Foundation Models for Clinical Records at Health System Scale
By: Haresh Rengaraj Rajamohan , Xiang Gao , Weicheng Zhu and more
Potential Business Impact:
Predicts future illnesses from patient records.
Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (EHRs). We present a novel generative pretraining strategy for sequential EHR data using next-visit event prediction. Our model learns to autoregressively generate various tokenized clinical events for the next visit based on patient history and inherently handles the joint prediction of heterogeneous data types. Additionally, we introduce regularization on predicting repeated events and highlight a key pitfall in EHR-based foundation model evaluations: repeated event tokens can inflate performance metrics when new onsets are not distinguished from subsequent occurrences. Our model is evaluated via zero-shot prediction for forecasting dementia and knee osteoarthritis incidence within 2 and 5 years, and the model performance rivals a fully fine-tuned masked pretrained Transformer baseline, demonstrating that our approach captures complex clinical dependencies without requiring costly task-specific fine-tuning.
Similar Papers
Zero-shot Medical Event Prediction Using a Generative Pre-trained Transformer on Electronic Health Records
Machine Learning (CS)
Predicts future patient health events without extra training.
Quantifying surprise in clinical care: Detecting highly informative events in electronic health records with foundation models
Machine Learning (CS)
Finds important patient health clues in records.
Generative Foundation Model for Structured and Unstructured Electronic Health Records
Artificial Intelligence
Helps doctors predict sickness and write notes faster.