Huang Kuo-Yang, Hsu Ying-Lin, Chung Che-Liang, Chen Huang-Chi, Horng Ming-Hwarng, Lin Ching-Hsiung, Liu Ching-Sen, Xu Jia-Lang
Division of Chest Medicine, Department of Internal Medicine, Changhua Christian Hospital, Changhua, Taiwan.
Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung, Taiwan.
Sci Rep. 2025 May 22;15(1):17858. doi: 10.1038/s41598-025-02317-z.
The advancement of the Internet of Medical Things (IoMT) has revolutionized data acquisition and processing in critical care settings. Given the pivotal role of ventilators, accurately predicting extubation outcomes is essential to optimize patient care. This study presents an edge computing-based framework that incorporates machine learning algorithms to predict ventilator extubation success using real-time data collected directly from ventilators. The system was deployed on edge devices to enable on-site inference with minimal latency. Among the evaluated models, Random Forest and XGBoost, the latter demonstrated superior predictive performance under both holdout and tenfold cross-validation schemes. Notably, the edge-based architecture reduced server data transmissions by 83.33%, while improving system stability, resilience, and sustainability. This paper details the model evaluation and demonstrates the feasibility and efficiency of edge intelligence in ventilator weaning decision support.
医疗物联网（IoMT）的发展彻底改变了重症监护环境中的数据采集和处理方式。鉴于呼吸机的关键作用，准确预测拔管结果对于优化患者护理至关重要。本研究提出了一个基于边缘计算的框架，该框架结合机器学习算法，利用直接从呼吸机收集的实时数据来预测呼吸机拔管成功率。该系统部署在边缘设备上，以实现低延迟的现场推理。在评估的模型中，随机森林和XGBoost，后者在留出法和十折交叉验证方案下均表现出卓越的预测性能。值得注意的是，基于边缘的架构将服务器数据传输减少了83.33%，同时提高了系统的稳定性、弹性和可持续性。本文详细介绍了模型评估，并展示了边缘智能在呼吸机撤机决策支持中的可行性和效率。
