Using Artificial Intelligence to Predict Muscle Loss Risk in Adults With Brain Injuries in Intensive Care Units

What this Trial Is About

Researchers are evaluating the early prediction of muscle loss, known as sarcopenia, in intensive care patients with brain injuries. This prospective observational study focuses on adults aged 18 to 65 admitted to intensive care units with various intracranial conditions such as hemorrhages, tumors, and ischemic stroke. The study aims to compare the accuracy of different artificial intelligence models in predicting sarcopenia development by day 7 of ICU admission. Participants will be observed without any experimental treatment changes. Their rectus femoris muscle thickness will be measured using ultrasound on the day of ICU admission Day 0 and again on Day 7. Blood levels of prealbumin, a nutritional marker, will be checked on Days 0, 3, and 7. The modified Nutrition Risk in Critically Ill mNUTRIC score will be calculated on the first ICU day. These clinical, laboratory, and ultrasound data will be fed into various AI models to evaluate their prediction performance. During the study, patients will undergo routine clinical monitoring, and all data will be collected as part of standard care. Ultrasound measurements will be standardized and performed by the same investigator. Researchers will measure how accurately AI models predict muscle loss by Day 7 and compare these predictions with clinical assessments. Data privacy will be strictly maintained, with all information securely stored and de-identified. The study is planned to enroll 100 to 150 patients and run from January to August 2026.

Al Prediction of Sarcopenia Risk in Neurocritical ICU Patients