AI Predicts Cancer-Related Wasting Syndrome with Up to 85% Accuracy
A groundbreaking study has revealed that a newly developed artificial intelligence (AI) system can predict which cancer patients are most likely to develop cachexia, a severe and potentially life-threatening wasting syndrome. Cachexia is responsible for approximately 20% of all cancer-related deaths, making early detection crucial.
Cachexia is characterized by systemic inflammation, significant muscle loss, and substantial weight loss, according to Sabeen Ahmed, lead researcher and graduate student at the University of South Florida. The exact cause of cachexia remains unknown, but factors such as inflammation, increased cancer metabolism, insulin resistance, and hormonal changes are believed to contribute to its development.
Unlike simple weight loss, cachexia cannot be reversed through nutrition alone and requires medical intervention. It is particularly common among patients with advanced cancers and is challenging to reverse once it begins.
The AI system developed by the researchers analyzes CT scans to assess muscle mass and then evaluates a patient’s risk of developing cachexia using additional clinical data. In tests, the AI accurately identified cachexia in 77% of cases when provided with imaging scans, demographic information, weight, height, and cancer stage. The accuracy increased to 81% when lab results were included and reached 85% when doctors’ clinical notes were added to the data.
This assessment enabled the AI to better predict survival odds for patients with pancreatic, colon, and ovarian cancers. The AI’s evaluation of muscle mass differed from expert radiologists’ calculations by only about 2.5% on average, demonstrating its reliability.
“Detection of cancer cachexia enables interventions that can help slow muscle wasting, improve metabolic function, and enhance the patient’s quality of life,” Ahmed emphasized. Current detection methods rely on clinical observations, weight loss thresholds, and indirect biomarkers, which are often inconsistent and too late in disease progression.
The findings were presented at the American Association for Cancer Research’s annual meeting in Chicago. While considered preliminary until published in a peer-reviewed journal, the study highlights the potential of AI in improving cancer patient outcomes.
Early detection of cachexia is critical as it significantly increases a cancer patient’s risk of death. The National Cancer Institute provides more information on cancer cachexia, underscoring the importance of this research in the fight against cancer.
