Faculty
Shyam Visweswaran, MD, PhD
Research Interests
Visweswaran's research interests lie in the application of artificial intelligence, machine learning, data mining and Bayesian methods to problems in clinical medicine and bioinformatics with a specific focus on data mining of biomedical data, patient-specific predictive modeling, medical anomaly detection, and decision support systems. He is particularly interested in the area of personalized medicine and genomic medicine.
Appointments and Positions
Biomedical Informatics Training Program Core Faculty
Current Research Projects and Collaborations
Personalized Medicine. Personalized medicine is healthcare that is informed by each individual's unique clinical, genetic, genomic, and environmental information. Since these factors are potentially different for every individual, various facets of healthcare including risk assessment and initiation of preventive measures, diagnosis, prognosis and selection of appropriate therapy will be increasingly tailored to the individual. My work focuses on learning patient-specific predictive models using artificial intelligence and machine learning techniques where the goal is to improve prediction by constructing predictive models that are personalized to the characteristics of the patient at hand.
Genomic Medicine. Genomic medicine is the use of information obtained from the entire genome for risk assessment, diagnosis, prognosis, and development of new therapies. Whole genome information, in combination with other clinical data, will lead to increased understanding of the biology of human health and disease, improved prediction of disease and effect of therapy, and ultimately the realization of personalized medicine. My work focuses on data obtained from genome-wide studies that type several hundreds of thousands of single nucleotide polymorphisms (SNPs) per individual. I apply variable selection methods and model non-linear variable interactions among SNPs using artificial intelligence and machine learning techniques to predict the development of disease.
Anomaly Detection in Clinical Care. I am involved in developing and implementing machine-learning methods that predict anomalies or deviations in therapy and clinical management of patients.
Adverse Drug Reaction Monitoring. I am involved in implementing and evaluating computerized adverse drug reaction monitoring systems in the long term care and intensive care unit settings.
Recent Publications
Wang, J, Day, R, Visweswaran, S, Hogan, W. The use of semantic distance metrics to support ontology. In: Proceedings of the Fall Symposium of the American Medical Informatics Association (Nov 2010).
Jiang, X, Neapolitan, RE, Barmada, MM, Visweswaran, S, Cooper, GF. A fast algorithm for learning epistatic genomic relationships. In: Proceedings of the Fall Symposium of the American Medical Informatics Association (Nov 2010).
Cooper, GF, Hennings-Yeomans, P, Visweswaran, S, Barmada, MM. An efficient Bayesian method for predicting clinical outcomes from genome-wide data. In: Proceedings of the Fall Symposium of the American Medical Informatics Association (Nov 2010).
Hauskrecht, M, Valko, M, Batal, I, Clermont, G, Visweswaran, S, Cooper, GF. Conditional outlier detection for clinical alerting. In: Proceedings of the Fall Symposium of the American Medical Informatics Association (Nov 2010).
Wang S, Hauskrecht, M, Visweswaran, S.Candidate gene prioritization using network based probabilistic models. BMC Bioinformatics. (in press)