Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction

TL;DR

This paper introduces CSA-TTA, a novel test-time adaptation framework that improves intraoperative hypotension prediction by leveraging cross-sample data and advanced retrieval strategies, achieving better robustness and personalization.

Contribution

The paper proposes CSA-TTA, a new framework combining cross-sample augmentation, semantic retrieval, and self-supervised signals for improved test-time adaptation in hypotension prediction.

Findings

CSA-TTA improves prediction recall and F1 scores on VitalDB dataset.

The method enhances robustness in zero-shot and fine-tuning scenarios.

It demonstrates strong generalization across datasets.

Abstract

Intraoperative hypotension (IOH) poses significant surgical risks, but accurate prediction remains challenging due to patient-specific variability. While test-time adaptation (TTA) offers a promising approach for personalized prediction, the rarity of IOH events often leads to unreliable test-time training. To address this, we propose CSA-TTA, a novel Cross-Sample Augmented Test-Time Adaptation framework that enhances training by incorporating hypotension events from other individuals. Specifically, we first construct a cross-sample bank by segmenting historical data into hypotensive and non-hypotensive samples. Then, we introduce a coarse-to-fine retrieval strategy for building test-time training data: we initially apply K-Shape clustering to identify representative cluster centers and subsequently retrieve the top-K semantically similar samples based on the current patient signal. Additionally, we integrate both self-supervised masked reconstruction and retrospective sequence forecasting signals during training to enhance model adaptability to rapid and subtle intraoperative dynamics. We evaluate the proposed CSA-TTA on both the VitalDB dataset and a real-world in-hospital dataset by integrating it with state-of-the-art time series forecasting models, including TimesFM and UniTS. CSA-TTA consistently enhances performance across settings-for instance, on VitalDB, it improves Recall and F1 scores by +1.33% and +1.13%, respectively, under fine-tuning, and by +7.46% and +5.07% in zero-shot scenarios-demonstrating strong robustness and generalization.