Sarcopenia detection with portable ultrasound

Recent advancements in healthcare show that machine learning models can be used in clinical practice, embedded into assisting tools, aiming to enhance the experience of both patients and clinicians. Specifically in the field of disease monitoring and improving the QoL of patients, applications are being developed to be tailored to each patient's symptoms to produce personal recommendations. This study focuses on the development of a tool designed to monitor sarcopenia, a disease characterized by muscle wasting and malnutrition, in this case in advanced pancreatic cancer patients. The aim is to develop a multimodal approach, utilizing measurements from electronic health records (EHR), the measurement of a hand-held dynamometer and the 4m walking stride, alongside muscle ultrasound images from the biceps branchii, to measure the muscle thickness and estimate the stage of the disease. The ultimate goal of using portable ultrasound devices for disease monitoring, combined with AI tools, is cutting down expensive and time-consuming exams, as well as providing selfmanagement of the disease. This study falls on but is not limited to the scope of the Horizon RELEVIUM Project.