sensors, alternative delivery paradigms, and analytical methods. Conclusions: There is a need for designing interventions for the full breadth of mental disorders, rather than primarily focusing on most prevalent disorders. We further contend that an increasingly systematic focus, that is, involving RCTs, is needed to improve the robustness and trustworthiness of assessments. Regarding technical aspects, we argue that further exploration and innovative use of the novel capabilities of smartphones are needed to fully realize their potential for the treatment of mental health disorders.
William Van Woensel; Patrice C Roy; Syed Sibte Raza Abidi; Samina Raza Abidi
Indoor location identification of patients for directing virtual care: An AI approach using machine learning and knowledge-based methods Journal Article
In: Artificial Intelligence in Medicine, 108 , pp. 101931, 2020, ISSN: 0933-3657.
Abstract | Links | BibTeX | Tags: Activities of daily living, Ambient assisted living, Ambient Intelligence, Ambient sensors, Chronic disease self-management, Data fusion, eHealth Platform, Indoor Localization, Machine Learning, Self-Management, Semantic Web, Virtual care
@article{VANWOENSEL2020101931,
title = {Indoor location identification of patients for directing virtual care: An AI approach using machine learning and knowledge-based methods},
author = {William Van Woensel and Patrice C Roy and Syed Sibte Raza Abidi and Samina Raza Abidi},
url = {http://www.sciencedirect.com/science/article/pii/S0933365720301275
https://authors.elsevier.com/a/1bTwR3KEGaD3xR},
doi = {https://doi.org/10.1016/j.artmed.2020.101931},
issn = {0933-3657},
year = {2020},
date = {2020-01-01},
journal = {Artificial Intelligence in Medicine},
volume = {108},
pages = {101931},
abstract = {In a digitally enabled healthcare setting, we posit that an individual’s current location is pivotal for supporting many virtual care services—such as tailoring educational content towards an individual’s current location, and, hence, current stage in an acute care process; improving activity recognition for supporting self-management in a home-based setting; and guiding individuals with cognitive decline through daily activities in their home. However, unobtrusively estimating an individual’s indoor location in real-world care settings is still a challenging problem. Moreover, the needs of location-specific care interventions go beyond absolute coordinates and require the individual’s discrete semantic location; i.e., it is the concrete type of an individual’s location (e.g., exam vs. waiting room; bathroom vs. kitchen) that will drive the tailoring of educational content or recognition of activities. We utilized Machine Learning methods to accurately identify an individual’s discrete location, together with knowledge-based models and tools to supply the associated semantics of identified locations. We considered clustering solutions to improve localization accuracy at the expense of granularity; and investigate sensor fusion-based heuristics to rule out false location estimates. We present an AI-driven indoor localization approach that integrates both data-driven and knowledge-based processes and artifacts. We illustrate the application of our approach in two compelling healthcare use cases, and empirically validated our localization approach at the emergency unit of a large Canadian pediatric hospital.},
keywords = {Activities of daily living, Ambient assisted living, Ambient Intelligence, Ambient sensors, Chronic disease self-management, Data fusion, eHealth Platform, Indoor Localization, Machine Learning, Self-Management, Semantic Web, Virtual care},
pubstate = {published},
tppubtype = {article}
}
In a digitally enabled healthcare setting, we posit that an individual’s current location is pivotal for supporting many virtual care services—such as tailoring educational content towards an individual’s current location, and, hence, current stage in an acute care process; improving activity recognition for supporting self-management in a home-based setting; and guiding individuals with cognitive decline through daily activities in their home. However, unobtrusively estimating an individual’s indoor location in real-world care settings is still a challenging problem. Moreover, the needs of location-specific care interventions go beyond absolute coordinates and require the individual’s discrete semantic location; i.e., it is the concrete type of an individual’s location (e.g., exam vs. waiting room; bathroom vs. kitchen) that will drive the tailoring of educational content or recognition of activities. We utilized Machine Learning methods to accurately identify an individual’s discrete location, together with knowledge-based models and tools to supply the associated semantics of identified locations. We considered clustering solutions to improve localization accuracy at the expense of granularity; and investigate sensor fusion-based heuristics to rule out false location estimates. We present an AI-driven indoor localization approach that integrates both data-driven and knowledge-based processes and artifacts. We illustrate the application of our approach in two compelling healthcare use cases, and empirically validated our localization approach at the emergency unit of a large Canadian pediatric hospital.
