Machine Learning for Prediction of Stable Warfarin Dose in US Latinos and Latin Americans

Autor(es):Mostrar menos -

Steiner, Heidi E. ^[1] ; Giles, Jason B. ^[1] ; Patterson, Hayley Knight ^[1] ; Feng, Jianglin ^[1] ; El Rouby, Nihal ^{[2, 3]} ; Claudio, Karla ^{[2, 3, 4]} ; Marcatto, Leiliane Rodrigues ^[5] ; Tavares, Leticia Camargo ^{[5, 6]} ; Galvez, Jubby Marcela ^[7] ; Calderon-Ospina, Carlos-Alberto ^[7] ; Sun, Xiaoxiao ^[8] ; Hutz, Mara H. ^[9] ; Scott, Stuart A. ^[10] ; Cavallari, Larisa H. ^{[2, 3]} ; Fonseca-Mendoza, Dora Janeth ^[7] ; Duconge, Jorge ^[4] ; Botton, Mariana Rodrigues ^{[9, 11]} ; Santos, Paulo Caleb Junior Lima ^{[5, 12]} ; Karnes, Jason H. ^{[1, 13]}

Afiliação do(s) autor(es):Mostrar menos -

^[1] Univ Arizona, Coll Pharm, Dept Pharm Practice & Sci, Tucson, AZ 85721 - USA

^[2] Univ Florida, Coll Pharm, Dept Pharmacotherapy & Translat Res, Gainesville, FL 32610 - USA

^[3] Univ Florida, Coll Pharm, Ctr Pharmacogen & Precis Med, Gainesville, FL 32610 - USA

^[4] Univ Puerto Rico, Sch Pharm, Dept Pharmaceut Sci, Med Sci Campus, San Juan, PR 00936 - USA

^[5] Univ Sao Paulo, Inst Coracao Hosp Clin, Fac Med, HCFMUSP, Sao Paulo - Brazil

^[6] Monash Univ, Sch Biol Sci, Fac Sci, Melbourne, Vic - Australia

^[7] Univ Rosario, Sch Med & Hlth Sci, GENIUROS Res Grp, Ctr Res Genet & Genom CIGGUR, Bogota - Colombia

^[8] Univ Arizona, Coll Publ Hlth, Dept Epidemiol Biostat, Tucson, AZ - USA

^[9] Univ Fed Rio Grande do Sul, Dept Genet, Porto Alegre, RS - Brazil

^[10] Stanford Univ, Dept Pathol, Clin Genom Lab, Stanford, CA - USA

^[11] Hosp Clin Porto Alegre, Cells Tissues & Genes Lab, Porto Alegre, RS - Brazil

^[12] Univ Fed Sao Paulo, Dept Pharmacol, Escola Paulista Med, EPM Unifesp, Sao Paulo - Brazil

^[13] Vanderbilt Univ, Med Ctr, Dept Biomed Informat, Nashville, TN - USA

• Tipo de documento: Artigo Científico
• Fonte: FRONTIERS IN PHARMACOLOGY; v. 12, OCT 29 2021.
• Citações Web of Science: 0

Resumo

Populations used to create warfarin dose prediction algorithms largely lacked participants reporting Hispanic or Latino ethnicity. While previous research suggests nonlinear modeling improves warfarin dose prediction, this research has mainly focused on populations with primarily European ancestry. We compare the accuracy of stable warfarin dose prediction using linear and nonlinear machine learning models in a large cohort enriched for US Latinos and Latin Americans (ULLA). Each model was tested using the same variables as published by the International Warfarin Pharmacogenetics Consortium (IWPC) and using an expanded set of variables including ethnicity and warfarin indication. We utilized a multiple linear regression model and three nonlinear regression models: Bayesian Additive Regression Trees, Multivariate Adaptive Regression Splines, and Support Vector Regression. We compared each model's ability to predict stable warfarin dose within 20% of actual stable dose, confirming trained models in a 30% testing dataset with 100 rounds of resampling. In all patients (n = 7,030), inclusion of additional predictor variables led to a small but significant improvement in prediction of dose relative to the IWPC algorithm (47.8 versus 46.7% in IWPC, p = 1.43 x 10(-15)). Nonlinear models using IWPC variables did not significantly improve prediction of dose over the linear IWPC algorithm. In ULLA patients alone (n = 1,734), IWPC performed similarly to all other linear and nonlinear pharmacogenetic algorithms. Our results reinforce the validity of IWPC in a large, ethnically diverse population and suggest that additional variables that capture warfarin dose variability may improve warfarin dose prediction algorithms.</p> (AU)

• Processo FAPESP: 16/23454-5 - Avaliação de algoritmo estimador de dose de varfarina em pacientes sem dose estável
• Beneficiário: Leiliane Rodrigues Marcatto
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 13/09295-3 - Avaliação farmacogenética para fármacos do sistema cardiovascular com foco na implementação
• Beneficiário: Paulo Caleb Júnior de Lima Santos
• Modalidade de apoio: Auxílio à Pesquisa - Jovens Pesquisadores
• Processo FAPESP: 19/08338-7 - Farmacogenômica: implementação e avaliação do custo-efetividade
• Beneficiário: Paulo Caleb Júnior de Lima Santos
• Modalidade de apoio: Auxílio à Pesquisa - Regular