Article

EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution Shift

2022-04-19

Abstract excerpt

<h4>ABSTRACT</h4> <h4>Background</h4> Temporal distribution shift negatively impacts the performance of clinical prediction models over time. Pretraining foundation models using self-supervised learning on electronic health records (EHR) may be effective in acquiring informative global patterns that can improve the robustness of task-specific models. <h4>Objective</h4> To evaluate the utility of EHR foundation...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: b1dca56c-6cd1-5ac8-855e-2f3e739b555b
DOI: 10.1101/2022.04.15.22273900

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution ShiftDOI 10.1101/2022.04.15.22273900Read

Predicting Hospital Admissions Using Pretrained EHR Embeddings: External Evaluation and Insights on Local Vocabulary AdaptationSemantic proximity Read

Multi-Hospital Electronic Health Record Foundation Models Without Data Sharing: A Comparison of Federated Learning and Inference-Time EnsemblingSemantic proximity Read

Deep Representation Learning for Risk Prediction in Electronic Health Records Using Self-Supervised MethodsSemantic proximity Read

Predicting Near-term Mortality in Heart Failure: External Validation of Electronic Health Record-Based Deep Learning ModelSemantic proximity Read

Revolutionizing Postoperative Ileus Monitoring: Exploring GRU-D’s Real-Time Capabilities and Cross-Hospital TransferabilitySemantic proximity Read

Application of Foundation Models in Emergency and Critical Care: A Scoping ReviewSemantic proximity Read

Disease Risk Prediction Using Structured EHR Data: Can Generalist Large Language Models Match Specialized Clinical Foundation Models? A Comparative Evaluation with Fine-TuningSemantic proximity Read

Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world ConstraintsSemantic proximity Read

A Foundation Model for Intensive Care: Unlocking Generalization across Tasks and Domains at ScaleSemantic proximity Read

Predicting 30-Day Hospital Readmission in Medicare Patients: Insights from an LSTM Deep Learning ModelSemantic proximity Read

Synthetic Data for Accessible Learning in Healthcare: Improving Mortality Prediction with Longitudinal DataSemantic proximity Read

Longitudinal Masked Representation Learning for Pulmonary Nodule Diagnosis from Language Embedded EHRsSemantic proximity Read