Eseohen Imoukhome; Lori Weeks; Samina Abidi
Fall Prevention and Management App Prototype for the Elderly and Their Caregivers: Design, Implementation, and Evaluation Journal Article
In: International Journal of Extreme Automation and Connectivity in Healthcare, 2 , pp. 48-67, 2020.
@article{article,
title = {Fall Prevention and Management App Prototype for the Elderly and Their Caregivers: Design, Implementation, and Evaluation},
author = {Eseohen Imoukhome and Lori Weeks and Samina Abidi},
doi = {10.4018/IJEACH.2020010104},
year = {2020},
date = {2020-01-01},
journal = {International Journal of Extreme Automation and Connectivity in Healthcare},
volume = {2},
pages = {48-67},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2019
Benjamin Rose-Davis; William Van Woensel; Elizabeth Stringer; Samina Raza Abidi; Syed Sibte Raza Abidi
In: 17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30, pp. 1337 - 1341, Lyon, France, 2019.
@inproceedings{Rose-Davis2019,
title = {Using Artificial Intelligence-Based Argument Theory To Generate Automated Patient Education Dialogues For Families Of Children With Juvenile Idiopathic Arthritis},
author = {Benjamin Rose-Davis and William Van Woensel and Elizabeth Stringer and Samina Raza Abidi and Syed Sibte Raza Abidi},
url = {http://ebooks.iospress.nl/publication/52209},
doi = {10.3233/SHTI190444},
year = {2019},
date = {2019-08-26},
booktitle = {17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30},
volume = {264},
pages = {1337 - 1341},
address = {Lyon, France},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Raquel da Luz Diaz; Marcela de Oliveira Lima; João G B Alves; William Van Woensel; Asil Naqvi; Zahra Take; Syed Sibte Raza Abidi
A Digital Health Platform to Deliver Tailored Early Stimulation Programs for Children With Developmental Delay Inproceedings
In: 17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30, pp. 571 - 575, IOS Press, Lyon, France, 2019.
@inproceedings{DaLuzDiaz2019,
title = {A Digital Health Platform to Deliver Tailored Early Stimulation Programs for Children With Developmental Delay},
author = {Raquel da Luz Diaz and Marcela de Oliveira Lima and João G B Alves and William Van Woensel and Asil Naqvi and Zahra Take and Syed Sibte Raza Abidi},
url = {http://ebooks.iospress.nl/publication/52052},
doi = {10.3233/SHTI190287},
year = {2019},
date = {2019-08-26},
booktitle = {17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30},
volume = {264},
pages = {571 - 575},
publisher = {IOS Press},
address = {Lyon, France},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Samina Raza Abidi; Borna Jafarpour; Syed Sibte Raza Abidi
In: 17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30, pp. 858 - 862, IOS Press, Lyon, France, 2019.
@inproceedings{VanWoensel2019a,
title = {Providing Comorbid Decision Support via the Integration of Clinical Practice Guidelines at Execution-Time by Leveraging Medical Linked Open Datasets},
author = {William Van Woensel and Samina Raza Abidi and Borna Jafarpour and Syed Sibte Raza Abidi},
url = {http://ebooks.iospress.nl/publication/52110},
doi = {10.3233/SHTI190345},
year = {2019},
date = {2019-08-26},
booktitle = {17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30},
volume = {264},
pages = {858 - 862},
publisher = {IOS Press},
address = {Lyon, France},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Ali Daowd; Syed M Faizan; Samina Raza Abidi; Ashraf Abusharekh; A Shehzad; Syed Sibte Raza Abidi
Towards Personalized Lifetime Health: A Platform for Early Multimorbid Chronic Disease Risk Assessment and Mitigation Inproceedings
In: 17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30, pp. 935 - 939, Lyon, France, 2019.
@inproceedings{Daowd2019,
title = {Towards Personalized Lifetime Health: A Platform for Early Multimorbid Chronic Disease Risk Assessment and Mitigation},
author = {Ali Daowd and Syed M Faizan and Samina Raza Abidi and Ashraf Abusharekh and A Shehzad and Syed Sibte Raza Abidi},
url = {http://ebooks.iospress.nl/publication/52126},
doi = {10.3233/SHTI190361},
year = {2019},
date = {2019-08-26},
booktitle = {17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30},
volume = {264},
pages = {935 - 939},
address = {Lyon, France},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
William Van Woensel; Samina Raza Abidi; Syed Sibte Raza Abidi
Pro-Actively Guiding Patients through ADL via Knowledge-Based and Context-Driven Activity Recognition Inproceedings
In: 17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30, pp. 863 - 867, IOS Press, Lyon, France, 2019.
