Score: 1

Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models

Published: July 30, 2025 | arXiv ID: 2507.22798v1

By: Michael C. Burkhart , Bashar Ramadan , Luke Solo and more

Potential Business Impact:

Finds important patient health clues in records.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

We present a foundation model-derived method to identify highly informative tokens and events in electronic health records. Our approach considers incoming data in the entire context of a patient's hospitalization and so can flag anomalous events that rule-based approaches would consider within a normal range. We demonstrate that the events our model flags are significant for predicting downstream patient outcomes and that a fraction of events identified as carrying little information can safely be dropped. Additionally, we show how informativeness can help interpret the predictions of prognostic models trained on foundation model-derived representations.

Country of Origin
πŸ‡ΊπŸ‡Έ United States

Repos / Data Links

Page Count
33 pages

Category
Computer Science:
Machine Learning (CS)