Creating a Non-invasive Tool Using Machine Learning and Bioimpedance to Detect Metabolic Dysfunction-associated Steatotic Liver Disease MASLD in Clinical Trial Volunteers

What this Trial Is About

Researchers are studying metabolic dysfunction-associated steatotic liver disease MASLD, commonly known as fatty liver disease, which affects about 25% of the population and can lead to serious liver problems including inflammation, scarring, and cancer. This observational study aims to develop a non-invasive clinical scoring tool to accurately predict MASLD in volunteers, including both healthy individuals and patients with known MASLD, without needing invasive procedures like tissue biopsies. Volunteers will attend a single study visit where they will provide consent and undergo various assessments including blood tests, body measurements such as BMI and waist circumference, and a full medical history and physical exam. Additional tests include bioimpedance body composition analysis using an ACUNIQ device, liver ultrasound, and fibroscan. After all assessments, volunteers will be discharged, and the collected data will be analyzed using statistical and machine learning methods to develop the predictive clinical score. Participants will complete all assessments in one day at the study unit. Researchers will measure the effectiveness of the classification tool over one year and establish normal liver function test ranges for patients with non-alcoholic fatty liver disease NAFLD. The study involves no treatment administration, focusing on diagnostic evaluations, and ensures volunteer safety by excluding those with certain liver diseases or implanted cardiac devices. Total participation time is limited to the single visit, with data analysis conducted afterward.

Development of a Non-invasive Screening Tool to Predict Metabolic Dysfunction-associated Steatotic Liver Disease