Multimodal Forecasting of Sparse Intraoperative Hypotension Events Powered by Language Model

TL;DR

This paper introduces IOHFuseLM, a multimodal language model that improves intraoperative hypotension prediction by integrating physiological data and clinical descriptions through a two-stage training process and token-level alignment.

Contribution

The paper presents a novel multimodal framework with domain adaptive pretraining and token-level alignment for better IOH event prediction.

Findings

Outperforms baseline models in IOH event detection

Effective integration of clinical descriptions and physiological data

Demonstrates robustness across two intraoperative datasets

Abstract

Intraoperative hypotension (IOH) frequently occurs under general anesthesia and is strongly linked to adverse outcomes such as myocardial injury and increased mortality. Despite its significance, IOH prediction is hindered by event sparsity and the challenge of integrating static and dynamic data across diverse patients. In this paper, we propose \textbf{IOHFuseLM}, a multimodal language model framework. To accurately identify and differentiate sparse hypotensive events, we leverage a two-stage training strategy. The first stage involves domain adaptive pretraining on IOH physiological time series augmented through diffusion methods, thereby enhancing the model sensitivity to patterns associated with hypotension. Subsequently, task fine-tuning is performed on the original clinical dataset to further enhance the ability to distinguish normotensive from hypotensive states. To enable multimodal fusion for each patient, we align structured clinical descriptions with the corresponding physiological time series at the token level. Such alignment enables the model to capture individualized temporal patterns alongside their corresponding clinical semantics. In addition, we convert static patient attributes into structured text to enrich personalized information. Experimental evaluations on two intraoperative datasets demonstrate that IOHFuseLM outperforms established baselines in accurately identifying IOH events, highlighting its applicability in clinical decision support scenarios. Our code is publicly available to promote reproducibility at https://github.com/zjt-gpu/IOHFuseLM.