Levodopa-induced dyskinesia in Parkinson's disease: Insights from cross-cohort prognostic analysis using machine learning

Prolonged levodopa treatment in Parkinson's disease (PD) often leads to motor complications, including levodopa-induced dyskinesia (LID). Despite continuous levodopa treatment, some patients do not develop LID symptoms, even in later stages of the disease. This study explores machine learning (...

Full description

Saved in:

Bibliographic Details
Published in:	Parkinsonism & related disorders Vol. 126; p. 107054
Main Authors:	Loo, Rebecca Ting Jiin, Klucken, Jochen, Khoury, Fouad, Vidailhet, Marie, Krüger, Rejko, Acharya, Geeta, Alexandre, Myriam, Ali, Muhammad, Ammerlann, Wim, Arena, Giuseppe, Batutu, Roxane, Béchet, Sibylle, Berchem, Guy, Bisdorff, Alexandre, Boussaad, Ibrahim, Bouvier, David, Castillo, Lorieza, Contesotto, Gessica, DE Bremaeker, Nancy, Dewitt, Brian, Diederich, Nico, Dondelinger, Rene, Ramia, Nancy E., Ferrari, Angelo, Frauenknecht, Katrin, Fritz, Joëlle, Gantenbein, Manon, Gawron, Piotr, Georges, Laura, Ghosh, Soumyabrata, Giraitis, Marijus, Goergen, Martine, Gómez DE Lope, Elisa, Graas, Jérôme, Graziano, Mariella, Groues, Valentin, Grünewald, Anne, Hammot, Gaël, Anne-Marie, H.A.N.F.F., Hansen, Linda, Heneka, Michael, Henry, Estelle, Henry, Margaux, Herbrink, Sylvia, Hundt, Alexander, Jónsdóttir, Sonja, Kofanova, Olga, Lambert, Pauline, Landoulsi, Zied, Lentz, Roseline, Longhino, Laura, Lopes, Ana Festas, Lorentz, Victoria, Marques, Guilherme, Martins Conde, Patricia, Patrick, M.A.Y., Mcintyre, Deborah, Mediouni, Chouaib, Meisch, Francoise, Mendibide, Alexia, Menster, Myriam, Minelli, Maura, Mittelbronn, Michel, Mtimet, Saïda, Nati, Romain, Nickels, Sarah, Nicolai, Beatrice, Jean-Paul, N.I.C.O.L.A.Y., Gomes, Clarissa P.C., Pauly, Claire, Pauly, Laure, Pavelka, Lukas, Perquin, Magali, Pexaras, Achilleas, Rauschenberger, Armin, Rawal, Rajesh, Remark, Lucie, Richard, Ilsé, Roland, Olivia, Rosales, Eduardo, Sapienza, Stefano, Satagopam, Venkata, Schmitz, Sabine, Schneider, Reinhard, Schwamborn, Jens, Sharify, Amir, Soare, Ruxandra, Soboleva, Ekaterina, Sokolowska, Kate, Theresine, Maud, Thien, Hermann, Thiry, Elodie, Ting Jiin Loo, Rebecca, Trouet, Johanna, Vaillant, Michel, Vilas Boas, Liliana, Wilmes, Paul, Wollscheid-Lengeling, Evi
Format:	Journal Article
Language:	English
Published:	England Elsevier Ltd 01-09-2024
Subjects:	Cross-cohort analysis Levodopa-induced dyskinesia Longitudinal cohorts Machine learning Predictive modeling Prognosis Cross-cohort analysis Predictive modeling Prognosis Levodopa-induced dyskinesia Longitudinal cohorts Machine learning
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Prolonged levodopa treatment in Parkinson's disease (PD) often leads to motor complications, including levodopa-induced dyskinesia (LID). Despite continuous levodopa treatment, some patients do not develop LID symptoms, even in later stages of the disease. This study explores machine learning (ML) methods using baseline clinical characteristics to predict the development of LID in PD patients over four years, across multiple cohorts. Using interpretable ML approaches, we analyzed clinical data from three independent longitudinal PD cohorts (LuxPARK, n = 356; PPMI, n = 484; ICEBERG, n = 113) to develop cross-cohort prognostic models and identify potential predictors for the development of LID. We examined cohort-specific and shared predictive factors, assessing model performance and stability through cross-validation analyses. Consistent cross-validation results for single and multiple cohort analyses highlighted the effectiveness of the ML models and identified baseline clinical characteristics with significant predictive value for the LID prognosis in PD. Predictors positively correlated with LID include axial symptoms, freezing of gait, and rigidity in the lower extremities. Conversely, the risk of developing LID was inversely associated with the occurrence of resting tremors, higher body weight, later onset of PD, and visuospatial abilities. This study presents interpretable ML models for dyskinesia prognosis with significant predictive power in cross-cohort analyses. The models may pave the way for proactive interventions against dyskinesia in PD by optimizing levodopa dosing regimens and adjunct treatments with dopamine agonists or MAO-B inhibitors, and by employing non-pharmacological interventions such as dietary adjustments affecting levodopa absorption for high-risk LID patients. •Baseline clinical data contains significant predictive information for LID prognosis.•Axial symptoms and freezing of gait correlate significantly with dyskinesia.•Rigidity in the lower extremities is significantly associated with LID prognosis.•Resting tremors and cognitive function are associated with a favorable LID prognosis.•Lower body weight and younger age at PD onset are inversely associated with LID risk.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1353-8020 1873-5126 1873-5126
DOI:	10.1016/j.parkreldis.2024.107054