Artificial intelligence showed promise in diagnosing sarcopenia in patients with head and neck cancer.
Artificial intelligence (AI) may be able to diagnose sarcopenia in patients with head and neck cancer through a muscle mass assessment, according to researchers from Dana-Farber Cancer Institute.
Sarcopenia is the loss of muscle mass within a patient’s body, and increases the chances of poor outcomes.
“Sarcopenia is an indicator that the patient is not doing well. A real-time tool that tells us when a patient is losing muscle mass would trigger us to intervene and do something supportive to help,” lead author, Dr. Benjamin Kann, a radiation oncologist in the Department of Radiation Oncology at Dana-Farber Brigham Cancer Center, said in a press release.
When doctors are analyzing the presence of sarcopenia, they typically use a CT scan to determine if the condition is present in the abdomen or neck. This scan gives doctors a quick way to control sarcopenia. Although CT scans are available, they are extremely time-consuming, and not done often, as an expert needs to complete the scan.
So, researchers used data from more than 400 patients with head and neck cancer train AI to diagnose sarcopenia with CT scanning. The tool looked for muscle mass assessment and skeletal muscle index scores (SMI) .
“The AI model automatically delineates the muscle in the neck from other tissues. The results are transparent. You can see the outline of the muscle as assessed by AI and verify it with your own eyes,” according to Kann.
To check AI’s accuracy, researchers created another dataset to evaluate sarcopenia diagnoses in a group of patients who have already been determined by an expert panel to have sarcopenia. AI was able to correctly complete the assessments in less than one second.
SMI was seen as a more precise indicator than body mass index (BMI) of poor health outcomes throughout patients with a diagnosis of sarcopenia, resulting in an impactful clinical.
“BMI is an imperfect measure. It doesn’t tell you anything about fat content or muscle content, which are really the components we need to be measuring in the clinic,” Kann explained.
For patients with head and neck cancer, the three main types of treatments — which are often given in combination — are surgery, radiation and chemotherapy. With these treatments can difficulty swallowing, which can lead to a risk of poor nutrition and in more severe conditions, sarcopenia.
Sarcopenia is a very serious condition, resulting in lower quality of life, and sometimes, death, according to the press release. “Muscle mass is a very important indicator of health. People with more muscle mass are generally healthier and more robust,” Kann explained.
AI can now help to catch the early stages of sarcopenia during treatment as well. “If we see muscle mass begin to decline, we can do something to prevent it,” said Kann.
Researchers plan on investigating the way in which treatments and interventions can be most beneficial while using these scans. Muscle mass changes will also be evaluated by researchers in the foreseeable future.
For more news on cancer updates, research and education, don’t forget to subscribe to CURE®’s newsletters here
