Modelo farmacogenético y clínico para la predicción de desenlaces en pacientes con artritis reumatoide tratados con metotrexato y adalimumab
GOAL: To develop a pharmacogenetic and clinical model to predict effectiveness outcomes in a cohort of patients diagnosed with rheumatoid arthritis (RA) treated with methotrexate or adalimumab at the Central Military Hospital in Bogota, Colombia. METHODS: Five statistical learning methods were teste...
| Autor: | |
|---|---|
| Tipo de recurso: | tesis de maestría |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2020 |
| País: | Colombia |
| Institución: | Universidad Nacional de Colombia |
| Repositorio: | Repositorio UN |
| Idioma: | español |
| OAI Identifier: | oai:repositorio.unal.edu.co:unal/78759 |
| Acceso en línea: | https://repositorio.unal.edu.co/handle/unal/78759 |
| Access Level: | acceso abierto |
| Palabra clave: | 610 - Medicina y salud::615 - Farmacología y terapéutica Artritis Reumatoide Farmacogenética Modelo predictivo Aprendizaje Automático Rheumatoid Arthritis Pharmacogenetics Predictive Model Machine Learning |
| Sumario: | GOAL: To develop a pharmacogenetic and clinical model to predict effectiveness outcomes in a cohort of patients diagnosed with rheumatoid arthritis (RA) treated with methotrexate or adalimumab at the Central Military Hospital in Bogota, Colombia. METHODS: Five statistical learning methods were tested on the data set with previous pre-processing for variable cleaning and selection: Logistic regression, decision trees, random forests, Support Vector Machines (SVM) and Artificial Neural Networks (ANN). The models were applied in a cohort of 155 patients treated with MTX which was derived in a training (124 patients) and a test cohort (31 patients). Both clinical variables and genetic variations were included. The chosen outcome was the therapy response measured as a DAS 28 score <3.2. The performance evaluation criterion was the area (AUC) under the receiver operating characteristics (ROC) curve. RESULTS: The algorithms with the highest predictive power were SVM and ANN. For the MTX cohort, the main selected variables were age, time with RA, functional classification, and genotypes of the rs9344, rs4148396, rs4673993, rs1801133 and rs7279445 variants. Given the size of the cohort of ADA-treated patients (12 patients), no machine learning model could be successfully adjusted. CONCLUSIONS: A prognostic model with high predictive power was developed in the cohort of patients treated with MTX, which is able to identify patients prone to not responding well to treatment. |
|---|