Abstract
Purpose :
Age-related cataract is the leading cause of blindness worldwide and associated with impaired quality of life. Anti-cataract compounds can block its progression in animal models but their clinical validation is lacking. Thus, currently, no medication is approved or known to delay clinical cataract progression.
Methods :
We developed an AI-based drug discovery system for repurposing potential anti-cataract drugs among 2650 FDA approved drugs and used a retrospective cohort design leveraging multicenter electronic health records (EHRs) from TriNetX platform with 793,108 patients with diabetes and cataract.. The clinical efficacy of the top-10 drug candidates was ranked by our Ai based drug repositoning system. Hazard ratios (HR) with 95% confidence intervals (95% CI) was used to investigate cataract surgery risk at various time points after drug prescription (3, 5, 10, and 20 years).
Results :
Among top-10 AI predicted repurposed candidate drugs, aspirin, acetylcysteine, melatonin, and ibuprofen were associated with a reduced 3, 5, 10 and 20-year cataract extraction risk in both male and female diabetic patients. At 20 years, adjusted hazard ratios (HR) were 0.83 [0.80-0.87], 0.78 [0.68-0.88], 0.83 [0.77-0.88], 0.78 [0.74-0.81], respectively. The relative risk of cataract surgery at 20 years was suppressed ~40%, 15%, 7% and 0-7% by melatonin, ibuprofen, acetylcysteine, and aspirin, respectively.
Conclusions :
Four repositioned drugs have the potential to delay cataract progression in diabetes. Of these, melatonin appears to have the most robust and sustained potential in both genders. All four drugs share in common the ability to directly or indirectly inhibit cyclooxygenase-2 (COX-2), an enzyme that is increased by multiple cataractogenic stimuli.
This abstract was presented at the 2023 ARVO Annual Meeting, held in New Orleans, LA, April 23-27, 2023.