The diagnostic accuracy of AI-assisted diabetic retinopathy screening in primary care: a prospective validation study
Malene Krogh, Marie Ørskov, Thomas Lohne Nørgaard, Marie Germund Nielsen, Martin Bach Jensen, Morten Sig Ager Jensen, Henrik Vorum, Jette Kolding Kristensen · 2026
Read The diagnostic accuracy of AI-assisted diabetic retinopathy screening in primary care: a prospective validation study by Malene Krogh, Marie Ørskov, Thomas Lohne Nørgaard, Marie Germund Nielsen, Martin Bach Jensen, Morten Sig Ager Jensen, Henrik Vorum, Jette Kolding Kristensen (2026) 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/pmc-13267037.txt.
Description
Malene Krogh and co-authors test AI eye screening in primary care in a 2026 study. Diabetes can damage the retina, and regular screening catches it early. The team asked whether an AI tool used in local clinics could match screening led by eye specialists.
Patients with type 2 diabetes at ten clinics were screened with the AI tool, then re-screened at an eye clinic. Among 183 patients, about a fifth of the images were poor quality. Counting all images, the AI found about three-quarters of true cases and cleared nine in ten healthy ones. Dropping poor images raised detection to 80 percent. The scan also flagged other eye problems in many patients. The authors urge larger trials and better image quality first.
Catalog record
| CREATOR | Malene Krogh, Marie Ørskov, Thomas Lohne Nørgaard, Marie Germund Nielsen, Martin Bach Jensen, Morten Sig Ager Jensen, Henrik Vorum, Jette Kolding Kristensen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |