Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices.
Abràmoff MD, Lavin PT, Birch M, Shah N, Folk JC. · 2018
Read Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. by Abràmoff MD, Lavin PT, Birch M, Shah N, Folk JC. (2018) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc6550188.txt.
Description
Abràmoff and co-authors report the pivotal trial of an autonomous AI that spots diabetic eye disease in primary care offices, writing in NPJ Digital Medicine. Diabetic retinopathy is the top cause of blindness in working-age adults, yet under half of patients keep up with eye exams. The system reads retinal photos on the spot, with no specialist in the loop.
The trial enrolled 900 adults with diabetes at ten clinics. Trained office staff ran the camera, and results were judged against an expert reading center using photos plus cross-section scans. The AI caught 87.2% of cases beyond mild disease and cleared 90.7% of healthy eyes, beating both preset bars, with usable images in 96.1% of patients. On these results the FDA authorized it — the first autonomous AI diagnostic cleared in any branch of medicine.
Catalog record
| CREATOR | Abràmoff MD, Lavin PT, Birch M, Shah N, Folk JC. |
|---|---|
| YEAR | 2018 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |