Wang Dejian, Qi Guoqiang, Li Jing, Wang Yuqi, Dong Kexiong, Ding Jian, Zhu Chen, Zhu Jun, Li Beiyan, Yu Gang, Deng Shuiguang
School of Software Technology, Zhejiang University, Hangzhou, China.
Department of R&D, Hangzhou Healink Technology, Hangzhou, China.
Transl Pediatr. 2025 Jun 27;14(6):1287-1295. doi: 10.21037/tp-2025-349. Epub 2025 Jun 25.
There is a challenge of in diagnostic testing of pneumonia in children, especially severe pneumonia. Thus, developing an auxiliary diagnostic model to help identify severe pneumonia in pediatric patients at an early stage would be highly valuable to address the issues. To overcome the issue of privacy protection, we applied a privacy-preserving machine learning framework to build a multicenter diagnostic model based on federated learning technology.
Based on Arya, a novel privacy computing platform developed by Hangzhou Healink Technology Corporation, several privacy-preserving federated learning models were developed using datasets from one, two, or four medical centers. A total of 5,091 records were included in this multicenter retrospective study, with 2,484 pediatric patients with severe pneumonia and 2,607 with common pneumonia. Among the records, 80% were used in model training for the diagnosis of severe pneumonia, with 11 common indicators, including white blood cell count (WBC), high-sensitivity C-reactive protein (hs-CRP), hemoglobin (Hb), platelet count (PLT), lymphocyte percentage (L%), monocyte percentage (M%), neutrophil percentage (N%), prothrombin time (PT), alanine aminotransferase (ALT), aspartate aminotransferase (AST), and lactic dehydrogenase (LDH), while the other 20% records were used for model efficacy evaluation. During the process, the original data were stored in the individual hospitals without transmission.
Based on privacy-preserving federated learning technology, the developed models provided reliable diagnostic efficacy for severe pneumonia. Among these models, the four-center model achieved the highest diagnostic efficacy (95.10% sensitivity, 82.70% specificity, and 85.80% accuracy). Although the two-center models achieved a relatively low diagnostic efficacy, they still surpassed the diagnostic efficacy of the single-center model (88.10% sensitivity, 74.60% specificity, and 81.00% accuracy).
Privacy-preserving federated learning technology can facilitate the performance of multicenter studies and was used to develop a high-performance diagnostic model for severe pneumonia in pediatric patients, which can benefit doctors and patients as an auxiliary diagnostic tool.
儿童肺炎，尤其是重症肺炎的诊断检测存在挑战。因此，开发一种辅助诊断模型以帮助早期识别儿科患者的重症肺炎，对于解决这些问题将具有很高的价值。为了克服隐私保护问题，我们应用了一种隐私保护机器学习框架，基于联邦学习技术构建了一个多中心诊断模型。
基于杭州联川生物科技有限公司开发的新型隐私计算平台Arya，使用来自一个、两个或四个医疗中心的数据集开发了几种隐私保护联邦学习模型。本多中心回顾性研究共纳入5091条记录，其中2484例为重症肺炎儿科患者，2607例为普通肺炎患者。在这些记录中，80%用于重症肺炎诊断的模型训练，使用了11项常见指标，包括白细胞计数（WBC）、高敏C反应蛋白（hs-CRP）、血红蛋白（Hb）、血小板计数（PLT）、淋巴细胞百分比（L%）、单核细胞百分比（M%）、中性粒细胞百分比（N%）、凝血酶原时间（PT）、谷丙转氨酶（ALT）、谷草转氨酶（AST）和乳酸脱氢酶（LDH），而另外20%的记录用于模型疗效评估。在此过程中，原始数据存储在各个医院，无需传输。
基于隐私保护联邦学习技术开发的模型为重症肺炎提供了可靠的诊断效能。在这些模型中，四中心模型的诊断效能最高（灵敏度95.10%，特异度82.70%，准确度85.80%）。虽然两中心模型的诊断效能相对较低，但仍超过了单中心模型（灵敏度88.10%，特异度74.60%，准确度81.00%）。
隐私保护联邦学习技术有助于开展多中心研究，并被用于开发儿科患者重症肺炎的高性能诊断模型，作为辅助诊断工具可使医生和患者受益。