@inproceedings{VanWoensel2019,
title = {Pro-Actively Guiding Patients through ADL via Knowledge-Based and Context-Driven Activity Recognition},
author = {William Van Woensel and Samina Raza Abidi and Syed Sibte Raza Abidi},
url = {http://ebooks.iospress.nl/publication/52111},
doi = {10.3233/SHTI190346},
year = {2019},
date = {2019-08-26},
booktitle = {17th World Congress on Medical and Health Informatics (MEDINFO'19), Aug 26-30},
volume = {264},
pages = {863 - 867},
publisher = {IOS Press},
address = {Lyon, France},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Patrice C. Roy; William Van Woensel; Andy Wilcox; Syed Sibte Raza Abidi
In: 17th Conf. on Artificial Intelligence in Medicine (AIME2019), June 26-29, pp. 216–226, Springer International Publishing, Poznan, Poland, 2019, ISBN: 978-3-030-21642-9.
@inproceedings{Roy2019,
title = {Mobile Indoor Localization with Bluetooth Beacons in a Pediatric Emergency Department Using Clustering, Rule-based Classification and High-level Heuristics},
author = {Patrice C. Roy and William Van Woensel and Andy Wilcox and Syed Sibte Raza Abidi},
url = {https://link.springer.com/chapter/10.1007/978-3-030-21642-9_27},
doi = {10.1007/978-3-030-21642-9_27},
isbn = {978-3-030-21642-9},
year = {2019},
date = {2019-06-26},
booktitle = {17th Conf. on Artificial Intelligence in Medicine (AIME2019), June 26-29},
pages = {216--226},
publisher = {Springer International Publishing},
address = {Poznan, Poland},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Syed Sibte Raza Abidi; Jaber Rad; Ashraf Abusharekh; Patrice C. Roy; William Van Woensel; Samina Raza Abidi; Calvino Cheng; Bryan D. Crocker; Manal O. Elnenaei
AI-Driven Pathology Laboratory Utilization Management via Data- and Knowledge-Based Analytics Inproceedings
In: 17th Conf. on Artificial Intelligence in Medicine (AIME2019), June 26-29, pp. 241–251, Springer International Publishing, Poznan, Poland, 2019, ISBN: 978-3-030-21642-9.
@inproceedings{Abidi2019,
title = {AI-Driven Pathology Laboratory Utilization Management via Data- and Knowledge-Based Analytics},
author = {Syed Sibte Raza Abidi and Jaber Rad and Ashraf Abusharekh and Patrice C. Roy and William Van Woensel and Samina Raza Abidi and Calvino Cheng and Bryan D. Crocker and Manal O. Elnenaei},
url = {https://link.springer.com/chapter/10.1007/978-3-030-21642-9_30},
doi = {10.1007/978-3-030-21642-9_30},
isbn = {978-3-030-21642-9},
year = {2019},
date = {2019-06-26},
booktitle = {17th Conf. on Artificial Intelligence in Medicine (AIME2019), June 26-29},
pages = {241--251},
publisher = {Springer International Publishing},
address = {Poznan, Poland},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kathryn Young-Shand; Patrice C. Roy; Syed Sibte Raza Abidi; Michael Dunbar; Janie Astephen Wilson
Clinical and Biomechanical Cluster Classification Before TKA Impacts Functional Outcome Inproceedings
In: 2nd International Combined Meeting of Orthopaedic Research Societies, June 19-22, 2019, Montreal, Canada, 2019.
Abstract | BibTeX | Tags: Clustering, Total knee arthroplasty
@inproceedings{Young-Shand2019b,
title = {Clinical and Biomechanical Cluster Classification Before TKA Impacts Functional Outcome},
author = {Kathryn Young-Shand and Patrice C. Roy and Syed Sibte Raza Abidi and Michael Dunbar and Janie Astephen Wilson},
year = {2019},
date = {2019-06-19},
booktitle = {2nd International Combined Meeting of Orthopaedic Research Societies, June 19-22, 2019, Montreal, Canada},
abstract = {Purpose:
Identifying knee osteoarthritis (OA) patient phenotypes is relevant to assessing treatment efficacy, yet biomechanical variability has not been applied to phenotyping. This study aimed to identify demographic and gait related groups (clusters) among total knee arthroplasty (TKA) candidates, and examine inter-cluster differences in gait feature improvement post-TKA.
