Face aging rate, a measure of changes in biological age over time, could serve as a non-invasive prognostic biomarker for determining outcomes in patients with cancer, according to the results of a study published in Nature Communications.
“Deriving a Face Aging Rate from multiple, routine facial photographs allows for near real-time tracking of an individual’s health,” said co-senior and corresponding author Raymond Mak, MD, Radiation Oncologist at Mass General Brigham Cancer Institute and a Faculty Member in the Artificial Intelligence in Medicine (AIM) program at Mass General Brigham. “Our study suggests that [using an AI tool to measure face age] over time may refine personalized treatment planning, improve patient counseling, and help guide the frequency and intensity of follow-up in oncology.”
Background and Study Methods
Researchers used FaceAge, an artificial intelligence (AI) tool that can estimate biological age from a photograph of a person's face, to calculate face aging rate from serial facial photographs. FaceAge has previously been used as a biomarker for cancer prognosis.
In the new study, researchers analyzed data and multiple photographs taken during routine care from 2,276 patients with cancer who were receiving radiation therapy at Brigham and Women's Hospital between 2012 and 2023.
Face aging rate was calculated in the study as the change in FaceAge divided by the time between photographs.
Key Findings
A higher face aging rate was associated with worse overall survival for patients with cancer undergoing radiation therapy. In patients with a short time frame between photographs (range, 10–365 days), the adjusted hazard ratio (aHR) was 1.25 (95% confidence interval [CI] = 1.03–1.51); the aHR for patients with a medium time frame between photographs (range, 366–730 days) was 1.37 (95% CI = 1.00–1.86), and was 1.65 (95% CI = 1.22–2.22) for patients with a longer time frame between photographs (range, 731–1,460 days). Adjustments were made for time between photographs, sex, race, and cancer diagnosis.
Face aging rate provided prognostic information beyond just one-off measures of FaceAge and the researchers believe that it can capture dynamic changes in biological aging, making it a useful prognostic biomarker for patients with cancer.
“Tracking FaceAge over time from simple photos offers a non-invasive, cost-effective biomarker with potential to inform individuals of their health,” said study co-author Hugo Aerts, PhD, Director of the AIM program at Mass General Brigham. “We hope with continued study we can learn how FaceAge may provide prognostic information for patients with other chronic diseases and for healthy individuals.”
The researchers have also created an institutional review board–approved web portal for patients with cancer to submit their own photographs for FaceAge assessments.
The research team hopes to expand FaceAge to study prognoses from other diseases as well.
DISCLOSURES: This research was partly funded by a philanthropic gift from George Denny. Dr. Mak reports being on an Advisory Board for ViewRay and AstraZeneca; Consulting for AstraZeneca, Pfizer, Varian Medical Systems, and Sio Capital Management; Honorarium from Novartis and Springer Nature; and Research Funding from the National Institute of Health, ViewRay, AstraZeneca, Siemens Medical Solutions USA, Inc., and Varian Medical Systems; Patents pending for FaceAge and related technologies. For full disclosures of the other study authors, visit nature.com.
