Cox-nnet v2.0: improved neural-network-based survival prediction extended to large-scale EMR data

• DOI: 10.1093/bioinformatics/btab046
• Publication Date: 2021-01-23T15:58:04Z
• Authors: Di Wang; Zheng Jing; Kevin He; Lana X. Garmire
• Keywords: Interpretability; Feature (linguistics)

Cox-nnet is a neural-network-based prognosis prediction method, originally applied to genomics data. Here, we propose the version 2 of Cox-nnet, with significant improvement on efficiency and interpretability, making it suitable predict based large-scale population data, including those electronic medical records (EMR) datasets. We also add permutation-based feature importance scores direction coefficients. When kidney transplantation dataset, v2.0 reduces training time up 32-folds (n =10 000) achieves better accuracy than Cox-PH (P<0.05). It similarly superior performance publicly available SUPPORT data (n=8000). The high make desirable method for survival in EMR data.Cox-nnet freely public at https://github.com/lanagarmire/Cox-nnet-v2.0.Supplementary are Bioinformatics online.