Work

Pathophysiological Features in Electronic Medical Records Sustain Model Performance under Temporal Dataset Shift.

Year: 2024

Type: article

Abstract: based on their reflection of patient pathophysiology or healthcare processes. We adapt Shapley values to explain feature groups' and feature categories' marginal contribution to initial and sustained model performance. We investigate three standard clinical prediction tasks and find that while feature contributions to initial performance differ across tasks, pathophysiological features help mitigate temporal discrimination deterioration. These results provide interpretable insights on how specific feature groups contribute to model performance and robustness to temporal dataset shift.

Source: PubMed Central

Authors: Raphael Brosula, Conor K Corbin, Jonathan H Chen

Institutions: Broad Institute, Stanford University

Language: English

Topic: Machine Learning in Healthcare

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: green

Funder: National Institute of Allergy and Infectious Diseases

Award: Measuring and Predicting Appropriate Antibiotic Use to Combat Resistant Bacteria