Voice analisis as a digital biomarker: a machine learning approach for automated multiple sclerosis classification

Voice analysis is a non-invasive tool that can capture subtle motor impairments in Multiple Sclerosis (MS). The objective of this study is to develop and validate a machine learning (ML) framework for the automated classification of MS through acoustic voice analysis. A cohort of 300 gender-balanced...

Descripción completa

Detalles Bibliográficos
Autores: Delgado Hernández, Jonathan, Betancort Montesinos, Moisés, Romero Arias, Tatiana, Hernández Pérez, Miguel Ángel
Tipo de recurso: artículo
Fecha de publicación:2026
País:España
Institución:Universidad Europea (UEM)
Repositorio:ABACUS. Repositorio de Producción Científica
Idioma:inglés
OAI Identifier:oai:abacus.universidadeuropea.com:11268/16926
Acceso en línea:https://hdl.handle.net/11268/16926
Access Level:acceso abierto
Palabra clave:Esclerosis múltiple
Aprendizaje automático
Biomarcadores
Enfermedad del sistema nervioso
Investigación médica
Medicina preventiva
Goal 3: Ensure healthy lives and promote well-being for all at all ages
Descripción
Sumario:Voice analysis is a non-invasive tool that can capture subtle motor impairments in Multiple Sclerosis (MS). The objective of this study is to develop and validate a machine learning (ML) framework for the automated classification of MS through acoustic voice analysis. A cohort of 300 gender-balanced participants (200 with MS and 100 healthy controls) provided sustained vocal recordings. Fifteen acoustic features were extracted. An elastic network model first identified the most relevant parameters from the development cohort, which were then used to train five supervised ML classifiers.