Source study found
Story checked
Single photo predicts your chances of surviving cancer treatment (opens in a new tab)
newatlas.com · 2026-10-25
Short answer
Not assessedCheck incomplete.
We found a likely source study, but its evidence could not be prepared for claim review. The article's claims remain unverified.
Share this check
The story
Single photo predicts your chances of surviving cancer treatment
newatlas.com · 2026-10-25
The story’s checkable claims.
Read the original story (opens in a new tab)NewsLink checks it
Source study identified.
A source study was identified, but the study's evidence could not be prepared for claim assessment. No claim verdicts are available.
View article claimsThe source study
Foundation artificial intelligence models for health recognition by use of face photographs (FAHR-Face): a model development and validation study
Evidence layer
Claim by claim
A source study was identified, but the study's evidence could not be prepared for claim assessment. The claims below have not been assessed.
Reading mode
Scan verdicts. Open evidence only when needed.
Claim 1 of 8Not checkedResearchers at Mass General Brigham Cancer Institute have developed an AI tool that determines biological age and chances of surviving challenging cancer treatment from a single photograph of a face.View evidenceHide evidence
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Claim 2 of 8Not checkedThe tools could supplement clinicians' intuitive assessment of how well a patient might fare and potentially reduce reliance on extensive testing before intensive treatments.View evidenceHide evidence
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Claim 3 of 8Not checkedThe team built FAHR-Face, a foundation model trained on more than 42 million facial photos, and then fine-tuned it into FaceAge and FaceSurvival.View evidenceHide evidence
As statedmore than 42 million photos
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Claim 4 of 8Not checkedFaceAge estimated chronological age with a low average error of 5.1 years, compared with another model's 6.92 years, and it was said not to be tripped up by makeup, facelifts, glasses, or lighting changes, though it made small errors with nose jobs.View evidenceHide evidence
As stated5.1 years; 6.92 years
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Claim 5 of 8Not checkedPeople who appeared five or more years older than their actual age had a 21% higher risk of mortality, while looking five years younger than real age was associated with 17% higher survival rates.View evidenceHide evidence
As stated21% higher risk of mortality; 17% higher survival rates
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Claim 6 of 8Not checkedFaceSurvival was trained on facial photographs from more than 34,000 cancer patients undergoing radiotherapy, plus two additional groups of nearly 4,000 and 5,000 cancer patients.View evidenceHide evidence
As statedmore than 34,000; nearly 4,000 and 5,000
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Claim 7 of 8Not checkedFaceSurvival identified high-risk patients; those in the highest-risk category had more than triple the mortality rate of those in the lowest-risk category, and 52% died within 90 days versus 2.1% in the lowest-risk group.View evidenceHide evidence
As statedmore than triple; 52% vs 2.1% within 90 days
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Claim 8 of 8Not checkedThe article says consumer-grade facial photos could serve as a reliable, non-invasive biomarker to help clinicians gauge patients' overall health and treatment risk.View evidenceHide evidence
Not checked
A source study was identified, but the evidence comparison for this claim was not completed. No verdict has been assigned.
Method layer
NewsLink found the paper. Tessa takes you deeper.
NewsLink checks the story. Tessa is where you inspect the paper, authors, evidence, and research context.
Open the paper in Tessa
Foundation artificial intelligence models for health recognition by use of face photographs (FAHR-Face): a model development and validation study
The Lancet Digital Health · 2026
Why this one
Confident
NewsLink found the paper. Tessa is where you inspect it deeply.
Papers considered
The selected paper, plus nearby candidates.
Crossref, PubMed, Europe PMC · 16 candidate papers
Foundation artificial intelligence models for health recognition by use of face photographs (FAHR-Face): a model development and validation study
The Lancet Digital Health · 2026 · Crossref
Face aging rate quantifies change in biological age to predict cancer outcomes.
Nature Communications · 2026 · PubMed, Europe PMC
Table 3 : Unadjusted overall survival and breast cancer-specific survival.
Crossref
Associations Between G8 Geriatric Screening Score, Charlson Comorbidity Index, AI-Based Age Phenotype, and Overall Survival in Older Adults With Stage I-II Non-Small Cell Lung Cancer.
International Journal of Radiation Oncology, Biology, Physics · 2025 · PubMed, Europe PMC
Table 4 : Multivariate analysis overall survival and breast cancer-specific survival.
Crossref
FaceAge, a deep learning system to estimate biological age from face photographs to improve prognostication: a model development and validation study.
The Lancet. Digital Health · 2025 · PubMed, Europe PMC
And 10 more candidates considered.