Method:
Knee OA patients scheduled for TKA underwent three-dimensional gait analysis one-week pre and one-year post-TKA, capturing lower-limb external ground reaction forces and kinematics using a force platform and optoelectronic motion capture. Principal component analysis was applied to frontal and sagittal knee angle and moment waveforms (n=135 pre-TKA, n=106 post-TKA), resulting in a new uncorrelated dataset of subject PCscores and PC vectors, describing major modes of variability throughout one gait cycle (0-100%). Demographics (age, gender, body mass index (BMI), gait speed), and gait angle and moment PCscores were standardized and assessed for outliers. One patient exceeding Tukey’s outer (3*IQR) fence was removed. Two-dimensional multidimensional scaling followed by k-medoids clustering was applied to scaled demographics and pre-TKA PCscores [134x15]. Number of clusters (k=2:10) were assessed by silhouette coefficients, s, and stability by Adjusted Rand Indices (ARI) of 100 data subsets. Clusters were validated by examining inter-cluster differences at baseline, and inter-cluster gait changes (PostPCscore–PrePCscore, n=105) by k-way ANOVA and Tukey's honestly significant difference (HSD) criterion.
Results:
Four (k=4) TKA candidate groups yielded optimum clustering metrics (s=0.4, ARI=0.75). Cluster 1 was all-males (male:female=19:0) who walked with faster gait speeds (1>2,3), larger flexion angle magnitudes and stance-phase angle range (PC1 & PC4 1>2,3,4), and more flexion (PC2 1>2,3,4) and adduction moment (PC2 & PC3 1>2,3) range patterns. Cluster 1 had the most dynamic kinematics and kinetic loading/unloading range amongst the clusters, representing a higher-functioning (less “stiff”) male subset. Cluster 2 captured older (2>1,3) males (31:1) with slower gait speeds (2<1,4), and less flexion moment (PC2 2<1,4) and adduction moment (PC2 2<1,4) range, describing an older, stiff-gait male subset. Cluster 3 was mostly (4:36) females with slower gait speeds (3<1,4), higher BMIs (3>4), and lower flexion angle magnitude (PC1 3<1,2,4) and flexion moment range (PC2 3<1,2,4) features. Cluster 3 showed the “stiffest” gait amongst the clusters, representing a more-obese, stiff-gait female subset. Cluster 4 was mostly (2:41) females with faster gait speeds (4>2,3) and less stiff kinematic and kinetic patterns relative to Clusters 2 and 3, representing a higher-functioning female subset. Radiographic severity did not differ between clusters (Kellgren-Lawrence Grade, p=0.9, n=102), and after removing demographics and re-clustering, gender differences remained (p<0.04). Pre-TKA, higher-functioning clusters (1&4) had more dynamic loading/un-loading kinetic patterns. Post-TKA, high-functioning clusters experienced less gait improvement (flexion angle PC2, 1,4<3, p≥0.004; flexion moment PC2, 4<2,3), with some sagittal range patterns decreasing postoperatively.
Conclusion:
TKA candidates can be characterized by four clusters, differing by demographics and biomechanical severity features. Post-TKA, functional gains were cluster-specific; stiff-gait clusters experienced more improvement, while higher-functioning clusters experienced less gain and showed some decline. Results suggest the presence of cohorts who may not benefit functionally from TKA. Cluster profiling may support triaging and developing targeted OA treatment strategies, meeting individual function needs.},
keywords = {Clustering, Total knee arthroplasty},
pubstate = {published},
tppubtype = {inproceedings}
}
Purpose:
Identifying knee osteoarthritis (OA) patient phenotypes is relevant to assessing treatment efficacy, yet biomechanical variability has not been applied to phenotyping. This study aimed to identify demographic and gait related groups (clusters) among total knee arthroplasty (TKA) candidates, and examine inter-cluster differences in gait feature improvement post-TKA.
Method:
Knee OA patients scheduled for TKA underwent three-dimensional gait analysis one-week pre and one-year post-TKA, capturing lower-limb external ground reaction forces and kinematics using a force platform and optoelectronic motion capture. Principal component analysis was applied to frontal and sagittal knee angle and moment waveforms (n=135 pre-TKA, n=106 post-TKA), resulting in a new uncorrelated dataset of subject PCscores and PC vectors, describing major modes of variability throughout one gait cycle (0-100%). Demographics (age, gender, body mass index (BMI), gait speed), and gait angle and moment PCscores were standardized and assessed for outliers. One patient exceeding Tukey’s outer (3*IQR) fence was removed. Two-dimensional multidimensional scaling followed by k-medoids clustering was applied to scaled demographics and pre-TKA PCscores [134x15]. Number of clusters (k=2:10) were assessed by silhouette coefficients, s, and stability by Adjusted Rand Indices (ARI) of 100 data subsets. Clusters were validated by examining inter-cluster differences at baseline, and inter-cluster gait changes (PostPCscore–PrePCscore, n=105) by k-way ANOVA and Tukey's honestly significant difference (HSD) criterion.
