The AI-Driven Future of Health Data Science

Chronic and polymedicated patients represent a critical healthcare priority, driving substantial costs and posing significant safety risks. As the population ages, the prevalence of patients receiving multiple concurrent medications (and the potential for adverse interactions) continues to escalate. In this seminar we will discuss how comprehensive patient-level datasets, encompassing demographics, clinical events, diagnoses, and prescription histories, can be leveraged through both expert-guided methodologies and advanced data-driven approaches to identify potentially harmful drug interactions. By applying sophisticated patient clustering techniques based on biomedical criteria, we explore how medical ontologies can effectively structure and interrelate complex clinical and pharmacological data. Furthermore, we highlight the transformative potential of artificial intelligence in health research, particularly its ability to analyze intricate data structures to uncover previously hidden clinical patterns. These capabilities enable more precise diagnostic insights and support the development of safer, truly personalized treatment <a href="http://strategies.

Co-sponsored” target=”_blank” title=”strategies.

Co-sponsored”>strategies.

Co-sponsored by: CU@EMBS

Speaker(s): Dr. Rocío Romero Zaliz,

Room: ME4463, Bldg: Mckenzie building, Carleton University, 1125 Colonel By Drive, Ottawa, Ontario, Canada, K1S5B6