Research from Alphabet's Verily shows that blood pressure, age, whether someone smokes, and more can be deduced by analyzing scans of patients' retinas with AI
James Vincent / The Verge :
Context & Ripple Effects
The retina has been quietly turning into Alphabet's favorite diagnostic surface. DeepMind's five-year project on a million anonymous NHS eye scans established the data pipeline, and this Verily result shows why the effort was worth it: the same image that screens for eye disease also encodes blood pressure, age, and smoking status.
The finding lands ahead of the regulatory and payment infrastructure that would commercialize it — an approval path that arrived weeks later with the first FDA-cleared AI diagnostic requiring no doctor interpretation, and a reimbursement one by 2020 when CMS began paying doctors to use AI eye-disease diagnostics.
First-order effects
- Clinics already photographing retinas for diabetic screening gain cardiovascular risk signals — blood pressure and smoking status — from images they were taking anyway, at no added capture cost.
Second-order effects
- Payers and employers get a cheap, passive biomarker source, which pressures device makers and EHR vendors to treat every retinal camera as a multi-purpose sensor rather than an eye-disease tool.
Third-order effects
- If inference from incidental scans keeps expanding — as it did years later with RETFound predicting heart failure and Parkinson's risk from retinal images — medical imaging shifts from targeted diagnosis toward opportunistic screening, forcing regulators to decide when an inference counts as a diagnosis and who consents to it.
The trend: Retinal imaging is becoming a general-purpose health-data platform, with Alphabet building the scan pipelines, models, and regulatory precedents across Verily, DeepMind, and Google.