Saved in:
Bibliographic Details
Main Authors: Li, Kanxue, Zhan, Yibing, Jin, Hua, Qi, Chongchong, Lin, Xu, Yu, Baosheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.15762
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912979760447488
author Li, Kanxue
Zhan, Yibing
Jin, Hua
Qi, Chongchong
Lin, Xu
Yu, Baosheng
author_facet Li, Kanxue
Zhan, Yibing
Jin, Hua
Qi, Chongchong
Lin, Xu
Yu, Baosheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction
Li, Kanxue
Zhan, Yibing
Jin, Hua
Qi, Chongchong
Lin, Xu
Yu, Baosheng
Machine Learning
Artificial Intelligence
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.
title Cross-Sample Augmented Test-Time Adaptation for Personalized Intraoperative Hypotension Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.15762