Objective:
To evaluate the effectiveness of a clinic-based AI tool in reducing screen failures for geographic atrophy (GA) clinical trials.
Key Findings:
- AI-assisted prescreening identified 80 eligible eyes and 27 ineligible eyes.
- 67 of the 80 prescreened eyes were confirmed eligible by a reading center.
- Mean GA area measured by manual planimetry was 9.39 mm², while AI measured it at 8.98 mm².
- False-positive rate was 12% and false-negative rate was 1%.
- Screen failure rate was reduced from 25% to 16% with AI-assisted prescreening.
Interpretation:
The use of clinic-based AI tools may significantly reduce screening burden and improve efficiency in GA clinical trials.
Limitations:
- Discrepancies in eligibility were attributed to measurement error and confounding lesions.
- The study was conducted at a single center, which may limit generalizability.
Conclusion:
Clinic-based AI tools show promise in enhancing trial efficiency and reducing patient burden in GA clinical trials.
This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.