AI Based Muscular Ultrasound to Assess Intensive Care Unit-acquired Weakness

The aim of this observational case-control study is to investigate, whether artificial intelligence can detect ultrasound-derived imaging characteristics typical for intensive care unit-acquired weakness. The main questions it aims to answer are: 1. Is the evaluation of specific parameters of neuromuscular ultrasound using AI-based image analysis suitable for detecting and monitoring critically ill ICU patients with ICUAW? 2. Do the results of AI-based ultrasound image analysis correlate with: (A) the severity of ICUAW (B) the visual grading of muscle echogenicity (C) the 30- and 90-day-outcome?

Inclusion Criteria: * Patients aged 18 years or above * Major elective surgery, e.g. cardiothoracic or abdominal surgery * Expected ICU stay \>1 day postoperatively * Healthy, age-machted subjects without ICUAW (recruited from staff of the department of anesthesiology and intensive care medicine) Exclusion Criteria: * No informed consent * Emergency surgery * Previous participation in the same study * Preexisting neuromuscular disease * Preexisting central nervous system disease with residual neuromuscular impairment (e.g. cerebral haemorrhage, stroke, brain tumor) * High-dose glucocorticoid therapy (\>300 mg hydrocortisone or equivalent per day) before or during particiation in the study