Bibliographic Details
| Title: |
Esclerosis múltiple: caracterización del fenotipo progresivo y remitente-recurrente con aprendizaje automático. |
| Alternate Title: |
Multiple sclerosis: characterization of the progressive and relapsing-remitting phenotype with machine learning. |
| Authors: |
Guevara-Tirado, Alberto1 albertoguevara1986@gmail.com |
| Source: |
Archivos de Neurociencias. abr-jun2025, Vol. 30 Issue 2, p57-64. 8p. |
| Subjects: |
THERAPEUTIC use of interferons, MULTIPLE sclerosis risk factors, RISK assessment, CROSS-sectional method, MULTIPLE sclerosis, PREDICTION models, PROPYLENE glycols, NEUROLOGISTS, SECONDARY analysis, SEX distribution, SMOKING, LOGISTIC regression analysis, ADENOSINES, AGE distribution, CHI-squared test, RITUXIMAB, DESCRIPTIVE statistics, DISEASE relapse, MACHINE learning, DECISION trees, EPIDEMIOLOGISTS, DISEASE progression, PHENOTYPES, GLUCOCORTICOIDS, ACYCLIC acids, DISEASE risk factors |
| Abstract (English): |
Background: Supervised learning algorithms can contribute to building efficient classification and prediction models around the multiple sclerosis (MS) phenotype. Objective: To identify and characterize the factors associated with primary progressive and relapsing-remitting multiple sclerosis phenotypes using a machine learning model, based on decision trees. Method: This was an analytical and cross-sectional study from a secondary source. The variables were phenotype, age, sex, glucocorticoids, cigarette consumption, and modifying therapy. The decision tree was used using the chi-square automatic interaction detector and binary logistic regression. Results: The tree correctly classified (87%) patients with a smoking history between 51 and 70 years of age as characteristics associated with primary progressive MS (PPMS). In relapsing remitting MS (RRMS), the group with the greatest association was women between 18 and 50 years old. When including disease-modifying medications (correct prognoses: 89.70%), the groups associated with PPMS were history of smoking, treated with teriflunomide, rituximab, glatiramer and ocrelizumab between 51 and 70 years old, men between 18 and 50 years old with ocrelizumab and rituximab. For RRMS, they were women 18 to 50 years old with ocrelizumab and rituximab. Patients aged 18 to 50 years with dimethyl fumarate, teriflunomide, interferon, glatiramer, fingolimod, natalizumab, cladribine, and alemtuzumab. Conclusions: Machine learning using decision trees with easily accessible data is efficient in rapidly classifying personal factors and pharmacological profiles associated with RRMS and PPMS. Likewise, smoking history is a predictor of PPMS. The decision tree could help neurologists and epidemiologists by providing additional information to make clinical, therapeutic, and epidemiological decisions. [ABSTRACT FROM AUTHOR] |
| Abstract (Spanish): |
Antecedentes: El uso de algoritmos de aprendizaje supervisado puede contribuir a construir modelos de clasificación y predicción eficientes en torno al fenotipo de esclerosis múltiple (EM). Objetivo: Identificar y caracterizar los factores asociados a los fenotipos de esclerosis múltiple primaria progresiva y remitente-recurrente utilizando un modelo de aprendizaje automático, basado en árboles de decisión. Método: Estudio analítico y transversal de una fuente secundaria, las variables fueron fenotipo, edad, sexo, glucocorticoides, consumo de cigarro, terapia modificadora. Se utilizó el árbol de decisiones mediante detector de interacciones automáticas de chi-cuadrado y regresión logística binaria. Resultados: El árbol clasificó correctamente (87%) como características asociadas a EM primaria progresiva (EMPP) a pacientes con antecedentes tabáquicos entre 51 a 70 años. En EM remitente recurrente (EMRR), el grupo con mayor asociación fue el de mujeres entre 18 a 50 años. Al incluir medicamentos modificadores de la enfermedad (pronósticos correctos: 89.70%), los grupos asociados a EMPP fueron antecedentes de fumar, tratados con teriflunomida, rituximab, glatiramero y ocrelizumab de entre 51 a 70 años, hombres entre 18 a 50 años con ocrelizumab y rituximab. Para EMRR, fueron mujeres de 18 a 50 años con ocrelizumab, rituximab. Pacientes de 18 a 50 años con dimetilfumarato, teriflunomida, interferón, glatiramero, fingolimod, natalizumab, cladribina y alemtuzumab. Conclusiones: El aprendizaje automático mediante arboles de decisión con datos de fácil acceso es eficiente en la clasificación rápida de factores personales y perfiles farmacológicos asociados a EMRR y EMPP. Asimismo, el antecedente tabáquico es un predictor de EMPP. El árbol de decisión podría ayudar a neurólogos y epidemiólogos proporcionando información adicional para tomar decisiones clínicas, terapéuticas y epidemiológicas. [ABSTRACT FROM AUTHOR] |
|
Copyright of Archivos de Neurociencias is the property of Instituto Nacional de Neurologia y Neurocirugia, Departamento de Publicaciones Cientificas and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
MedicLatina |
