About Me
Research Interests
Machine Learning, Natural Language Processing, Data Visualization and Analytics, Big Data.
Publications
2018
Ben Rose Davis; E. Stringer; Samina Abidi; Syed Sibte Raza Abidi
Interactive Dialogue-Based Patient Education for Juvenile Idiopathic Arthritis Using Argument Theory Proceedings Article
In: 28th European Medical Informatics Conference (MIE2018), April 24 - 26, IOSPress, Gothenburg, Sweden, 2018.
Abstract | Links | BibTeX | Tags: Clinical Decision Support Systems, Health Informatics, Patient Education, Personalized Medicine
@inproceedings{davis-mie-2018,
title = {Interactive Dialogue-Based Patient Education for Juvenile Idiopathic Arthritis Using Argument Theory},
author = {Ben Rose Davis and E. Stringer and Samina Abidi and Syed Sibte Raza Abidi},
url = {https://www.ncbi.nlm.nih.gov/pubmed/29678020},
year = {2018},
date = {2018-04-24},
booktitle = {28th European Medical Informatics Conference (MIE2018), April 24 - 26},
publisher = {IOSPress},
address = {Gothenburg, Sweden},
abstract = {Families of children with Juvenile Idiopathic Arthritis need a way to interact with Patient Education Materials (PEM) so that learning occurs at their own pace, on topics that are relevant to them. This paper proposes a novel, dialogue-based approach to address these needs. Using an extended version of Toulmin's model of argument as a theory-based classification method, we digitized paper-based PEM to render an interactive dialogue. The dialogue allows the user to explore a topic with respect to their interests and apprehensions as opposed to providing a static, generic document.},
keywords = {Clinical Decision Support Systems, Health Informatics, Patient Education, Personalized Medicine},
pubstate = {published},
tppubtype = {inproceedings}
}
Families of children with Juvenile Idiopathic Arthritis need a way to interact with Patient Education Materials (PEM) so that learning occurs at their own pace, on topics that are relevant to them. This paper proposes a novel, dialogue-based approach to address these needs. Using an extended version of Toulmin's model of argument as a theory-based classification method, we digitized paper-based PEM to render an interactive dialogue. The dialogue allows the user to explore a topic with respect to their interests and apprehensions as opposed to providing a static, generic document.
Ali Daowd; Samina Abidi; Ashraf Abusharekh; Syed Sibte Raza Abidi
A Personalized Risk Stratification Platform for Population Lifetime Healthcare Proceedings Article
In: 28th European Medical Informatics Conference (MIE2018), April 24 - 26, IOSPress, Gothenburg, Sweden, 2018.
Abstract | Links | BibTeX | Tags: Clinical Decision Support Systems, Health Informatics, Personalized Medicine
@inproceedings{daowd-mie-2018,
title = {A Personalized Risk Stratification Platform for Population Lifetime Healthcare},
author = {Ali Daowd and Samina Abidi and Ashraf Abusharekh and Syed Sibte Raza Abidi},
url = {https://www.ncbi.nlm.nih.gov/pubmed/29678095},
year = {2018},
date = {2018-04-24},
booktitle = {28th European Medical Informatics Conference (MIE2018), April 24 - 26},
publisher = {IOSPress},
address = {Gothenburg, Sweden},
abstract = {Chronic diseases are the leading cause of death worldwide. It is well understood that if modifiable risk factors are targeted, most chronic diseases can be prevented. Lifetime health is an emerging health paradigm that aims to assist individuals to achieve desired health targets, and avoid harmful lifecycle choices to mitigate the risk of chronic diseases. Early risk identification is central to lifetime health. In this paper, we present a digital health-based platform (PRISM) that leverages artificial intelligence, data visualization and mobile health technologies to empower citizens to self-assess, self-monitor and self-manage their overall risk of major chronic diseases and pursue personalized chronic disease prevention programs. PRISM offers risk assessment tools for 5 chronic conditions, 2 psychiatric disorders and 8 different cancers.},
keywords = {Clinical Decision Support Systems, Health Informatics, Personalized Medicine},
pubstate = {published},
tppubtype = {inproceedings}
}
Chronic diseases are the leading cause of death worldwide. It is well understood that if modifiable risk factors are targeted, most chronic diseases can be prevented. Lifetime health is an emerging health paradigm that aims to assist individuals to achieve desired health targets, and avoid harmful lifecycle choices to mitigate the risk of chronic diseases. Early risk identification is central to lifetime health. In this paper, we present a digital health-based platform (PRISM) that leverages artificial intelligence, data visualization and mobile health technologies to empower citizens to self-assess, self-monitor and self-manage their overall risk of major chronic diseases and pursue personalized chronic disease prevention programs. PRISM offers risk assessment tools for 5 chronic conditions, 2 psychiatric disorders and 8 different cancers.
2017
William Van Woensel; Wasif Baig; Syed Sibte Raza Abidi; Samina Abidi
A Semantic Web Framework for Behavioral User Modeling and Action Planning for Personalized Behavior Modification Proceedings Article
In: 10th International Conference on Semantic Web Applications and Tools for Life Sciences, CEUR, Rome, Italy, 2017.
