Open AccessBig Data Toolsets to Pharmacometrics: Application of Machine Learning for Time‐to‐Event Analysis
Author(s) -
Gong Xiajing,
Hu Meng,
Zhao Liang
Publication year - 2018
Publication title -
clinical and translational science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.303
H-Index - 44
eISSN - 1752-8062
pISSN - 1752-8054
DOI - 10.1111/cts.12541
Subject(s) - proportional hazards model , censoring (clinical trials) , computer science , event (particle physics) , statistics , logistic regression , regression , data mining , regression analysis , big data , hazard , linear regression , machine learning , mathematics , physics , chemistry , organic chemistry , quantum mechanics
Additional value can be potentially created by applying big data tools to address pharmacometric problems. The performances of machine learning (ML) methods and the Cox regression model were evaluated based on simulated time‐to‐event data synthesized under various preset scenarios, i.e., with linear vs. nonlinear and dependent vs. independent predictors in the proportional hazard function, or with high‐dimensional data featured by a large number of predictor variables. Our results showed that ML‐based methods outperformed the Cox model in prediction performance as assessed by concordance index and in identifying the preset influential variables for high‐dimensional data. The prediction performances of ML‐based methods are also less sensitive to data size and censoring rates than the Cox regression model. In conclusion, ML‐based methods provide a powerful tool for time‐to‐event analysis, with a built‐in capacity for high‐dimensional data and better performance when the predictor variables assume nonlinear relationships in the hazard function.