FaceAge, a deep learning system, was developed and validated to estimate biological age from photographs of faces. In a study published in The Lancet Digital Health, FaceAge showed the ability to predict short-term outcomes in patients with cancer.
The study demonstrated that FaceAge could determine biological age compared with chronological age in patients with cancer and that the biological age tended to be more advanced for patients with cancer than those without. Additionally, the model found that older biological age, or FaceAge, than the chronological age in patients with cancer was associated with worse survival outcomes, especially in those who looked older than 85, even after adjusting for factors of cancer type, sex, and chronological age.
“We can use artificial intelligence [AI] to estimate a person’s biological age from face pictures, and our study shows that information can be clinically meaningful,” said co-senior and corresponding author Hugo Aerts, PhD, Director of the Artificial Intelligence in Medicine (AIM) program at Mass General Brigham. “This work demonstrates that a photo, like a simple selfie, contains important information that could help to inform clinical decision-making and care plans for patients and clinicians. How old someone looks compared to their chronological age really matters—individuals with FaceAges that are younger than their chronological ages do significantly better after cancer therapy.”
Study Methods and Results
The investigators trained FaceAge on data from 58,851 presumed-healthy individuals who were aged 60 or older, including 56,304 from the IMDb-Wiki data set, which was used for training, and 2,547 from the UTKFace data set, which was used for validation. Additionally, the tool was trained with 6,196 patients with cancer from the Netherlands and the United States who were receiving radiotherapy and compared them with a group of 535 patients without cancer.
The study results showed that an older biological age than the patient’s real chronological age was correlated with worse overall survival (hazard ratio [HR] = 1.151; P = .013 for a pan-cancer cohort and HR = 1.117; P = .021 in a palliative cohort). Most patients with cancer also had a higher biological age than their chronological age (mean increase of 4.79 years; P < .0001). Among patients with incurable cancer who were receiving palliative radiotherapy, FaceAge could improve physicians’ survival predictions from an AUC of 0.74 to 0.8 (P < .0001), which the study authors suggested may help with end-of-life decision-making.
“This opens the door to a whole new realm of biomarker discovery from photographs, and its potential goes far beyond cancer care or predicting age,” said co-senior author Ray Mak, MD, a faculty member in the AIM program at Mass General Brigham. “As we increasingly think of different chronic diseases as diseases of aging, it becomes even more important to be able to accurately predict an individual’s aging trajectory. I hope we can ultimately use this technology as an early detection system in a variety of applications, within a strong regulatory and ethical framework, to help save lives.”
“Subject to further testing and validation, approaches such as FaceAge could be used to translate a patient’s visual appearance into objective, quantitative, and clinically valuable measures,” the study authors concluded.
Disclosure: For full disclosures of the study authors, visit thelancet.com.