Results:
Four (k=4) TKA candidate groups yielded optimum clustering metrics (s=0.4, ARI=0.75). Cluster 1 was all-males (male:female=19:0) who walked with faster gait speeds (1>2,3), larger flexion angle magnitudes and stance-phase angle range (PC1 & PC4 1>2,3,4), and more flexion (PC2 1>2,3,4) and adduction moment (PC2 & PC3 1>2,3) range patterns. Cluster 1 had the most dynamic kinematics and kinetic loading/unloading range amongst the clusters, representing a higher-functioning (less “stiff”) male subset. Cluster 2 captured older (2>1,3) males (31:1) with slower gait speeds (2<1,4), and less flexion moment (PC2 2<1,4) and adduction moment (PC2 2<1,4) range, describing an older, stiff-gait male subset. Cluster 3 was mostly (4:36) females with slower gait speeds (3<1,4), higher BMIs (3>4), and lower flexion angle magnitude (PC1 3<1,2,4) and flexion moment range (PC2 3<1,2,4) features. Cluster 3 showed the “stiffest” gait amongst the clusters, representing a more-obese, stiff-gait female subset. Cluster 4 was mostly (2:41) females with faster gait speeds (4>2,3) and less stiff kinematic and kinetic patterns relative to Clusters 2 and 3, representing a higher-functioning female subset. Radiographic severity did not differ between clusters (Kellgren-Lawrence Grade, p=0.9, n=102), and after removing demographics and re-clustering, gender differences remained (p<0.04). Pre-TKA, higher-functioning clusters (1&4) had more dynamic loading/un-loading kinetic patterns. Post-TKA, high-functioning clusters experienced less gait improvement (flexion angle PC2, 1,4<3, p≥0.004; flexion moment PC2, 4<2,3), with some sagittal range patterns decreasing postoperatively.
Conclusion:
TKA candidates can be characterized by four clusters, differing by demographics and biomechanical severity features. Post-TKA, functional gains were cluster-specific; stiff-gait clusters experienced more improvement, while higher-functioning clusters experienced less gain and showed some decline. Results suggest the presence of cohorts who may not benefit functionally from TKA. Cluster profiling may support triaging and developing targeted OA treatment strategies, meeting individual function needs.
Identifying knee osteoarthritis (OA) patient phenotypes is relevant to assessing treatment efficacy, yet biomechanical variability has not been applied to phenotyping. This study aimed to identify demographic and gait related groups (clusters) among total knee arthroplasty (TKA) candidates, and examine inter-cluster differences in gait feature improvement post-TKA.
Method:
Knee OA patients scheduled for TKA underwent three-dimensional gait analysis one-week pre and one-year post-TKA, capturing lower-limb external ground reaction forces and kinematics using a force platform and optoelectronic motion capture. Principal component analysis was applied to frontal and sagittal knee angle and moment waveforms (n=135 pre-TKA, n=106 post-TKA), resulting in a new uncorrelated dataset of subject PCscores and PC vectors, describing major modes of variability throughout one gait cycle (0-100%). Demographics (age, gender, body mass index (BMI), gait speed), and gait angle and moment PCscores were standardized and assessed for outliers. One patient exceeding Tukey’s outer (3*IQR) fence was removed. Two-dimensional multidimensional scaling followed by k-medoids clustering was applied to scaled demographics and pre-TKA PCscores [134x15]. Number of clusters (k=2:10) were assessed by silhouette coefficients, s, and stability by Adjusted Rand Indices (ARI) of 100 data subsets. Clusters were validated by examining inter-cluster differences at baseline, and inter-cluster gait changes (PostPCscore–PrePCscore, n=105) by k-way ANOVA and Tukey's honestly significant difference (HSD) criterion.
