Category: Epidemiology
Objective: To identify which risk/protective factors influenced most incident Parkinson’s disease (PD) risk in a population of almost 24,000 Italian citizens, using both classical statistical analyses and supervised machine learning analyses.
Background: Several environmental/lifestyle factors have been individually investigated in previous PD studies with controversial results. No study has prospectively and simultaneously investigated potential risk/protective factors of PD using both linear and non-linear statistical approaches. The latter may reveal more complex non-linear associations and hidden risk/protective patterns that may go undetected by linear models.
Method: Participants in the Moli-sani study were enrolled between 2005-2010 and followed up until December 2018. Incident PD cases were identified by individual-level record linkage to regional hospital discharge forms, the Italian death registry, and the regional prescription register. Exposure to potential risk/protective factors was assessed at baseline. Multivariable Cox proportional regression models and survival random forests were built to identify the most influential factors.
Results: We identified 213 incident PD cases out of 23,901 subjects. Linear association models revealed that age, sex, dysthyroidism, diabetes, and marginal paint exposure were associated with an increased risk of PD. Both hyper and hypothyroidism were independently associated with PD risk. A survival random forest showed that age was the most influential factor in PD risk, followed by coffee intake, daily physical activity, and hypertension.
Conclusion: This study sheds light on the role of dysthyroidism, diabetes and hypertension, characterized to date by an uncertain relationship with PD, and also confirms the relevance of most factors (age, sex, coffee intake, daily physical activity) reportedly shown be associated with PD.
The present abstract has been presented to the national congress of the Italian Society of Neurology (SIN), Milan (IT), 03-06 December 2022.
To cite this abstract in AMA style:
MI. de Bartolo, A. Gialluisi, S. Costanzo, D. Belvisi, S. Falciglia, M. Ricci, A. Di Castelnuovo, T. Panzera, MB. Donati, G. Fabbrini, G. de Gaetano, A. Berardelli, L. Iacoviello. Risk and protective factors in Parkinson’s disease: a simultaneous and prospective study with linear and machine learning models [abstract]. Mov Disord. 2023; 38 (suppl 1). https://www.mdsabstracts.org/abstract/risk-and-protective-factors-in-parkinsons-disease-a-simultaneous-and-prospective-study-with-linear-and-machine-learning-models/. Accessed June 15, 2025.« Back to 2023 International Congress
MDS Abstracts - https://www.mdsabstracts.org/abstract/risk-and-protective-factors-in-parkinsons-disease-a-simultaneous-and-prospective-study-with-linear-and-machine-learning-models/