Feng Bao, Shi Jiangfeng, Huang Liebin, Yang Zhiqi, Feng Shi-Ting, Li Jianpeng, Chen Qinxian, Xue Huimin, Chen Xiangguang, Wan Cuixia, Hu Qinghui, Cui Enming, Chen Yehang, Long Wansheng
Department of Radiology, Jiangmen Central Hospital, Jiangmen, China.
Laboratory of Intelligent Detection and Information Processing, Guilin University of Aerospace Technology, Guilin, China.
Nat Commun. 2024 Jan 25;15(1):742. doi: 10.1038/s41467-024-44946-4.
The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.
通过计算机断层扫描（CT）图像和人工智能技术预测患者疾病风险具有巨大潜力。然而，训练一个强大的人工智能模型通常需要大规模数据支持。在实践中，医学数据的收集面临与隐私保护相关的障碍。因此，本研究旨在建立一个强大的联邦学习模型，以克服数据孤岛问题，并在多中心、跨机构环境中识别胃癌术后复发的高危患者，从而实现具有重要价值的有力治疗。在本研究中，我们从四个独立的医疗机构收集数据进行实验。强大的联邦学习模型算法在四个数据中心的受试者操作特征曲线（AUC）值分别为0.710、0.798、0.809和0.869。此外，还评估了该算法的有效性，并通过分析识别了自适应特征和共同特征。