Results:
Four (k=4) TKA candidate groups yielded optimum clustering metrics (s=0.4, ARI=0.75). Cluster 1 was all-males (male:female=19:0) who walked with faster gait speeds (1>2,3), larger flexion angle magnitudes and stance-phase angle range (PC1 & PC4 1>2,3,4), and more flexion (PC2 1>2,3,4) and adduction moment (PC2 & PC3 1>2,3) range patterns. Cluster 1 had the most dynamic kinematics and kinetic loading/unloading range amongst the clusters, representing a higher-functioning (less “stiff”) male subset. Cluster 2 captured older (2>1,3) males (31:1) with slower gait speeds (2<1,4), and less flexion moment (PC2 2<1,4) and adduction moment (PC2 2<1,4) range, describing an older, stiff-gait male subset. Cluster 3 was mostly (4:36) females with slower gait speeds (3<1,4), higher BMIs (3>4), and lower flexion angle magnitude (PC1 3<1,2,4) and flexion moment range (PC2 3<1,2,4) features. Cluster 3 showed the “stiffest” gait amongst the clusters, representing a more-obese, stiff-gait female subset. Cluster 4 was mostly (2:41) females with faster gait speeds (4>2,3) and less stiff kinematic and kinetic patterns relative to Clusters 2 and 3, representing a higher-functioning female subset. Radiographic severity did not differ between clusters (Kellgren-Lawrence Grade, p=0.9, n=102), and after removing demographics and re-clustering, gender differences remained (p<0.04). Pre-TKA, higher-functioning clusters (1&4) had more dynamic loading/un-loading kinetic patterns. Post-TKA, high-functioning clusters experienced less gait improvement (flexion angle PC2, 1,4<3, p≥0.004; flexion moment PC2, 4<2,3), with some sagittal range patterns decreasing postoperatively.
Conclusion:
TKA candidates can be characterized by four clusters, differing by demographics and biomechanical severity features. Post-TKA, functional gains were cluster-specific; stiff-gait clusters experienced more improvement, while higher-functioning clusters experienced less gain and showed some decline. Results suggest the presence of cohorts who may not benefit functionally from TKA. Cluster profiling may support triaging and developing targeted OA treatment strategies, meeting individual function needs.
Syed Sibte Raza Abidi; Samina Raza Abidi
Intelligent health data analytics: A convergence of artificial intelligence and big data Journal Article
In: Healthcare Management Forum, 32 (4), pp. 178–182, 2019.
Abstract | Links | BibTeX | Tags:
@article{doi:10.1177/0840470419846134,
title = {Intelligent health data analytics: A convergence of artificial intelligence and big data},
author = {Syed Sibte Raza Abidi and Samina Raza Abidi},
url = {https://doi.org/10.1177/0840470419846134},
doi = {10.1177/0840470419846134},
year = {2019},
date = {2019-05-22},
journal = {Healthcare Management Forum},
volume = {32},
number = {4},
pages = {178--182},
abstract = {Healthcare is a living system that generates a significant volume of heterogeneous data. As healthcare systems are pivoting to value-based systems, intelligent and interactive analysis of health data is gaining significance for health system management, especially for resource optimization whilst improving care quality and health outcomes. Health data analytics is being influenced by new concepts and intelligent methods emanating from artificial intelligence and big data. In this article, we contextualize health data and health data analytics in terms of the emerging trends of artificial intelligence and big data. We examine the nature of health data using the big data criterion to understand “how big” is health data. Next, we explain the working of artificial intelligence–based data analytics methods and discuss “what insights” can be derived from a broad spectrum of health data analytics methods to improve health system management, health outcomes, knowledge discovery, and healthcare innovation.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Healthcare is a living system that generates a significant volume of heterogeneous data. As healthcare systems are pivoting to value-based systems, intelligent and interactive analysis of health data is gaining significance for health system management, especially for resource optimization whilst improving care quality and health outcomes. Health data analytics is being influenced by new concepts and intelligent methods emanating from artificial intelligence and big data. In this article, we contextualize health data and health data analytics in terms of the emerging trends of artificial intelligence and big data. We examine the nature of health data using the big data criterion to understand “how big” is health data. Next, we explain the working of artificial intelligence–based data analytics methods and discuss “what insights” can be derived from a broad spectrum of health data analytics methods to improve health system management, health outcomes, knowledge discovery, and healthcare innovation.
Kathryn Young-Shand; Patrice C. Roy; Syed Sibte Raza Abidi; Michael Dunbar; Janie Astephen Wilson
Clinical and Biomechanical Cluster Classification Before TKA Impacts Functional Outcome Inproceedings
In: Orthopaedic Research Society Conference (ORS), February 2-5, 2019 Austin, Texas, USA, 2019, (Recipient of the American Academy of Orthopaedic Surgeons (AAOS) Women’s Health Advisory Board (WHAB) Award).
