Objective: To apply machine learning and epidemiology to identify existing drugs that may have a disease modifying effect in Parkinson’s disease (PD).

Background: Drug repurposing is an effective means of increasing treatment options for diseases, but identifying candidate molecules for the indication of interest from the thousands of approved drugs is challenging. We have used machine learning to rank drugs approved for human use according to predicted ability to reduce alpha synuclein (aSyn) oligomerization. To provide evidence of a possible disease modifying effect in PD we have analyzed real-world data to investigate the association between exposure to highly ranked drugs and PD diagnosis.

Method: Using IBM Watson for Drug Discovery we identified several antihypertensive drugs that may reduce aSyn oligomer levels in cell or animal models. Using IBM MarketScan Research Databases we constructed a cohort of individuals with incident hypertension (HTN). Drugs were categorized as alpha-blockers (AB), beta-blockers (BB), ACE inhibitors (ACEi), angiotensin receptor blockers (ARBs), Renin Inhibitors (RI), dihydropyridine calcium channel blockers (DHP-CCB), non-dihydropyridine CCB (CCB) and diuretics. Exposure to HTN medications was classified as single, double or 3+ agents. We conducted univariate and multivariate Cox proportional hazard analyses with exposure as a time-dependent covariate. Diuretics were used as the referent group. Age at HTN diagnosis, sex, and several comorbidities were included in multivariate analyses.

Results: Compared to diuretics alone, ACEi with diuretics, ARBs with DHP-CCB, ARBs with diuretics, DHP-CCBs alone, and DHP-CCBs with diuretics were significantly associated with decreased risk of diagnosis of PD in univariate analyses. In multivariate analyses, ACEi with diuretics remained significant (hazard ratio =0.60, p-value < 0.01) as did ARBs plus DHP-CCBs (hazard ratio= 0.55, p-value < 0.01).

Conclusion: Exposure to the combinations of DHP-CCB with ARBs, as well as ACEi with diuretics, may reduce the risk of PD.   Our findings require replication in other cohorts.

References: Acknowledgements The authors would like to acknowledge: the Ontario Brain Institute and the Government of Ontario for providing access and training to the IBM Watson Drug Discovery platform.

« Back to 2019 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/exploring-anti-hypertensives-as-possible-disease-modifying-agents-in-parkinsons-disease-using-artificial-intelligence-and-epidemiology/