1. Inicio
  2. Publicaciones
  3. Artificial intelligence for identification of candidates for device-aided therapy in Parkinson's disease: DELIST-PD study

Artificial intelligence for identification of candidates for device-aided therapy in Parkinson's disease: DELIST-PD study

Fecha de publicación:

Autores de IIS La Fe

Participantes ajenos a IIS La Fe

  • Freire-Álvarez E.
  • Ramírez I.L.
  • García-Ramos R.
  • Carrillo F.
  • Santos-García D.
  • Gómez-Esteban J.C.
  • Martínez-Castrillo J.C.
  • Madrid-Navarro C.J.
  • Pérez-Navarro M.J.
  • Valero-García F.
  • Vives-Pastor B.
  • Muñoz-Delgado L.
  • Tijero B.
  • Martínez C.M.
  • Valls J.M.
  • Aler R.
  • Galván I.M.
  • Escamilla-Sevilla F.

Grupos

Abstract

Introduction: In Parkinson's Disease (PD), despite available treatments focusing on symptom alleviation, the effectiveness of conventional therapies decreases over time. This study aims to enhance the identification of candidates for device-aided therapies (DAT) using artificial intelligence (AI), addressing the need for improved treatment selection in advanced PD stages. Methods: This national, multicenter, cross-sectional, observational study involved 1086 PD patients across Spain. Machine learning (ML) algorithms, including CatBoost, support vector machine (SVM), and logistic regression (LR), were evaluated for their ability to identify potential DAT candidates based on clinical and demographic data. Results: The CatBoost algorithm demonstrated superior performance in identifying DAT candidates, with an area under the curve (AUC) of 0.95, sensitivity of 0.91, and specificity of 0.88. It outperformed other ML models in balanced accuracy and negative predictive value. The model identified 23 key features as predictors for suitability for DAT, highlighting the importance of daily “off” time, doses of oral levodopa/day, and PD duration. Considering the 5-2-1 criteria, the algorithm identified a decision threshold for DAT candidates as > 4 times levodopa tablets taken daily and/or =1.8 h in daily “off” time. Conclusion: The study developed a highly discriminative CatBoost model for identifying PD patients candidates for DAT, potentially improving timely and accurate treatment selection. This AI approach offers a promising tool for neurologists, particularly those less experienced with DAT, to optimize referral to Movement Disorder Units. © 2024 Elsevier Ltd

Datos de la publicación

ISSN/ISSNe:
0010-4825, 1879-0534

COMPUTERS IN BIOLOGY AND MEDICINE  PERGAMON-ELSEVIER SCIENCE LTD

Tipo:
Article
Páginas:
-
PubMed:
39637457
Enlace a otro recurso:
www.scopus.com
Factor de Impacto:
1,309 SCImago ℠
Cuartil:
Q1 SCImago ℠

Documentos

  • No hay documentos

Métricas

Filiaciones mostrar / ocultar

Keywords

  • Aged; Algorithms; Artificial Intelligence; Cross-Sectional Studies; Female; Humans; Machine Learning; Male; Middle Aged; Parkinson Disease; Spain; Support Vector Machine; Contrastive Learning; Disease control; Neurodegenerative diseases; levodopa; Decision support techniques; Deep learning; Device-aided therapy; Levodopa; Machine learning algorithms; Observational study; OFF time; Off-time; Parkinson's disease; Treatment selection; aged; Article; artificial intelligence; classification algorithm; controlled study; cross-sectional study; device therapy; disease duration; dyskinesia; feature selection; female; human; learning algorithm; logistic regression analysis; major clinical study; male; multicenter study; observational study; Parkinson disease; predictive model; predictive value; receiver operating characteristic; sensitivity and specificity; Spain; support vector machine; algorithm; clinical trial; machine learning; middle aged; Parkinson disease; therapy; Adversarial machine lea

Compartir