BibTeX | Tags: Clustering, Total knee arthroplasty
@inproceedings{Young-Shand2019,
title = {Clinical and Biomechanical Cluster Classification Before TKA Impacts Functional Outcome},
author = {Kathryn Young-Shand and Patrice C. Roy and Syed Sibte Raza Abidi and Michael Dunbar and Janie Astephen Wilson},
year = {2019},
date = {2019-02-02},
booktitle = {Orthopaedic Research Society Conference (ORS), February 2-5, 2019 Austin, Texas, USA},
note = {Recipient of the American Academy of Orthopaedic Surgeons (AAOS) Women’s Health Advisory Board (WHAB) Award},
keywords = {Clustering, Total knee arthroplasty},
pubstate = {published},
tppubtype = {inproceedings}
}
Doerthe Arndt; William Van Woensel
Towards Supporting Multiple Semantics of Named Graphs Using N3 Rules Inproceedings
In: Proceedings of the 13th RuleML+RR 2019 Doctoral Consortium and Rule Challenge, September 16-19, 2019 - Bolzano, Italy, September 16-24, 2019, CEUR-WS.org, 2019.
Abstract | Links | BibTeX | Tags:
@inproceedings{DBLP:conf/ruleml/ArndtW19,
title = {Towards Supporting Multiple Semantics of Named Graphs Using N3 Rules},
author = {Doerthe Arndt and William Van Woensel},
url = {http://ceur-ws.org/Vol-2438/paper6.pdf},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 13th RuleML+RR 2019 Doctoral Consortium and Rule Challenge, September 16-19, 2019 - Bolzano, Italy, September 16-24, 2019},
volume = {2438},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
abstract = {Semantic Web applications often require the partitioning of triples into subgraphs, and then associating them with useful metadata(e.g., provenance). This led to the introduction of RDF datasets, with each RDF dataset comprising a default graph and zero or more named graphs. However, due to differences in RDF implementations, no consensus could be reached on a standard semantics; and a range of different dataset semantics are currently assumed. For an RDF system not be limited to only a subset of online RDF datasets, the system would need to be extended to support different dataset semantics—exactly the problem that eluded consensus before. In this paper, we transpose this problem to Notation3 Logic, an RDF-based rule language that similarly allows citing graphs within RDF documents. We propose a solution where an N3 author can directly indicate the intended semantics of a cited graph—possibly, combining multiple semantics within a single document. We supply an initial set of companion N3 rules, which implement a number of RDF dataset semantics, which allow an N3-compliant system to easily support multiple different semantics.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Semantic Web applications often require the partitioning of triples into subgraphs, and then associating them with useful metadata(e.g., provenance). This led to the introduction of RDF datasets, with each RDF dataset comprising a default graph and zero or more named graphs. However, due to differences in RDF implementations, no consensus could be reached on a standard semantics; and a range of different dataset semantics are currently assumed. For an RDF system not be limited to only a subset of online RDF datasets, the system would need to be extended to support different dataset semantics—exactly the problem that eluded consensus before. In this paper, we transpose this problem to Notation3 Logic, an RDF-based rule language that similarly allows citing graphs within RDF documents. We propose a solution where an N3 author can directly indicate the intended semantics of a cited graph—possibly, combining multiple semantics within a single document. We supply an initial set of companion N3 rules, which implement a number of RDF dataset semantics, which allow an N3-compliant system to easily support multiple different semantics.
Hani Nabeel Mufti; Gregory Marshal Hirsch; Samina Raza Abidi; Syed Sibte Raza Abidi
In: JMIR Med Inform, 7 (4), pp. e14993, 2019, ISSN: 2291-9694.
