A multicenter random forest model for effective prognosis prediction in collaborative clinical research network
作者：
Highlights：
• A multicenter random forest prognosis prediction model that enables federated clinical data mining is proposed.
• A novel data enhancement approach based on a differentially private generative adversarial network enables the model building.
• A case study based on the colorectal cancer data from the US and China is presented to illustrate the feasibility of the proposed model.
• The multicenter random forest model performs better than the centrally trained version but without aggregating the raw data.
摘要
•A multicenter random forest prognosis prediction model that enables federated clinical data mining is proposed.•A novel data enhancement approach based on a differentially private generative adversarial network enables the model building.•A case study based on the colorectal cancer data from the US and China is presented to illustrate the feasibility of the proposed model.•The multicenter random forest model performs better than the centrally trained version but without aggregating the raw data.
论文关键词：Clinical decision support,Distributed privacy-preserving modeling,Ensemble learning,Generative adversarial networks,Variable importance ranking
论文评审过程：Received 16 September 2019, Revised 4 February 2020, Accepted 4 February 2020, Available online 5 February 2020, Version of Record 14 February 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101814
