arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.00282cs.LGcs.AIcs.CR
收藏

FedScore:一种用于联邦评分系统开发的隐私保护框架

FedScore: A privacy-preserving framework for federated scoring system development

Duke-NUS Medical School(杜克-新加坡国立大学医学院);Singapore Health Services(新加坡保健服务集团);Singapore General Hospital(新加坡中央医院);National University of Singapore(新加坡国立大学);Duke University(杜克大学);Duke University School of Medicine(杜克大学医学院);University of Pennsylvania(宾夕法尼亚大学);Institute of Data Science, National University of Singapore(新加坡国立大学数据科学研究院)

Siqi Li, Yilin Ning, Marcus Eng Hock Ong, Bibhas Chakraborty, Chuan Hong, Feng Xie, Han Yuan, Mingxuan Liu, Daniel M. Buckland, Yong Chen, Nan Liu

AI总结:

FedScore是一个隐私保护的联邦学习框架,通过五个模块在多个站点生成评分系统,在急诊死亡率预测中达到AUC 0.763,接近集中式模型,且稳定性优于多数本地模型。

摘要:

我们提出了FedScore,这是一种隐私保护的联邦学习框架,用于在多个站点间生成评分系统,以促进跨机构合作。FedScore框架包含五个模块:联邦变量排序、联邦变量转换、联邦评分推导、联邦模型选择和联邦模型评估。为了说明用法并评估FedScore的性能,我们利用新加坡一家三级医院划分出的10个模拟站点,构建了一个假设性的全球评分系统,用于预测急诊就诊后30天内的死亡率。我们在每个站点独立使用一个预先存在的评分生成器构建了10个本地评分系统,并利用集中式数据开发了一个评分系统以作比较。我们使用受试者工作特征(ROC)分析,将所获得的FedScore模型的性能与其他评分模型进行了比较。FedScore模型在所有站点的平均曲线下面积(AUC)值为0.763,标准差(SD)为0.020。我们还计算了每个本地模型的平均AUC值和SD,FedScore模型显示出有前景的准确性和稳定性,其高平均AUC值最接近合并模型的值,且SD低于大多数本地模型。本研究证明,FedScore是一种隐私保护的评分系统生成器,具有潜在的良好泛化能力。

英文摘要:

We propose FedScore, a privacy-preserving federated learning framework for scoring system generation across multiple sites to facilitate cross-institutional collaborations. The FedScore framework includes five modules: federated variable ranking, federated variable transformation, federated score derivation, federated model selection and federated model evaluation. To illustrate usage and assess FedScore's performance, we built a hypothetical global scoring system for mortality prediction within 30 days after a visit to an emergency department using 10 simulated sites divided from a tertiary hospital in Singapore. We employed a pre-existing score generator to construct 10 local scoring systems independently at each site and we also developed a scoring system using centralized data for comparison. We compared the acquired FedScore model's performance with that of other scoring models using the receiver operating characteristic (ROC) analysis. The FedScore model achieved an average area under the curve (AUC) value of 0.763 across all sites, with a standard deviation (SD) of 0.020. We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models. This study demonstrates that FedScore is a privacy-preserving scoring system generator with potentially good generalizability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