Use of artificial neural network to predict warfarin individualized dosage regime in Chinese patients receiving low-intensity anticoagulation after heart valve replacement

摘要

Chinese are reported more sensitive to warfarin [1 ]; hence for Chinese the western recommended target international normalized ratio (INR) range (2.5-3.5) might not be appropriate [2]. So we developed artificial neural network (ANN) models with patient-related clinical parameters derived from multicenter Chinese population receiving low-intensity anticoagulation (INR 1.5-2.5) after heart valve replacement to predict the maintenance dose of warfarin, and compared their predictive effects with multiple linear regression (MLR) models. This is an analysis of data from the Chinese Low Intensity Anticoagulant Therapy After Heart Valve Replacement (CL1ATHVR) multicenter clinical study, which is an ongoing prospective cohort study involving 45 participating centers from 15 provinces in China. From the CLIATHVR database we selected 1093 eligible Chinese patients whose details were registered in the database during the period January 2011 to September 2012. Written informed consent was obtained from all participants and the study was approved by the Ethics Committee of West China Hospital of Sichuan University.