BEGIN:VCALENDAR VERSION:2.0 PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4// BEGIN:VEVENT UID:20260122T160355EST-1783ztPvui@132.216.98.100 DTSTAMP:20260122T210355Z DESCRIPTION:Jean Nikiema\, MD\, PhD\n\nAssistant Professor | School of Publ ic Health\n Department of Health Management\, Evaluation and Policy Univers ité de Montréal\n\nThe Seminars in Epidemiology organized by the Departmen t of Epidemiology\, Biostatistics and Occupational Health at the 鶹ýվ Sc hool of Population and Global Health is a self-approved Group Learning Act ivity (Section 1) as defined by the maintenance of certification program o f the Royal College of Physicians and Surgeons of Canada. Physicians requi ring accreditation\, please complete the Evaluation Form and send to admin coord.eboh [at] mcgill.ca \n\nWHEN: Monday\, January 26\, 2026\, from 3:30 -4:30 p.m.\n WHERE: Hybrid | Onsite at 2001 鶹ýվ College\, Rm 1140 | Zoom \n NOTE: Jean Nikiema will be presenting in-person\n\nAbstract\n\nReal-worl d data (RWD)\, especially information extracted from electronic health rec ords\, holds enormous potential for clinical decision support\, cost analy sis\, and public health planning. Yet this potential is frequently limited by fragmented data pipelines\, inconsistent clinical semantics\, incomple te provenance\, and uncertain fitness-for-use. The CIRCULATE consortium\, paired with the Provem platform\, were created to address these challenges through an integrated ecosystem that turns raw RWD into decision-ready as sets.\n\nThis talk will describe how Provem and the CIRCULATE consortium o perationalizes a pragmatic “AI for Health” mindset: starting with data pro venance and quality signals\, enabling interoperability through ontology-b ased harmonization\, and supporting clinical trajectory reconstruction (ho spital stays\, transitions\, and longitudinal care pathways). We will pres ent how pathway discovery (clustering\, labeling\, and phenotyping of stay s/trajectories) is combined with knowledge-based standardization\, and how a human-in-the-loop workflow supports validation\, traceability\, and cli nical relevance of AI algorithms. Finally\, we will highlight how the ecos ystem creates a continuous transparency loop so that improvements to data governance and data production directly translate into more reliable analy tics and AI capabilities.\n\nLearning Objectives\n\nAt the end of this tal k\, attendees will be able to:\n\n\n Present the limitations of RWD for AI: data quality\, bias\, and recognize what “realistic expectations” look li ke in clinical settings\;\n Present the evaluation of a responsible AI syst em that identifies and convert patterns in EHR data into clinically useful information for decision support and cost analysis\;\n Understand the oper ationalized responsible\, and scalable analytics by combining data-driven pathway discovery with knowledge-based standardization while keeping human -in-the-loop for algorithm validation.\n\n\nSpeaker Bio\n\nJean-Noël Nikie ma is an Assistant Professor at the Université de Montréal School of Publi c Health (ESPUM)\, a regular researcher at the Centre de recherche en sant é publique (UdeM–CIUSSS du Centre-Sud-de-l’Île-de-Montréal)\, a researcher with OBVIA (Sustainable Health Axis)\, and Co-Director of LabTNS\, focuse d on digital transformation in health\, and co responsible of the infrastr ucture axe at Québec Digital Health Network. His research centers on the r eal-world conditions required for successful health innovation\, data qual ity\, interoperability\, governance\, organizational impact\, and uptake i n practice settings\, to support learning health systems aligned with oper ational constraints. His training integrates clinical\, public health\, an d informatics perspectives: MD (Université Nazi Boni)\, MSc in Public Heal th-Medical Informatics (Université de Bordeaux)\, PhD in Public Health-Inf ormatics and Health (Université de Bordeaux)\, followed by postdoctoral tr aining at CHUM. Prior to joining ESPUM\, he was research visiting scholar at the U.S. National Library of Medicine.\n DTSTART:20260126T203000Z DTEND:20260126T213000Z SUMMARY:From Data to Decisions: Building a Data-Quality Ecosystem for Clini cal Decision Support and Care Pathway Analytics URL:/epi-biostat-occh/channels/event/data-decisions-bu ilding-data-quality-ecosystem-clinical-decision-support-and-care-pathway-a nalytics-370260 END:VEVENT END:VCALENDAR