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

📅 2025-07-30
📈 Citations: 0
Influential: 0
📄 PDF

career value

170K/year
🤖 AI Summary
Clinical electronic health records (EHRs) contain critical anomalous events that evade detection by rule-based systems—particularly subtle, “apparently normal” events with substantial prognostic impact. Method: We propose an information-theoretic, foundation-model–driven anomaly detection framework that quantifies token- and event-level informativeness via context-aware entropy estimation and event saliency scoring. Contribution/Results: This work pioneers the integration of information theory into clinical event detection, overcoming reliance on handcrafted rules. By coupling informativeness scoring with interpretable attribution techniques, it provides event-level explanations for prognostic models. Experiments demonstrate that high-informativeness events identified by our method significantly improve downstream outcome prediction (average AUC gain of 0.08), while low-informativeness events can be safely pruned without performance degradation—validating the clinical utility and decision-support value of informativeness as a biomarker.

Technology Category

Application Category

📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Detecting anomalous events in electronic health records
Predicting downstream patient outcomes effectively
Interpreting prognostic models using informativeness metrics
Innovation

Methods, ideas, or system contributions that make the work stand out.

Foundation model identifies informative EHR tokens
Context-aware anomaly detection in patient data
Informativeness improves prognostic model interpretation
🔎 Similar Papers
No similar papers found.
M
Michael C. Burkhart
Department of Medicine, University of Chicago, Chicago, Illinois, USA
B
Bashar Ramadan
Department of Medicine, University of Chicago, Chicago, Illinois, USA
L
Luke Solo
Department of Medicine, University of Chicago, Chicago, Illinois, USA
W
William F. Parker
Department of Medicine, University of Chicago, Chicago, Illinois, USA
B
Brett K. Beaulieu-Jones
Department of Medicine, University of Chicago, Chicago, Illinois, USA