Research & Publications
Dr. Khera is leading the development and implementation of strategies to improve outcomes of patients with or at-risk for cardiovascular disease through data-driven innovations in delivering evidence-based, patient-centered care. His work focuses on novel strategies to learn from complex clinical data and incorporates information and technology in healthcare to improve care efficiency and provide actionable insights to improve patient outcomes. He pursues this work as the Principal Investigator of the Cardiovascular Data Science (CarDS) Lab at the Yale School of Medicine. The work he has led has been published in JAMA, BMJ, Circulation, JAMA Internal Medicine, Journal of the American College of Cardiology, and JAMA Cardiology, among others.
Extensive Research Description
Dr. Khera's clinical observations have informed my research, which has been featured in leading medical and cardiovascular journals.
- First, he has pursued data-driven strategies to evaluate the quality of care measures and their association with patient outcomes in those hospitalized with cardiovascular disease.
- Second, he and his team have developed novel strategies that employ machine learning to infer personalized effect estimates from clinical trials using computational phenomaps.
- Third, he has led the application of deep learning and artificial intelligence to electrocardiography and cardiac imaging.
- Fourth, he has led the development of data-driven quality measurement programs in cardiovascular diseases in large national datasets.
- Finally, he has conducted methodological investigations that focus on improving the rigor of studies that use large datasets.
A key focus of his ongoing work is digital phenotyping of cardiovascular disease and the development of automated assays of care quality within the electronic health record. The work is specifically designing and implementing clinical decision support with a mixed quantitative-qualitative research methodology that incorporates inputs from patients and clinicians in retrieving information and designing interventions. His group has developed a series of applications of machine learning to clinical data. These tools have been validated in multinational populations and are designed to increase efficiency and personalization of care.
Artificial Intelligence; Cardiovascular Diseases; Health Care Quality, Access, and Evaluation; Machine Learning; Health Equity; Data Science