Twin Health’s digital twin app improves user’s liver metrics by 9 points in 100 days
Twin Health, a digital twin service for metabolic health, claims its app helped a test user improve their metabolic health score by nine points in 100 days. The user, a Verge staff member, logged data from a Dexcom G7 continuous glucose monitor, smart scale, blood pressure cuff, Apple Watch, and lab tests into the Twin Health app. The service uses AI to predict glucose responses to meals,…
Key points
- Twin Health’s digital twin app claims a 9-point metabolic health score improvement in 100 days for a test user
- User’s triglycerides dropped by 70mg/dL and hs-CRP levels declined, with liver enzymes nearly normalized
- Service requires continuous data input (CGMs, scale, blood pressure, lab tests) and is currently limited to corporate/private health plans
Twin Health is not yet widely available, requiring corporate or private health plans and targeting users with chronic metabolic issues. The service provides hardware (CGMs, smart scale, blood pressure cuff) and supplements, along with human coaching. While the user reported behavioral changes—like avoiding unhealthy treats—they noted tracking fatigue and limited weight loss. The app’s predictions aligned with prior experience but offered little surprise. Twin Health’s bimonthly check-ins also motivated increased physical activity, including a 5K run and resumed strength training.
My AI doppelganger tells me what to eat
The Verge AI · 14 October 2026
Loading the full article…
This text was published by The Verge AI and written by Victoria Song. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Society & Work
All →- Meta’s AI assistant may access user networks without explicit consent, privacy expert warns · 1 src
- Google adds AI scam detection to Messages for more Android phones · 3 src
- Anthropic’s Claude AI sent fake murder tip to Philadelphia police, delayed reporting sparks criticism · 8 src
- OpenAI engineer Abdulrahman Alfozan charged with planting hidden recording device in executive conference room · 32 src
- MI5 warns AI may alter bioweapons development stakes · 1 src
Comments
via GitHub Discussions