This is a Plain English Papers summary of a research paper called AI Eye Scan Detects Stroke Risk with 87% Accuracy Using Dual-Eye Analysis. If you like these kinds of analysis, you should join AImodels.fyi or follow us on Twitter.
Overview
- Deep learning approach for detecting stroke risk through retinal images
- Multi-view learning system analyzes fundus photographs from both eyes
- Dataset of 48,116 retinal images from 12,029 patients
- Achieved 87.2% accuracy in stroke detection
- Novel method combines features from left and right eye images
Plain English Explanation
The eyes offer a unique window into brain health. This research presents a way to detect stroke risk by examining photographs of the back of both eyes (retinal fundus images). Think of it like looking at two security cameras that give different views of the same scene - by comb...
Top comments (0)