Abstract | Links | BibTeX | Tags: delirium; cardiac surgery; machine learning; predictive modeling
@article{info:doi/10.2196/14993,
title = {Exploiting Machine Learning Algorithms and Methods for the Prediction of Agitated Delirium After Cardiac Surgery: Models Development and Validation Study},
author = {Hani Nabeel Mufti and Gregory Marshal Hirsch and Samina Raza Abidi and Syed Sibte Raza Abidi},
url = {http://www.ncbi.nlm.nih.gov/pubmed/31558433},
doi = {10.2196/14993},
issn = {2291-9694},
year = {2019},
date = {2019-01-01},
journal = {JMIR Med Inform},
volume = {7},
number = {4},
pages = {e14993},
abstract = {Background: Delirium is a temporary mental disorder that occasionally affects patients undergoing surgery, especially cardiac surgery. It is strongly associated with major adverse events, which in turn leads to increased cost and poor outcomes (eg, need for nursing home due to cognitive impairment, stroke, and death). The ability to foresee patients at risk of delirium will guide the timely initiation of multimodal preventive interventions, which will aid in reducing the burden and negative consequences associated with delirium. Several studies have focused on the prediction of delirium. However, the number of studies in cardiac surgical patients that have used machine learning methods is very limited. Objective: This study aimed to explore the application of several machine learning predictive models that can pre-emptively predict delirium in patients undergoing cardiac surgery and compare their performance. Methods: We investigated a number of machine learning methods to develop models that can predict delirium after cardiac surgery. A clinical dataset comprising over 5000 actual patients who underwent cardiac surgery in a single center was used to develop the models using logistic regression, artificial neural networks (ANN), support vector machines (SVM), Bayesian belief networks (BBN), na"ive Bayesian, random forest, and decision trees. Results: Only 507 out of 5584 patients (11.4%) developed delirium. We addressed the underlying class imbalance, using random undersampling, in the training dataset. The final prediction performance was validated on a separate test dataset. Owing to the target class imbalance, several measures were used to evaluate algorithm's performance for the delirium class on the test dataset. Out of the selected algorithms, the SVM algorithm had the best F1 score for positive cases, kappa, and positive predictive value (40.2%, 29.3%, and 29.7%, respectively) with a P=.01, .03, .02, respectively. The ANN had the best receiver-operator area-under the curve (78.2%; P=.03). The BBN had the best precision-recall area-under the curve for detecting positive cases (30.4%; P=.03). Conclusions: Although delirium is inherently complex, preventive measures to mitigate its negative effect can be applied proactively if patients at risk are prospectively identified. Our results highlight 2 important points: (1) addressing class imbalance on the training dataset will augment machine learning model's performance in identifying patients likely to develop postoperative delirium, and (2) as the prediction of postoperative delirium is difficult because it is multifactorial and has complex pathophysiology, applying machine learning methods (complex or simple) may improve the prediction by revealing hidden patterns, which will lead to cost reduction by prevention of complications and will optimize patients' outcomes.},
keywords = {delirium; cardiac surgery; machine learning; predictive modeling},
pubstate = {published},
tppubtype = {article}
}
Background: Delirium is a temporary mental disorder that occasionally affects patients undergoing surgery, especially cardiac surgery. It is strongly associated with major adverse events, which in turn leads to increased cost and poor outcomes (eg, need for nursing home due to cognitive impairment, stroke, and death). The ability to foresee patients at risk of delirium will guide the timely initiation of multimodal preventive interventions, which will aid in reducing the burden and negative consequences associated with delirium. Several studies have focused on the prediction of delirium. However, the number of studies in cardiac surgical patients that have used machine learning methods is very limited. Objective: This study aimed to explore the application of several machine learning predictive models that can pre-emptively predict delirium in patients undergoing cardiac surgery and compare their performance. Methods: We investigated a number of machine learning methods to develop models that can predict delirium after cardiac surgery. A clinical dataset comprising over 5000 actual patients who underwent cardiac surgery in a single center was used to develop the models using logistic regression, artificial neural networks (ANN), support vector machines (SVM), Bayesian belief networks (BBN), na"ive Bayesian, random forest, and decision trees. Results: Only 507 out of 5584 patients (11.4%) developed delirium. We addressed the underlying class imbalance, using random undersampling, in the training dataset. The final prediction performance was validated on a separate test dataset. Owing to the target class imbalance, several measures were used to evaluate algorithm's performance for the delirium class on the test dataset. Out of the selected algorithms, the SVM algorithm had the best F1 score for positive cases, kappa, and positive predictive value (40.2%, 29.3%, and 29.7%, respectively) with a P=.01, .03, .02, respectively. The ANN had the best receiver-operator area-under the curve (78.2%; P=.03). The BBN had the best precision-recall area-under the curve for detecting positive cases (30.4%; P=.03). Conclusions: Although delirium is inherently complex, preventive measures to mitigate its negative effect can be applied proactively if patients at risk are prospectively identified. Our results highlight 2 important points: (1) addressing class imbalance on the training dataset will augment machine learning model's performance in identifying patients likely to develop postoperative delirium, and (2) as the prediction of postoperative delirium is difficult because it is multifactorial and has complex pathophysiology, applying machine learning methods (complex or simple) may improve the prediction by revealing hidden patterns, which will lead to cost reduction by prevention of complications and will optimize patients' outcomes.