AI Breakthrough: Predicting Cachexia in Cancer Patients with High Accuracy

AI predicts wasting syndrome in cancer patients

A newly developed AI can predict which cancer patients are at risk for a life-threatening wasting syndrome, a new study says. The syndrome, called cachexia, accounts for about 20% of all cancer-related deaths, statistics show. "Cancer cachexia is a serious complication affecting many patients with cancer and is characterized by systemic inflammation, severe muscle wasting, and profound weight loss," lead researcher Sabeen Ahmed, a graduate student at the University of South Florida, said in a news release. No one knows what causes cachexia, but inflammation, increased cancer metabolism, insulin resistance and hormone changes are suspected in the wasting syndrome, according to the National Cancer Institute. Cachexia can't be reversed by nutrition alone, but must be treated with medicines, the NCI says. It's hard to reverse once it starts, and is most common in people with advanced 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 said. "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 new study, researchers taught an AI program to estimate the risk of cachexia based on imaging scans and clinical data. The AI first examines CT scans to assess the amount of muscle in a person's body, and then uses other data to judge a patient's risk of cachexia, researchers said. The AI accurately identified cachexia in 77% of cases when fed imaging scans along with a patient's demographic info, weight, height and cancer stage, researchers reported. Accuracy increased to 81% with the addition of lab results and 85% when doctors' clinical notes were included in the mix, results show. Using this assessment, the AI was able to better predict survival odds for patients with pancreatic, colon and ovarian cancer, researchers said. Results also showed that the AI's assessment of muscle differed by about 2.5% on average from calculations made by expert 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 said. Ahmed presented these findings at the American Association for Cancer Research's annual meeting in Chicago.

AI Predicts Wasting Syndrome In Cancer Patients

MONDAY, April 28, 2025 (HealthDay News) -- A newly developed AI can predict which cancer patients are at risk for a life-threatening wasting syndrome, a new study says. The syndrome, called cachexia, accounts for about 20% of all cancer-related deaths, statistics show. "Cancer cachexia is a serious complication affecting many patients with cancer and is characterized by systemic inflammation, severe muscle wasting, and profound weight loss," lead researcher Sabeen Ahmed, a graduate student at the University of South Florida, said in a news release. No one knows what causes cachexia, but inflammation, increased cancer metabolism, insulin resistance and hormone changes are suspected in the wasting syndrome, according to the National Cancer Institute. Cachexia can't be reversed by nutrition alone, but must be treated with medicines, the NCI says. It's hard to reverse once it starts, and is most common in people with advanced 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 said. "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 new study, researchers taught an AI program to estimate risk of cachexia based on imaging scans and clinical data. The AI first examines CT scans to assess the amount of muscle in a person's body, and then uses other data to judge a patient's risk of cachexia, researchers said The AI accurately identified cachexia in 77% of cases when fed imaging scans along with a patient's demographic info, weight, height and cancer stage, researchers reported. Accuracy increased to 81% with the addition of lab results and 85% when doctors' clinical notes were included in the mix, results show. Using this assessment, the AI was able to better predict survival odds for patients with pancreatic, colon and ovarian cancer, researchers said. Results also showed that the AI's assessment of muscle differed by about 2.5% on average from calculations made by expert 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 said. Ahmed presented these findings Sunday at the American Association for Cancer Research's annual meeting in Chicago. Findings presented at a medical meeting should be considered preliminary until published in a peer-reviewed journal. SOURCE: American Association for Cancer Research, news release, April 27, 2025