基于联邦学习的网络化ICU呼吸机和镇静剂管理方法  

Ventilator and Sedative Management in Networked ICUs Based on Federated Learning

作　　者：曹林霄 刘佳 朱怡飞 周浩泉 龚伟[4] 于卫华[5] 李朝友[6] CAO Linxiao;LIU Jia;ZHU Yifei;ZHOU Haoquan;GONG Wei;YU Weihua;LI Chaoyou(School of Data Science,University of Science and Technology of China,Hefei 230026,China;Department of Pediatrics,Provincial Hospital Affiliated to Anhui Medical University,Hefei 230001,China;University of Michigan-Shanghai Jiao Tong University Joint Institute,Shanghai Jiao Tong University,Shanghai 200240,China;Department of Pediatrics,The First Affiliated Hospital of USTC,Hefei 230001,China;Department of Nursing,The First People’s Hospital of Hefei,Hefei 230061,China;Department of Pediatrics,The First People’s Hospital of Hefei,Hefei 230061,China)

机构地区：[1]中国科学技术大学大数据学院,合肥230026 [2]安徽医科大学附属省立医院儿科,合肥230001 [3]上海交通大学密西根学院,上海200240 [4]中国科学技术大学附属第一医院儿科,合肥230001 [5]合肥市第一人民医院护理部,合肥230061 [6]合肥市第一人民医院儿科,合肥230061

出　　处：《计算机科学》2023年第10期165-175,共11页Computer Science

基　　金：合肥市自主创新政策“借转补”项目(J2020Y03)。

摘　　要：医疗物联网设备的激增和丰富的医疗数据为智慧医疗提供了新的可能。重症监护室(ICU)的病人依靠众多医疗边缘设备来持续监测管理患者的健康状况。在ICU常见的治疗干预措施中,有创机械通气和镇静剂的注射多用于维持患者的呼吸功能,提高治疗质量,而现有的治疗干预措施很大程度上依赖于医生的判断。文中提出了一种基于联邦学习的临床辅助决策方法——MFed,可以基于网络化ICU分布式协作学习最佳干预政策。该方法应用基于差分隐私的联邦学习方法,打破了医疗数据隐私方面的限制以及医疗数据孤岛的窘境;用分布鲁棒优化确保最坏情况下的性能并结合伪孪生网络实现自适应地滤除噪声数据。最后,在现实ICU数据集上的实验表明,与其他最先进的基线相比,所提方法的准确率提高了36.75%。The proliferation of medical IoT devices and the abundance of medical data open up new possibilities for smart healthcare.Patients in the intensive care unit(ICU)rely on numerous medical IoT devices to continuously monitor and manage patients’health status.Among the common therapeutic interventions in ICUs,invasive mechanical ventilation and sedation are mostly administered to maintain patients’respiratory function and enhance the care quality.While the existing therapeutic interventions rely heavily on physician judgment.This paper proposes a data-driven optimal policy learning framework named MFed that allows distributed learning of optimal intervention policies on networked ICUs.A differentially private federated learning method is constructed to overcome privacy limitations in medical data.MFed further ensures worst-case performance with distributionally robust optimization and adaptively filters out noisy data.Extensive experiments on a real-world ICU dataset show that the proposed method improves accuracy by 36.75%compared to other state-of-the-art baselines.

关 键 词：联邦学习 医疗物联网 分布式鲁棒优化 医疗数据噪声 医疗数据隐私 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]