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

Autor: Freire-Álvarez E; Hospital General Universitario de Elche, Alicante, Spain., Ramírez IL; Hospital Universitario Son Espases, Palma de Mallorca, Spain., García-Ramos R; Departament of Neurology, Instituto de Neurociencias, Hospital Clínico San Carlos, Madrid, Spain., Carrillo F; Movement Disorders Unit, Neurology and Clinical Neurophysiology department, Instituto de Biomedicina de Sevilla, Hospital Universitario Virgen del Rocío/CSIC/Universidad de Sevilla, Centro de Investigación Biomédica en Red sobre Enfermedades Neurodegenerativas (CIBERNED), Spain., Santos-García D; Departament of Neurology, Complejo Hospitalario Universitario de A Coruña-INIBIC, A Coruña, Spain., Gómez-Esteban JC; Neurodegenerative Diseases Group, Biobizkaia Health Research Institute, Barakaldo, Spain., Martínez-Castrillo JC; Departament of Neurology, Hospital Universitario Ramón y Cajal, IRYCIS, Madrid, Spain., Martínez-Torres I; Departament of Neurology, Hospital Universitari i Politècnic La Fe, Valencia, Spain., Madrid-Navarro CJ; Departament of Neurology, Hospital Universitario Virgen de las Nieves, Instituto de Investigación Biosanitaria ibs.GRANADA, Granada, Spain., Pérez-Navarro MJ; Departament of Neurology, Hospital Universitario Virgen de las Nieves, Instituto de Investigación Biosanitaria ibs.GRANADA, Granada, Spain., Valero-García F; Hospital Universitario Son Espases, Palma de Mallorca, Spain., Vives-Pastor B; Hospital Universitario Son Espases, Palma de Mallorca, Spain., Muñoz-Delgado L; Movement Disorders Unit, Neurology and Clinical Neurophysiology department, Instituto de Biomedicina de Sevilla, Hospital Universitario Virgen del Rocío/CSIC/Universidad de Sevilla, Centro de Investigación Biomédica en Red sobre Enfermedades Neurodegenerativas (CIBERNED), Spain., Tijero B; Neurodegenerative Diseases Group, Biobizkaia Health Research Institute, Barakaldo, Spain; Department of Neurology, Cruces University Hospital-OSAKIDETZA, Barakaldo, Spain., Martínez CM; Departament of Neurology, Hospital Universitari i Politècnic La Fe, Valencia, Spain., Valls JM; Department of Computer Science, Universidad Carlos III de Madrid, Madrid, Spain., Aler R; Department of Computer Science, Universidad Carlos III de Madrid, Madrid, Spain., Galván IM; Department of Computer Science, Universidad Carlos III de Madrid, Madrid, Spain., Escamilla-Sevilla F; Departament of Neurology, Hospital Universitario Virgen de las Nieves, Instituto de Investigación Biosanitaria ibs.GRANADA, Granada, Spain. Electronic address: francisco.escamilla@sen.es.
Jazyk: angličtina
Zdroj: Computers in biology and medicine [Comput Biol Med] 2024 Dec 04; Vol. 185, pp. 109504. Date of Electronic Publication: 2024 Dec 04.
DOI: 10.1016/j.compbiomed.2024.109504
Abstrakt: 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.
Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests:• Eric Freire-Alvarez has received advisory, consulting, and lecture fees from AbbVie, Almirall, Bial, Eisai, UCB Pharma, Teva, Neuraxpharm, Stada, Esteve and Zambon. He is an investigator on clinical trials as principal investigator for AbbVie, Neuroderm, Anavex, Cerevel, Roche, Irlab, Zambon, Bial, Impax and Annovis.• Rocio García-Ramos has participated as a consultant and received sponsorship for multiple activities from Abbvie, Bial, Merz, Esteve, Stada and Zambon.• Francisco Escamilla-Sevilla has participated as a consultant and received sponsorship for multiple activities from Abbvie, Bial, Boston Scientific, Esteve, Medtronic, Stada and Zambon.
(Copyright © 2024 Elsevier Ltd. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: