Electronic Health Records
A preprint of work by Charles Gadd describing “SurvivEHR: a competing risks, time-to-event foundation model for multiple long-term conditions from primary care electronic health records” is now available on medRxiv.
“Multiple long-term conditions (MLTCs) or multimorbidity – 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 real-world, longitudinal health data. Here, we present SurvivEHR, a generative 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 mortality. We demonstrate that SurvivEHR achieves strong risk stratification performance, 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 records, SurvivEHR offers a scalable and privacy-preserving approach for building generalisable clinical risk tools that address the complexity of MLTCs in primary care..”
Christopher Yau has contributed as a member of the expert working group to a new report “The Synthetic Data for Development of AI as a Medical Device” now available via PHG Foundation:
We continue to contribute to the MUM-PREDICT and OPTIMAL projects over the last six months including:
Congratulations to Franziska Gunther on her collaborative work with Breaking Free Online on Identifying factors associated with user retention and outcomes of a digital intervention for substance use disorder: a retrospective analysis of real-world data which has been published in JAMIA Open.
Congratulations to Franziska Gunther on her collaborative work with Breaking Free Online which was presented at MIE 2023: On the difficulty of predicting engagement with digital interventions for substance use disorders.
