AI tool predicts cancer survival chances with single face photo
Trained on over 40 million images of faces, the model assigns risk scores to those with the illness
Researchers have developed an artificial intelligence tool capable of predicting cancer patients' survival chances based on a single face photograph. Trained on over 40 million images of faces and more than 30,000 cancer patient photographs, the model assigns risk scores to patients, with higher scores indicating a greater likelihood of death within 90 days, according to the study published in Lancet Digital Health.
The AI tool estimates a patient's age with a margin of error of approximately 5 years and accurately classifies patients into higher or lower risk groups, which subsequently have varying risks of death. This technology can be applied across different ages, races, genders, and types of cancer. However, while the findings are groundbreaking, the tool is not yet ready for clinical use.
Miroslaw Bober, a professor of video processing and machine learning at the University of Surrey, cautions that predicting outcomes is not the same as explaining them, as the study did not demonstrate how the predictions could add clinically useful information beyond doctors' assessments of patients' general health and fitness. The researchers found that the algorithm focused primarily on the bridge of the nose and the area just beneath the eyes to make its assessments.
Despite the promising results, further testing against doctors' own judgments and across various hospitals and patient groups is necessary before the tool can be integrated into clinical practice.
Written by urgent.news from The Business Times - Companies & Markets's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
