Artificial Intelligence-Based Prediction of Sarcopenia Risk in Intensive Care Unit Patients With Intracranial Pathology

This prospective observational study aims to evaluate sarcopenia in intensive care patients with intracranial pathologies using ultrasound and to compare the predictive performance of different artificial intelligence models. Rectus femoris muscle thickness will be measured by ultrasound on ICU admission (Day 0) and Day 7. Prealbumin levels will be assessed on Days 0, 3, and 7, and the modified Nutrition Risk in Critically Ill (mNUTRIC) score will be calculated on the first day of ICU admission. Clinical, laboratory, and ultrasonographic data will be integrated into different artificial intelligence models to predict sarcopenia status on Day 7. The study aims to determine the effectiveness of artificial intelligence in the early identification of sarcopenia and to support future clinical decision-making in intensive care practice.