BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:SurvivEHR: a competing risks\, time-to-event foundation model for 
 multiple long-term conditions from primary care electronic health records 
 - Christopher Yau (Oxford)
DTSTART:20260115T100000Z
DTEND:20260115T110000Z
UID:TALK242398@talks.cam.ac.uk
CONTACT:Spencer Keene
DESCRIPTION:Title: SurvivEHR: a competing risks\, time-to-event foundation
  model for multiple long-term conditions from primary care electronic heal
 th records\n \nAbstract: Multiple long-term conditions (MLTCs) or multimor
 bidity – the co-occurrence of multiple chronic conditions –presents a 
 growing challenge for primary care. Current predictive models often target
  single outcomes and overlook the complexities of time-to-event risk in re
 al-world\, longitudinal health data. Here\, we present SurvivEHR\, a gener
 ative transformer-based foundation model trained on over 7.6 billion coded
  events from 23 million patients in UK primary care. SurvivEHR introduces 
 a competing risk time-to-event pretraining objective that enables accurate
  forecasting of future diagnoses\, investigations\, medications\, and mort
 ality. We demonstrate that SurvivEHR achieves strong risk stratification p
 erformance\, captures clinically meaningful trajectories\, and outperforms
  benchmark survival models across multiple tasks. The model also transfers
  effectively to fine-tuned prognostic tasks\, particularly in low-resource
  settings. By learning patient trajectories directly from routine health r
 ecords\, SurvivEHR offers a scalable and privacy-preserving approach for b
 uilding generalisable clinical risk tools that address the complexity of M
 LTCs in primary care.\n \nBio: Christopher Yau is Professor of Artificial 
 Intelligence and a UKRI Turing AI Fellow at the University of Oxford in th
 e Nuffield Department for Women’s and Reproductive Health where he co-di
 rects the Ellison Institute of Technology Centre for Doctoral Training in 
 Fundamentals of AI. He is also Co-Programme Lead for Capacity Building at 
 Health Data Research UK where he leads the Wellcome PhD Programme in Healt
 h Data Science.\n\n
LOCATION:Heart and Lung Research Institute (R.100 to 102)
END:VEVENT
END:VCALENDAR