Automated warfarin dose prediction for Asian, American, and Caucasian populations using a deep neural network

• Published in: Computers in biology and medicine 2023-02, Vol.153, p.106548, Article 106548
• Main Authors: Jahmunah, V., Chen, Sylvia, Oh, Shu Lih, Acharya, U Rajendra, Chowbay, Balram
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Anticoagulants; Anticoagulants - administration & dosage; Artificial neural networks; Cardiac arrhythmia; Consortia; CYP2C9; Datasets; Deep Learning; Deep neural network; Dosage; Dose-Response Relationship, Drug; Errors; Ethnicity; Gene polymorphism; Genotype; Genotype & phenotype; Heterogeneity; Humans; Machine learning; Minority & ethnic groups; Neural networks; Patients; Pharmacogenetics; Pharmacogenetics - methods; Pharmacogenomics; Pharmacology; Polymorphism; Populations; Predictions; Regression analysis; Thromboembolism; Thrombosis; Vitamin K Epoxide Reductases - genetics; VKORC1; Warfarin; Warfarin - administration & dosage
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106548

Existing warfarin dose prediction algorithms based on pharmacogenetics and clinical parameters have not been used clinically due to the absence of external validation, lack of assessment for clinical utility, and high risk of bias. Moreover, given the high degree of heterogeneity across different datasets used to develop these algorithms, it is unsurprising that prediction errors remain high, and dosing accuracy is dependent on specific ethnic populations. To circumvent these challenges, deep neural models are increasingly used to improve the precision and accuracy of warfarin dose predictions. Hence, this study sought to develop a deep learning-based model using a well-established curated dataset of over 6000 patients from the International Warfarin Pharmacogenomics Consortium (IWPC). Clinically-relevant input data such as physical attributes, medical conditions, concomitant medications, genotype status of functional warfarin genetic polymorphisms, and therapeutic INR were entered followed by applying a unique and robust training and validation method. The deep model yielded a low average mean absolute error (MAE) of 7.6 mg/week and a relatively low mean percentage of error of 40.9% in Asians, 14.2 mg/week MAE and 36.9% in African Americans, and 12.7 mg/week MAE and 45.4% mean percentage of error in White Caucasians. This model also resulted in 36.4% of all patients with a predicted dose within 20% of the administered dose. Hence, our proposed deep model provides an alternative to predicting warfarin dose in the clinical setting upon validation in ethnically-similar datasets. •Proposed novel deep learning model for accurate warfarin dose prediction.•Well established and curated dataset of diverse ethnicities has been used.•Crucial clinical factors have been used to develop the model.•A unique, yet clinically robust training and validation method has been proposed.•Obtained lowest mean absolute error of 7.6 mg per week for the Asian population.