EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A machine learning pipeline identifies non-motor symptoms as key contributors to sarcopenia in Parkinson's disease

Minkyeong Kim, Myung Jun Lee, Dahun Kim, Dukjoong Kim, Seoung Hyeon Je, Soo-Kyoung Kim, Heeyoung Kang

Clinical Parkinsonism & Related Disorders · 2026 · 15 · 100476

DOI: 10.1016/j.prdoa.2026.100476 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical Parkinsonism & Related Disorders, 2026. Verfasst von Minkyeong Kim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Gyeongsang National University Hospital, Jinju, Republic of Korea. Die Arbeit nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Korea Ministry of Science and ICT, National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Sarcopenia, characterized by the loss of skeletal muscle mass and physical function, is more prevalent among patients with Parkinson's disease (PD) and is linked to poor clinical outcomes. This study aimed to investigate clinical features associated with sarcopenia in PD, which was further validated using a two-stage modeling pipeline.

Methods

Clinical and demographic data were collected and compared between the sarcopenia and non-sarcopenia groups. The dataset was split into a training and a hold-out test set (70:30). Following an initial variable screening in the training set based on clinical judgment and inter-variable correlations, a least absolute shrinkage and selection operator regression was applied to identify six key predictors. These variables were then used to train a logistic regression model selected based on the highest Area Under the Receiver Operating Characteristic (AUROC) in stratified cross-validation. Finally, the model was evaluated on the independent hold-out test set.

Results

Patients with PD and sarcopenia exhibited longer disease duration, higher Hoehn and Yahr stages, and a greater non-motor burden. The final logistic regression model revealed that body mass index, body fat ratio, and non-motor features including cognitive decline, autonomic dysfunction, fatigue, and mood disturbance were the most influential variables. The model achieved an AUROC of 0.793, recall of 0.500, and specificity of 0.902.

Conclusion

Patients with PD and sarcopenia exhibit distinct clinical characteristics defined by both anthropometric and non-motor features. These findings suggest that a comprehensive clinical assessment may be warranted for the early identification of sarcopenia in PD.

Schlagwörter

Stichwörter der Autor:innen

Machine learningNon-motor symptomsParkinson's diseaseSarcopenia

Autor:innen und Institutionen

  • Department of Neurology, Gyeongsang National University Hospital, Jinju, Republic of Korea.
  • Department of Neurology, Pusan National University Hospital, Busan, Republic of Korea.
  • Pusan National University School of Medicine and Biomedical Research Institute, Busan, Republic of Korea.
  • OHRAE Incorporation, Pusan, Republic of Korea.
  • Department of Research Planning, Gyeongsang National University Hospital, Jinju, Republic of Korea.
  • Department of Neurology, Gyeongsang National University College of Medicine, Jinju, Republic of Korea.

Förderung

  • Korea Ministry of Science and ICT
  • National Research Foundation of Korea

Zitieren

APA

Kim, M., Lee, M. J., Kim, D., Kim, D., Je, S. H., Kim, S. K., & Kang, H. (2026). A machine learning pipeline identifies non-motor symptoms as key contributors to sarcopenia in Parkinson's disease. Clinical Parkinsonism & Related Disorders, 15, 100476. https://doi.org/10.1016/j.prdoa.2026.100476

Vancouver

Kim M, Lee MJ, Kim D, Kim D, Je SH, Kim SK, et al. A machine learning pipeline identifies non-motor symptoms as key contributors to sarcopenia in Parkinson's disease. Clinical Parkinsonism & Related Disorders. 2026;15:100476. doi:10.1016/j.prdoa.2026.100476

BibTeX
@article{Kim2026,
  author = {Kim, Minkyeong and Lee, Myung Jun and Kim, Dahun and Kim, Dukjoong and Je, Seoung Hyeon and Kim, Soo-Kyoung and Kang, Heeyoung},
  title = {A machine learning pipeline identifies non-motor symptoms as key contributors to sarcopenia in Parkinson's disease},
  journal = {Clinical Parkinsonism & Related Disorders},
  year = {2026},
  volume = {15},
  pages = {100476},
  doi = {10.1016/j.prdoa.2026.100476}
}
Kostenlos starten →