Links | BibTeX | Tags: Behaviour Modelling, Behavioural Change Theory, Personalized Medicine
@inproceedings{SCT2017,
title = {A Semantic Web Framework for Behavioral User Modeling and Action Planning for Personalized Behavior Modification},
author = {William Van Woensel and Wasif Baig and Syed Sibte Raza Abidi and Samina Abidi},
url = {https://niche.cs.dal.ca/wp-content/uploads/2017/12/paper-21-camera-ready-1.pdf},
year = {2017},
date = {2017-12-06},
booktitle = {10th International Conference on Semantic Web Applications and Tools for Life Sciences},
publisher = {CEUR},
address = {Rome, Italy},
keywords = {Behaviour Modelling, Behavioural Change Theory, Personalized Medicine},
pubstate = {published},
tppubtype = {inproceedings}
}
2016
Wasif Hasan Baig
A Semantic Web Based Knowledge Management Framework to Model Behaviour Change Constructs for Generation of Personalized Action Plans Masters Thesis
Dalhousie University, 2016.
Links | BibTeX | Tags: Behavioural Theory, Chronic Illness, Knowledge Modelling, Ontology Engineering, Patient Empowerment, Personalized Medicine, Self-Management, Semantic Web, Social Cognition Theory
@mastersthesis{Baig-Wasif-MHI-HINF,
title = {A Semantic Web Based Knowledge Management Framework to Model Behaviour Change Constructs for Generation of Personalized Action Plans},
author = {Wasif Hasan Baig},
url = {https://niche.cs.dal.ca/wp-content/uploads/2016/01/Baig-Wasif-MHI-HINF-September-2015.pdf},
year = {2016},
date = {2016-09-01},
school = {Dalhousie University},
keywords = {Behavioural Theory, Chronic Illness, Knowledge Modelling, Ontology Engineering, Patient Empowerment, Personalized Medicine, Self-Management, Semantic Web, Social Cognition Theory},
pubstate = {published},
tppubtype = {mastersthesis}
}
Nelofar Kureshi; Syed Sibte Raza Abidi; Christian Blouin
A Predictive Model for Personalized Therapeutic Interventions in Non-small Cell Lung Cancer. Journal Article
In: IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 1, pp. 424-431, 2016, ISSN: 2168-2208.
Abstract | Links | BibTeX | Tags: Cancer, Data Mining, Decision Trees, Health Data Analytics, Personalized Medicine, Prediction Model
@article{Kureshi:IeeeJBiomedHealthInform:2014,
title = {A Predictive Model for Personalized Therapeutic Interventions in Non-small Cell Lung Cancer.},
author = {Nelofar Kureshi and Syed Sibte Raza Abidi and Christian Blouin},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6974996&isnumber=7369993},
doi = {10.1109/JBHI.2014.2377517},
issn = {2168-2208},
year = {2016},
date = {2016-01-01},
journal = {IEEE Journal of Biomedical and Health Informatics},
volume = {20},
number = {1},
pages = {424-431},
abstract = {Non-small cell lung cancer (NSCLC) constitutes the most common type of lung cancer and is frequently diagnosed at advanced stages. Clinical studies have shown that molecular targeted therapies increase survival and improve quality of life in patients. Nevertheless, the realization of personalized therapies for NSCLC faces a number of challenges including the integration of clinical and genetic data and a lack of clinical decision support tools to assist physicians with patient selection. To address this problem, we used frequent pattern mining to establish the relationships of patient characteristics and tumor response in advanced NSCLC. Univariate analysis determined that smoking status, histology, EGFR mutation, and targeted drug were significantly associated with response to targeted therapy. We applied four classifiers to predict treatment outcome from EGFR-TKIs. Overall, the highest classification accuracy was 76.56% and the AUC was 0.76. The decision tree used a combination of EGFR mutations, histology, and smoking status to predict tumor response and the output was both easily understandable and in keeping with current knowledge. Our findings suggest that support vector machines and decision trees are a promising approach for clinical decision support in the patient selection for targeted therapy in advanced NSCLC},
keywords = {Cancer, Data Mining, Decision Trees, Health Data Analytics, Personalized Medicine, Prediction Model},
pubstate = {published},
tppubtype = {article}
}
Non-small cell lung cancer (NSCLC) constitutes the most common type of lung cancer and is frequently diagnosed at advanced stages. Clinical studies have shown that molecular targeted therapies increase survival and improve quality of life in patients. Nevertheless, the realization of personalized therapies for NSCLC faces a number of challenges including the integration of clinical and genetic data and a lack of clinical decision support tools to assist physicians with patient selection. To address this problem, we used frequent pattern mining to establish the relationships of patient characteristics and tumor response in advanced NSCLC. Univariate analysis determined that smoking status, histology, EGFR mutation, and targeted drug were significantly associated with response to targeted therapy. We applied four classifiers to predict treatment outcome from EGFR-TKIs. Overall, the highest classification accuracy was 76.56% and the AUC was 0.76. The decision tree used a combination of EGFR mutations, histology, and smoking status to predict tumor response and the output was both easily understandable and in keeping with current knowledge. Our findings suggest that support vector machines and decision trees are a promising approach for clinical decision support in the patient selection for targeted therapy in advanced NSCLC