AI tool predicts cancer survival chances with single face photo, study finds

Read the original at The Straits Times ↗
Cite

The Straits Times. (2026, October 19). AI tool predicts cancer survival chances with single face photo, study finds. The Straits Times. https://www.straitstimes.com/world/united-states/ai-tool-predicts-cancer-survival-chances-with-single-face-photo-study-finds

Dated from the outlet's own feed. Check the original for its byline.

The Straits Times · collected 2026-10-20 · by The Straits Times

Quick Summary

Researchers developed an AI tool capable of predicting cancer patients' survival chances from a single face photo. The model was trained using over 40 million images and data from more than 30,000 cancer patients, accurately estimating age within about five years and classifying patients into high- or low-risk groups based on mortality risk within 90 days. Published in The Lancet Digital Health on October 19, the study highlights the tool's potential to complement doctors' assessments, especially when medical data is limited, though experts caution it needs further testing before clinical use.
Written locally by qwen2.5:14b on 2026-10-20, using this article's own text rather than the other coverage of the same event (that is the story summary below).

AI analysis runs on qwen2.5:14b, locally

Story summary

Doctors have developed an artificial intelligence tool that can predict a cancer patient's chances of survival from a single photograph of their face. The AI system was custom-built by experts at Mass General Brigham, a nonprofit healthcare system in Massachusetts, and its details were published in the Lancet Digital Health journal on October 19, 2026.

The tool, called FAHR-FaceSurvival, estimates a patient’s biological age and predicts their survival outcomes. It was trained on data from more than 40 million facial photographs, including over 30,000 cancer patients, many of whom had already passed away. The algorithm can estimate a person's biological age with an error margin of about five years and accurately categorize patients into higher- or lower-risk groups based on their likelihood of death within 90 days.

According to one of the study’s authors, Raymond Mak from the Mass General Brigham Cancer Institute, doctors are generally not very accurate in estimating end-of-life expectancy. The AI system complements doctors’ assessments and could potentially guide treatment decisions when medical data is limited.

Written for “AI Predicts Cancer Survival From Selfie” on 2026-10-20, grounded in this article and the 1 other(s) covering the same event.

Story

📰 AI Predicts Cancer Survival From Selfie
Technology · 2 article(s) covering the same event. See how they differ ↓

Compared with similar articles

This article reads unscored and hedges 16% of its claims. Each row says how that neighbour differs.
New AI tool can predict cancer survival by a single patient selfie, study suggests same event · 100%
The Guardian · 0.96 cosine similarity
⚖️ leaning not scored 🔴 28% hedged 7 of 25 📰 publisher trust 66
“Both articles describe the same AI tool developed to predict cancer patient survival from a single face photo, mentioning the same key details about its development and training.”
How this article was measured signals, leaning charts, publisher record, byline, topics and claims

Signals How these are calculated →

Claims extracted
19
sentences that state something as happening or true
Uncertain
16%
3 of 19 hedged ("reportedly", "may", "according to")
Leaning
not political
takes no side on a contested political question
Publisher signals
60/100
The Straits Times's corrections and hedging, across everything collected from it. Not a measure of accuracy.
Outlets on this story
2
Technology
Same framing elsewhere
1
articles that frame the event the way this one does
Analyzed 2026-10-20 · how these are computed

How this is being covered How these are calculated →

Article leaning vs. publisher reliability
Source leaning vs. consistency

Publisher

The Straits Times · 3156 article(s) · 3 correction(s) detected
Running correction rate · 3 correction(s)
2026-10-04
Tennessee prison chief resigns after failed execution
2026-10-03
US prison chief resigns after failed execution of death row inmate Christa Pike
2026-09-13
Russia hits Ukrainian-Polish border area, Kyiv says

Who wrote this

The Straits Times
2056 article(s) here · 1 carrying a prediction
🔮 hosting Tuesday's talks, and its President Alexander Stubb said he would attend meetings with Zelenskiy and Stoere, to discuss "Russia's illegal war of aggression against Ukraine and the overall security situation in Europe." Trump's son-in-law Jared Kushner was expected to attend meetings virtually, Norway said.
2026-10-20 · assertive framing · Zelenskiy to meet Witkoff as Trump praises Russia and rebukes Ukraine
🔮 A Cabinet meeting on Oct 20 is expected to give the go-ahead to the deployment and approve policing powers for soldiers temporarily supporting law enforcement in the city.
2026-10-20 · assertive framing · Italy to send 500 troops to Milan after clashes
🔮 During his two-day visit to the western cities of Mumbai and Jamnagar, Rubio is set to meet government and business leaders.
2026-10-20 · assertive framing · Rubio kicks off India visit with trade deal, Russian oil on agenda
🔮 Ukraine's President Volodymyr Zelenskiy will fly to Oslo to meet US special envoy Steve Witkoff on Tuesday, trying to repair ties with Washington that have deteriorated sharply over the past two weeks as President Donald Trump has increasingly courted Moscow.
2026-10-20 · assertive framing · Zelenskiy to meet Witkoff after Trump says Russia has been 'fine' on Ukraine
🔮 The AI tool showed it could estimate age with a margin of error of about five years and reliably allocate patients to higher- or lower-risk groups, which subsequently had different risks of death.
2026-10-20 · assertive framing · AI tool predicts cancer survival chances with single face photo, study finds
🔮 Trump has said he will not attack Iran before US midterm elections in November.
2026-10-20 · assertive framing · Hegseth meets Netanyahu in unannounced visit to Israel, source says
🔮 The Z.ai founders’ work on research partially funded by an alleged Chinese intelligence front highlights the risks cited by some US officials regarding China’s growing prowess in AI – and could add to further scrutiny of Z.ai in particular.
2026-10-20 · mixed framing · Z.ai founders worked on research funded by China institute that Britain tied to spies
🔮 The Russian Foreign Ministry said ahead of Lavrov’s visit to Iran that discussions were expected to focus on “ways to resolve the acute international crisis triggered by the unlawful aggression of the US and Israel” against the Islamic republic.
2026-10-20 · assertive framing · Iran foreign minister says Russia, Iran have ‘never’ worked so closely
🔮 Politicians on both the hard right and hard left have increasingly argued that restoring energy ties with Russia would help lower costs, challenging Europe's mainstream consensus on support for Ukraine.
2026-10-20 · assertive framing · As France erupts, Europe's far right gains from fuel-price anger ahead of elections
🔮 “As long as these incentives are not strong enough and consistent across countries, a company may well ask why it should contribute when its competitors are not doing so.”
2026-10-20 · assertive framing · Why is landmark UN biodiversity fund nearly empty?
Also by The Straits Times
Zelenskiy to meet Witkoff as Trump praises Russia and rebukes Ukraine
2026-10-20 · The Straits Times
Google Cloud services face outage in London, Revolut services down too
2026-10-20 · The Straits Times
Germany’s far-right AfD hit by mass e-mail theft
2026-10-20 · The Straits Times
Rubio kicks off India visit with trade deal, Russian oil on agenda
2026-10-20 · The Straits Times
Nothing else under this byline is closely related to this article, so these are simply their most recent.
All 2056 articles by The Straits Times →

