The study developed FAHR-Face, a foundation model pre-trained on over 40 million facial photographs. It was fine-tuned for biological age estimation using ten public image datasets. A separate fine-tuning for survival prediction used 34,363 photographs of patients with cancer, with two independent validation cohorts. For age estimation it had the lowest mean absolute error among the benchmark models tested across the lifespan. In patients with cancer, the highest-risk quartile had more than triple the mortality of the lowest after adjustment for clinical prognostic factors. Clinical testing was confined to patients with cancer, so general population performance is untested.
Why it is interesting: Face photographs are cheap and widely captured, and here they predicted mortality independently of clinical prognostic factors. The work also separates facial ageing from disease-related mortality risk.
Cite this item
BibTeX
Free sign-up. A digest of the new papers twice a week, grouped by domain.
Other drivers in Data, models and systems
-
Forecasts and their record
How the forecasts are made, how well they explained the past, and how well mortality can be forecast — and by whom.
5 this week -
What linked data reveals
What linked registries make it possible to know about whole populations
9 this week -
AI in medicine
Whether machine learning predicts, detects and decides better than the tools we have, and whether that has yet changed an outcome for a population.
5 this week -
Health systems and access
What the health system can provide, who gets it, and whether the gaps in health between groups are widening.
4 this week -
Value in health
What a treatment, health programme or policy is worth against what it costs, and how far the models that decide it can be trusted.
7 this week -
Revisions and new sources
What the figures are built from, what is newly available, and how much the numbers move when they are revised.
7 this week
