Early Warning of Intraoperative Adverse Events via Transformer-Driven Multi-Label Learning

2026-03-05

AI Summary

This study addresses key challenges in early intraoperative adverse event prediction, including inadequate modeling of inter-event dependencies, difficulties in fusing heterogeneous clinical data, and severe class imbalance. To this end, the authors introduce MuAE, the first multi-label intraoperative adverse event dataset, and propose IAENet, a Transformer-based framework that integrates static and dynamic clinical variables while explicitly modeling temporal dependencies and co-occurrence structures among events. Methodological innovations include an enhanced time-aware feature fusion module (TAFiLM) and a label-constrained reweighted loss with co-occurrence regularization (LCRLoss), which jointly mitigate class imbalance and preserve logical consistency among predicted events. Experimental results demonstrate significant performance gains, with average F1 scores improving by 5.05%, 2.82%, and 7.57% on 5-, 10-, and 15-minute early warning tasks, respectively, outperforming existing baselines.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Multiagent Systems: Adversarial Agents
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Early warning of intraoperative adverse events plays a vital role in reducing surgical risk and improving patient safety. While deep learning has shown promise in predicting the single adverse event, several key challenges remain: overlooking adverse event dependencies, underutilizing heterogeneous clinical data, and suffering from the class imbalance inherent in medical datasets. To address these issues, we construct the first Multi-label Adverse Events dataset (MuAE) for intraoperative adverse events prediction, covering six critical events. Next, we propose a novel Transformerbased multi-label learning framework (IAENet) that combines an improved Time-Aware Feature-wise Linear Modulation (TAFiLM) module for static covariates and dynamic variables robust fusion and complex temporal dependencies modeling. Furthermore, we introduce a Label-Constrained Reweighting Loss (LCRLoss) with co-occurrence regularization to effectively mitigate intra-event imbalance and enforce structured consistency among frequently co-occurring events. Extensive experiments demonstrate that IAENet consistently outperforms strong baselines on 5, 10, and 15-minute early warning tasks, achieving improvements of +5.05%, +2.82%, and +7.57% on average F1 score. These results highlight the potential of IAENet for supporting intelligent intraoperative decision-making in clinical practice.

Problem

• intraoperative adverse events
• early warning
• multi-label learning
• class imbalance
• clinical data

Innovation

• Transformer
• multi-label learning
• intraoperative adverse events
• TAFiLM
• class imbalance