详情页 - 首都医科大学宣武医院知识库

当前位置：首页 > 详情页

Federated Learning for Predicting Postoperative Remission of Patients with Acromegaly: A Multicentered study

12| 认领 | 导出 | 链接全文 |

文献详情

资源类型：

WOS体系：

Pubmed体系：

收录情况： ◇ SCIE

作者：

机构： [1]Department of Thoracic Surgery, Peking University First Hospital, Beijing, China. [2]Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, 999077, Hong Kong SAR, China. [3]Department of Neurosurgery, Xuanwu Hospital Capital Medical University, 100053, Beijing, China. [4]Department of Population and Public Health Sciences, University of Southern California, USA. [5]Department of Neurosurgery, Chinese Academy of Medical Sciences and Peking Union Medical College, Peking Union Medical College Hospital, 100730, Beijing, China.

出处：

DOI：

ISSN：

关键词： Acromegaly Federated learning Machine learning Multicentered study Privacy protection

摘要：

Decentralized federated learning (DFL) may serve as a useful framework for machine learning (ML) tasks in multicentered studies, maximizing the use of clinical data without data sharing. We aim to propose the first workflow of DFL for ML tasks in multicentered studies, which can be as powerful as those using centralized data.A DFL workflow was developed with four steps: registration, local computation, model update, and inspection. A total of 598 participants with acromegaly from PUMCH, and 120 participants from XWH were enrolled. The cohort from PUMCH was further split into five centers. Nine clinical features were incorporated into ML-based models trained based on four algorithms: LR, GBDT, SVM, and DNN. The area under the curve (AUC) of receiver operating characteristic curves was used to evaluate the performance of the models.Models trained based on DFL workflow performed better than most models in LR (P<0.05), all models in DNN, SVM, and GBDT (P<0.05). Models trained on DFL workflow performed as powerful as models trained on centralized data in LR, DNN, and SVM (P>0.05).We demonstrate that the DFL workflow without data sharing should be a more appropriate method in ML tasks in multicentered studies. And the DFL workflow should be further exploited in clinical researches in other departments and it can encourage and facilitate multicentered studies.Copyright © 2024. Published by Elsevier Inc.

基金：

语种：

WOS：

PubmedID：

中科院(CAS)分区：

出版当年[2025]版：

大类 | 4 区医学

小类 | 4 区临床神经病学 4 区外科

最新[2025]版：

大类 | 4 区医学

小类 | 4 区临床神经病学 4 区外科

JCR分区：

出版当年[2023]版：

Q2 SURGERY Q3 CLINICAL NEUROLOGY

最新[2023]版：

Q2 SURGERY Q3 CLINICAL NEUROLOGY

影响因子： 1.9 最新[2023版] 2 最新五年平均 1.9 出版当年[2023版] 2 出版当年五年平均 2 出版前一年[2022版]

第一作者：

第一作者机构： [1]Department of Thoracic Surgery, Peking University First Hospital, Beijing, China.

共同第一作者：

通讯作者：

推荐引用方式(GB/T 7714)：

APA：

MLA：

相关文献

[1]Dealing with Label Quality Disparity in Federated Learning [2]基于新医院评审标准的北京市某医院门诊患者隐私保护的实践与思考 [3]新医院评审标准下的门诊患者隐私权保护 [4]Machine learning in Alzheimer's disease drug discovery and target identification [5]Applications of Machine Learning to Diagnosis of Parkinson's Disease [6]RDAD: A Machine Learning System to Support Phenotype-Based Rare Disease Diagnosis [7]Characterizing the hyper- and hypometabolism in temporal lobe epilepsy using multivariate machine learning [8]Knowledge-Based Machine Learning for Glaucoma Diagnosis from Fundus Image Data [9]Machine-learning models for the prediction of ideal surgical outcomes in patients with adult spinal deformity [10]Machine learning for the prediction of acute kidney injury and paraplegia after thoracoabdominal aortic aneurysm repair.