Contrastive Representation Learning Helps Cross-institutional Knowledge Transfer: A Study in Pediatric Ventilation Management

TL;DR

This study demonstrates that contrastive predictive coding enhances cross-institutional knowledge transfer in pediatric ventilation management, especially with limited data, by enabling more effective model fine-tuning and transfer of temporal patterns.

Contribution

It introduces a systematic framework using CPC for knowledge transfer across institutions in clinical time series, highlighting the importance of fine-tuning and transfer pattern analysis.

Findings

CPC with fine-tuning improves transfer effectiveness

Temporal progression patterns transfer better than point-of-care decisions

Limited data scenarios benefit most from the proposed approach

Abstract

Clinical machine learning deployment across institutions faces significant challenges when patient populations and clinical practices differ substantially. We present a systematic framework for cross-institutional knowledge transfer in clinical time series, demonstrated through pediatric ventilation management between a general pediatric intensive care unit (PICU) and a cardiac-focused unit. Using contrastive predictive coding (CPC) for representation learning, we investigate how different data regimes and fine-tuning strategies affect knowledge transfer across institutional boundaries. Our results show that while direct model transfer performs poorly, CPC with appropriate fine-tuning enables effective knowledge sharing between institutions, with benefits particularly evident in limited data scenarios. Analysis of transfer patterns reveals an important asymmetry: temporal progression patterns transfer more readily than point-of-care decisions, suggesting practical pathways for cross-institutional deployment. Through a systematic evaluation of fine-tuning approaches and transfer patterns, our work provides insights for developing more generalizable clinical decision support systems while enabling smaller specialized units to leverage knowledge from larger centers.