Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Burkhart, Michael C., Ramadan, Bashar, Solo, Luke, Parker, William F., Beaulieu-Jones, Brett K.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2507.22798
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916871326924800
author Burkhart, Michael C.
Ramadan, Bashar
Solo, Luke
Parker, William F.
Beaulieu-Jones, Brett K.
author_facet Burkhart, Michael C.
Ramadan, Bashar
Solo, Luke
Parker, William F.
Beaulieu-Jones, Brett K.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22798
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models
Burkhart, Michael C.
Ramadan, Bashar
Solo, Luke
Parker, William F.
Beaulieu-Jones, Brett K.
Machine Learning
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.
title Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models
topic Machine Learning
url https://arxiv.org/abs/2507.22798