A newly developed AI can predict which most cancers sufferers are in danger for a life-threatening losing syndrome, a brand new examine says.
The syndrome, referred to as cachexia, accounts for about 20% of all cancer-related deaths, statistics present.
Nobody is aware of what causes cachexia, however irritation, elevated most cancers metabolism, insulin resistance and hormone adjustments are suspected within the losing syndrome, in line with the Nationwide Most cancers Institute.
Cachexia cannot be reversed by vitamin alone, however have to be handled with medicines, the NCI says. It is laborious to reverse as soon as it begins, and is most typical in folks with superior cancers.
“Detection of cancer cachexia enables lifestyle and pharmacological interventions that can help slow muscle wasting, improve metabolic function, and enhance the patient’s quality of life,” Ahmed stated.
“Unfortunately, current methods for detecting cancer cachexia rely on clinical observations, weight loss thresholds, and indirect biomarkers, which are often inconsistent, subjective, and detected too late in disease progression,” she added.
For the brand new examine, researchers taught an AI program to estimate the danger of cachexia primarily based on imaging scans and medical knowledge.
The AI first examines CT scans to evaluate the quantity of muscle in an individual’s physique, after which makes use of different knowledge to guage a affected person’s threat of cachexia, researchers stated.
The AI precisely recognized cachexia in 77% of circumstances when fed imaging scans together with a affected person’s demographic information, weight, peak and most cancers stage, researchers reported.
Accuracy elevated to 81% with the addition of lab outcomes and 85% when docs’ medical notes had been included within the combine, outcomes present.
Utilizing this evaluation, the AI was in a position to higher predict survival odds for sufferers with pancreatic, colon and ovarian most cancers, researchers stated.
Outcomes additionally confirmed that the AI’s evaluation of muscle differed by about 2.5% on common from calculations made by skilled radiologists.
“The median discrepancy of 2.48% indicates that, on average, the model’s measurements of skeletal muscle were very close to the expert radiologists’ measurements, demonstrating the high reliability of our AI-based approach,” Ahmed stated.
Ahmed offered these findings on the American Affiliation for Most cancers Analysis’s annual assembly in Chicago.
Quotation:
AI predicts losing syndrome in most cancers sufferers (2025, April 28)
retrieved 28 April 2025
from https://medicalxpress.com/information/2025-04-ai-syndrome-cancer-patients.html
This doc is topic to copyright. Other than any truthful dealing for the aim of personal examine or analysis, no
half could also be reproduced with out the written permission. The content material is offered for data functions solely.
