⌘+K

Pulse Explore Communities Researchers Journals

Home Communities Explore

March 27, 2026Journal of Medicine and Palliative Care

Explainable multimodal imaging–based machine learning for cardiovascular risk stratification in early Parkinson’s disease

Esra Demir Unal Ahmet Arslan

View at Publisher

Ask AI

Bookmark

Share

Key Points

To characterize biochemical and cardiovascular imaging endophenotypes of atherosclerotic risk in early Parkinson’s disease.
Analyzed 125 early-stage idiopathic Parkinson's disease patients and control group.
Reduced feature space using LASSO for multicollinearity mitigation.
Trained models including Random Forest and XGBoost with Bayesian hyperparameter optimization.
Increased hypertension (54.4%) in Parkinson's disease patients (OR 3.2, p=0.007).
Higher hypercholesterolemia rates (OR 2.8, p=0.01).
Excess left ventricular systolic dysfunction observed (28.8% vs 0%).

No abstract yet

We only have this paper's title and publication details.

Read it at the source→

Implication

Demonstrates machine learning identifies elevated hypertension and hypercholesterolemia in Parkinson’s disease patients, indicating atherosclerotic risk stratification may improve prognosis

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Unal et al. (2026) studied this question.

synapsesocial.com/papers/69c9c57ff8fdd13afe0bd7da https://doi.org/10.47582/jompac.1882083

View at Publisher

Ask AI

Bookmark

Share

Keep reading

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

1Quantitative susceptibility mapping and MRS-based multimodal machine learning for early Parkinson’s disease classificationOriginal Research · 2026
2Interpretable machine learning for cognitive impairment prediction in Parkinson’s disease: a multicenter validation study with SHAP analysis2025
3SHAP-based interpretable machine learning for Parkinson's disease severity prediction: integrated analysis of clinical and environmental features2025 · 11 citations
4Developing and validating a clinically actionable prediction tool for Parkinson disease using explainable machine learning with multidimensional national data: A cross-sectional studyLongitudinal Study · 2026
5A Comprehensive framework for Parkinson’s disease diagnosis using explainable artificial intelligence empowered machine learning techniques2024 · 41 citations

Personalized Data-Driven Robust Machine Learning Models to Differentiate Parkinson's Disease Patients Using Heterogeneous Risk Factors2025
Unveiling Key Biomarkers of Cardiovascular Risk in Psoriasis Through Explainable Artificial Intelligence2026
Interpretable machine learning for coronary heart disease risk stratification in patients with carotid atherosclerosis: A retrospective cross-sectional study2026
Vitreous humor attenuation on computed tomography and its association with hypertension: a retrospective comparative studyJournal of Medicine and Palliative Care · 2026
Association between temporomandibular disorders with anxiety and depression: a cross-sectional studyJournal of Medicine and Palliative Care · 2026

JMore from Journal of Medicine and Palliative Care

More from Inonu University

More from Ankara Yıldırım Beyazıt University