Objective: To investigate the directional influence between cardiovascular factors/interventions and Parkinson’s disease using causal inference based machine learning techniques.

Background: Parkinson’s disease (PD) is a neurodegenerative disorder whose development may be influenced by several risk factors. Procedures such as angioplasty, bypass surgery, and heart valve repair affect circulatory dynamics. We hypothesize that these changes may contribute to an increased risk of developing PD by influencing the vascular supply to the basal ganglia.

Method: We conducted a retrospective analysis using data from the NACC Database [1] till September 2024, where PD patients were diagnosed based on the UK PDS Brain Bank Criteria. We excluded early-onset PD (<50 years) and those on anti-psychotics. Missing data was imputed using Miss Forest Algorithm. Controls were matched with PD patients based on age and sex using the nearest-neighbor approach. Directed Acyclic Graphs guided the selection of features and confounders (e.g., hypercholesterolemia, BMI, smoking, hypertension and diabetes) [figure 1]. A Causal Forest model estimated both Average Treatment Effect (ATE) and marginal treatment effects. Additionally a simple linear regression was performed for validation.

Results: The analysis included 1163 PD patients and 1163 matched controls. The ATE of cardiovascular factors on PD was 0.241 and 0.193 for training and test data. Marginal effects revealed that procedures such as percutaneous coronary intervention (1.772), heart valve replacement (1.510), in the last 12 months had strong positive associations with PD [figure 2]. In contrast, carotid procedures (-0.081) and myocardial infarction (-0.970) demonstrated negative effects. In a linear regression, heart valve replacement (β = 0.348, p = 0.013) was significant. Myocardial infarction (β = -0.073, p = 0.293) and Carotid procedures (β = -0.24, p = 0.006) showed negative effects.

Conclusion: This study highlights potential causal links between cardiovascular interventions, such as heart valve replacement and PD. However, Vascular parkinsonism was not specifically excluded, which is offset by the robust algorithm used. These findings suggest possible directions of influence, but larger sample sizes are required for validation and further exploration of underlying bias.

figure 1

figure 2

References: 1. NACC Home | National Alzheimer’s Coordinating Center. Accessed March, 2025. https://naccdata.org/

Acknowledgment:
The NACC database is funded by NIA/NIH Grant U24 AG072122. NACC data are contributed by the NIA-funded ADRCs: P30 AG062429 (PI James Brewer, MD, PhD), P30 AG066468 (PI Oscar Lopez, MD), P30 AG062421 (PI Bradley Hyman, MD, PhD), P30 AG066509 (PI Thomas Grabowski, MD), P30 AG066514 (PI Mary Sano, PhD), P30 AG066530 (PI Helena Chui, MD), P30 AG066507 (PI Marilyn Albert, PhD), P30 AG066444 (PI David Holtzman, MD), P30 AG066518 (PI Lisa Silbert, MD, MCR), P30 AG066512 (PI Thomas Wisniewski, MD), P30 AG066462 (PI Scott Small, MD), P30 AG072979 (PI David Wolk, MD), P30 AG072972 (PI Charles DeCarli, MD), P30 AG072976 (PI Andrew Saykin, PsyD), P30 AG072975 (PI Julie A. Schneider, MD, MS), P30 AG072978 (PI Ann McKee, MD), P30 AG072977 (PI Robert Vassar, PhD), P30 AG066519 (PI Frank LaFerla, PhD), P30 AG062677 (PI Ronald Petersen, MD, PhD), P30 AG079280 (PI Jessica Langbaum, PhD), P30 AG062422 (PI Gil Rabinovici, MD), P30 AG066511 (PI Allan Levey, MD, PhD), P30 AG072946 (PI Linda Van Eldik, PhD), P30 AG062715 (PI Sanjay Asthana, MD, FRCP), P30 AG072973 (PI Russell Swerdlow, MD), P30 AG066506 (PI Glenn Smith, PhD, ABPP), P30 AG066508 (PI Stephen Strittmatter, MD, PhD), P30 AG066515 (PI Victor Henderson, MD, MS), P30 AG072947 (PI Suzanne Craft, PhD), P30 AG072931 (PI Henry Paulson, MD, PhD), P30 AG066546 (PI Sudha Seshadri, MD), P30 AG086401 (PI Erik Roberson, MD, PhD), P30 AG086404 (PI Gary Rosenberg, MD), P20 AG068082 (PI Angela Jefferson, PhD), P30 AG072958 (PI Heather Whitson, MD), P30 AG072959 (PI James Leverenz, MD).

« Back to 2025 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/determining-the-influence-of-cardiovascular-interventions-and-factors-on-developing-parkinsons-disease-inferences-from-a-data-driven-causal-forest-model/