Topics

Mass General Brigham Cancer Institute NEW YORK The Lancet Digital Health the University of Surrey

Subjects

Mak PERSON · 3× Bober PERSON · 2× Bloomberg ORG · 1× Hippocrates PERSON · 1× Mass General Brigham Cancer Institute ORG · 1× Miroslaw Bober PERSON · 1× NEW YORK GPE · 1× Raymond Mak PERSON · 1× The Lancet Digital Health ORG · 1× the University of Surrey ORG · 1×

Narrative

Bober added that the tool needs to be tested against doctors’ own judgment as well as across different hospitals and patient groups. Mak, who developed the tool with his team, said he was stunned by how well it worked for survival. The algorithm focused mostly on the bridge of the nose and the area just beneath the eyes to make its assessment, they found.
framing: assertive · carried by 1 article(s) · first seen 2026-10-20
🔮 The AI tool showed it could estimate age with a margin of error of about five years and reliably allocate patients to higher- or lower-risk groups, which subsequently had different risks of death.
2026-10-20 · The Straits Times
AI tool predicts cancer survival chances with single face photo, study finds · assertive framing

Claims (19 extracted, 3 hedged)

AI tool predicts cancer survival chances with single face photo, study finds AI generated NEW YORK - asserted
study → predict → AI
Researchers built an AI tool that can predict cancer patients’ survival chances by using a single photograph of their face, complementing doctors’ gut instincts to potentially guide treatment decisions, especially when medical data is scarce. asserted
data → build → decisions
The new model was trained to estimate a person’s age or, for those with cancer, their survival chances. asserted
model → train → cancer
The artificial intelligence was trained on more than 40 million images of people’s faces as well as photographs of more than 30,000 cancer patients, many of whom had already died. asserted
many → train → whom
The tool gave patients risk scores – those with the highest scores were more likely to die within 90 days, according to the research published in The Lancet Digital Health on Oct 19. uncertain
those → give → Oct
The scientists say the findings are a first. asserted
findings → say → ?
Doctors are trained to assess patients just by how they look, said Raymond Mak, a radiation oncologist at Mass General Brigham Cancer Institute and one of the study’s authors, but they are “in general not very good at estimating end-of-life expectancy”. asserted
they → train → expectancy
“We think that using AI, we can capture some of that physiological reserve, risk for mortality, just from a face photo,” Mak said in an interview. asserted
Mak → think → interview
The AI tool showed it could estimate age with a margin of error of about five years and reliably allocate patients to higher- or lower-risk groups, which subsequently had different risks of death. uncertain
which → show → death
The model worked across different ages, races, genders and types of cancer. asserted
model → work → cancer
AI tools are increasingly being tested for cancer detection and treatment, from helping to diagnose patients by reading scans to predicting the risk of a patient developing cancer by analysing genetic and lifestyle risk factors. asserted
tools → test → factors
Despite the promising results, Miroslaw Bober, professor of video processing and machine learning at the University of Surrey, said the tool is not ready for clinical use. asserted
tool → say → use
“Predicting an outcome is not the same as explaining it,” said Bober, who was not involved in the research. asserted
who → predict → research
“It has not shown that these predictions add clinically useful information beyond doctors’ assessments of a patient’s general health and fitness, which were not measured in the study,” he said. asserted
he → show → study
Bober added that the tool needs to be tested against doctors’ own judgment as well as across different hospitals and patient groups. Mak, who developed the tool with his team, said he was stunned by how well it worked for survival. The algorithm focused mostly on the bridge of the nose and the area just beneath the eyes to make its assessment, they found. asserted
they → add → assessment
He did some digging and found that Hippocrates was first to describe how sunken eyes and temples as well as a sharp nose were among the early physical signs of impending death. asserted
eyes → do → death
The tool is unlikely to be used to deny or limit patients’ access to medicine, according to Mak. uncertain
tool → use → Mak
“We know that doctors at the end of life tend to overtreat,” he said. asserted
he → know → life
He views it as “a way for doctors to have one more piece of information”. asserted
doctors → view → information
💬Give feedback
🕘History 🎫Support
Terms · Privacy · beta v2.0.0
Articles to 20 Oct 2026