Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center Cohorts

TL;DR

This paper introduces Adaptive Test-Time Training (AdaTTT), a novel framework that dynamically adapts predictive models during inference for ICU patients needing mechanical ventilation, addressing domain shifts across hospitals.

Contribution

The work develops AdaTTT with information-theoretic bounds, self-supervised pretext tasks, and partial optimal transport for improved domain adaptation in EHR-based IMV prediction.

Findings

Achieves robust performance across multi-center ICU datasets.

Enhances model generalization with domain adaptation techniques.

Demonstrates competitive results in test-time adaptation benchmarks.

Abstract

Accurate prediction of the need for invasive mechanical ventilation (IMV) in intensive care units (ICUs) patients is crucial for timely interventions and resource allocation. However, variability in patient populations, clinical practices, and electronic health record (EHR) systems across institutions introduces domain shifts that degrade the generalization performance of predictive models during deployment. Test-Time Training (TTT) has emerged as a promising approach to mitigate such shifts by adapting models dynamically during inference without requiring labeled target-domain data. In this work, we introduce Adaptive Test-Time Training (AdaTTT), an enhanced TTT framework tailored for EHR-based IMV prediction in ICU settings. We begin by deriving information-theoretic bounds on the test-time prediction error and demonstrate that it is constrained by the uncertainty between the main and auxiliary tasks. To enhance their alignment, we introduce a self-supervised learning framework with pretext tasks: reconstruction and masked feature modeling optimized through a dynamic masking strategy that emphasizes features critical to the main task. Additionally, to improve robustness against domain shifts, we incorporate prototype learning and employ Partial Optimal Transport (POT) for flexible, partial feature alignment while maintaining clinically meaningful patient representations. Experiments across multi-center ICU cohorts demonstrate competitive classification performance on different test-time adaptation benchmarks.