Can face photographs help predict cancer survival?
A new study published in the Lancet Digital Health suggests that artificial intelligence can estimate a person’s biological age from a simple face photo, and that this estimate could help doctors predict survival in patients with cancer.
Researchers developed FaceAge, a deep learning system trained on over 58,000 publicly available face images. The goal was to estimate a person’s biological age, which may differ from their chronological age, and reflect their overall health and aging process more accurately, according to the study.
The system was tested on 6,196 patients with cancer across cohorts in the U.S. and the Netherlands. The study found that patients who “looked older” than their actual age were more likely to have worse survival outcomes, even after accounting for factors like cancer type, sex and age. On average, patients with cancer appeared nearly five years older than their peers without cancer.
FaceAge also improved predictions in patients receiving palliative care, boosting the accuracy of survival estimates when added to existing clinical tools. The AI’s estimates were linked to genetic markers of cellular aging, suggesting it may capture meaningful biological signals rather than just appearance.
While promising, the researchers acknowledged ethical concerns, including bias and potential misuse, and stress the need for further testing in diverse populations before clinical use.
Read more: The Lancet Digital Health
The article presented here is intended to inform you about the broader media perspective on dentistry, regardless of its alignment with the ADA's stance. It is important to note that publication of an article does not imply the ADA's endorsement, agreement, or promotion of its content.