FAHR-FaceSurvival

Biomarker

2 papers study it2 findings

Humans2

Associations

Mortality

upin humans1upin silico1HR 3.22

2 studies

FAHR-FaceSurvival predicts mortality in humans (adjusted hazard ratio 3.23; p<0.0001).
“FAHR-FaceSurvival showed robust prediction of mortality, and the highest-risk quartile had more than triple the mortality of the lowest (adjusted hazard ratio 3·23; p<0·0001).”
Humanspatients with cancer; highest-risk versus lowest-risk quartile
Face-photo predictions linked to mortality in cancer patients
The Lancet. Digital healthOct 20, 2026
FAHR-FaceSurvival predicts mortality in silico (adjusted HR 3.22, P<0.001).
“the highest-risk quartile had more than triple the mortality of the lowest (adjusted hazard ratio 3.22; P<0.001)”
In silicoin cancer patients
Foundation Artificial Intelligence Models for Health Recognition Using Face Photographs (FAHR-Face)
arXiv (Cornell University)Jun 17, 2025Preprint

Latest

1 paper in 12 months

The Lancet Digital Health6 h

Face-photo predictions linked to mortality in cancer patients

In patients with cancer, the survival model’s highest-risk quarter had more than triple the relative mortality risk of the lowest-risk quarter.In patients with cancer, the survival model’s highest-risk quarter had more than triple the relative mortality risk of the lowest-risk quarter.

Cohort studyAI & data

Paper

arXivJun 17

Foundation Artificial Intelligence Models for Health Recognition Using Face Photographs (FAHR-Face)

Preprint: study of 34,389 peopleAI & data