Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 21, 2025Open Access

Personalized Data-Driven Robust Machine Learning Models to Differentiate Parkinson's Disease Patients Using Heterogeneous Risk Factors

View Full Paper
Ask AI
Bookmark
Share

Authors

MIMalinda IluppangamaLoyola University MarylandDADilmi AbeywardanaLoyola University MarylandCTChris P. TsokosUniversity of South Florida

Discussion

Loading...

Member takes

Implication

Machine learning improves classification accuracy in Parkinson's Disease patients, suggesting more precise clinical decision-making.

Key Points

  • To develop robust machine learning models that can accurately classify Parkinson's Disease patients using heterogeneous risk factors.
  • Employ six machine learning algorithms including SVM, RF, XGBoost, LR, KNN, and DT.
  • Evaluate model performances to identify the top-performing classifier.
  • Analyze feature importance using SHAP for model interpretability.
  • SVM achieved 96% accuracy, outperforming other machine learning models.
  • The study highlights the integration of artificial intelligence in healthcare.
  • The proposed models enhance early detection and clinical decision-making for high-risk patients.

Cite This Study

Iluppangama et al. (2025) studied this question.

synapsesocial.com/papers/69473b64db9c958d0dfca8aehttps://doi.org/10.64898/2025.12.18.25342612
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1The potential for artificial intelligence in healthcare2019 · 3,868 citations
  2. 2Prevalence of Parkinson’s disease across North America2018 · 1,032 citations
  3. 3MRI-Guided Focused Ultrasound in Parkinson’s Disease: A Review2017 · 51 citations
  4. 4A Close Look at Deep Learning with Small Data2021 · 202 citations
  5. 5Environmental sustainability technologies in biodiversity, energy, transportation and water management using artificial intelligence: A systematic review2022 · 157 citations