6 papers
Efficient Generative Prediction for EHR Foundation Models: The SCOPE and REACH Estimators
Luke Solo, Matthew B. A. McDermott, William F. Parker +3
Generative foundation models trained on tokenized electronic health record (EHR) timelines show promise for clinical outcome prediction via Monte Carlo sampling of simulated future…
Representation Before Training: A Fixed-Budget Benchmark for Generative Medical Event Models
Inhyeok Lee, Luke Solo, Michael C. Burkhart +3
Every prediction from a generative medical event model is bounded by how clinical events are tokenized, yet input representation is rarely isolated from other system and architectu…
Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs
Sahil Sethi, David Chen, Michael C. Burkhart +3
Prototype-based neural networks offer interpretable predictions by comparing inputs to learned, representative signal patterns anchored in training data. While such models have sho…
ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning
Sahil Sethi, David Chen, Thomas Statchen +4
Deep learning-based electrocardiogram (ECG) classification has shown impressive performance but clinical adoption has been slowed by the lack of transparent and faithful explanatio…
Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models
Michael C. Burkhart, Bashar Ramadan, Luke Solo +2
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 conte…
Foundation models for electronic health records: representation dynamics and transferability
Michael C. Burkhart, Bashar Ramadan, Zewei Liao +4
Foundation models (FMs) trained on electronic health records (EHRs) have shown strong performance on a range of clinical prediction tasks. However, adapting these models to local h…