biostudies-literatureNhat PTHWellcome Trust14798https://www.ebi.ac.uk/biostudies/studies/S-EPMC11208490biostudies-literatureUnknown14(1)Muscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the rectus femoris cross-sectional area (RFCSA), which is a subjective, time-consuming, and laborious task that requires significant expertise. We aimed to develop and evaluate an AI tool that performs automated recognition and measurement of RFCSA to support non-expert operators in measurement of the RFCSA using muscle ultrasound. Twenty patients were recruited between Feb 2023 and July 2023 and were randomized sequentially to operators using AI (n = 10) or non-AI (n = 10). Muscle loss during ICU stay was similar for both methods: 26 ± 15% for AI and 23 ± 11% for the non-AI, respScientific reportsClinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients.PMC11208490217650/Z/19/ZChanh HQKarlen WDenehy LGomez AAnh NHVan Hien HPhong NTDuc TMMoser NThao DPDung NTPPhu NHMcKnight JDuc DHPerez BHMing DVan Hao NChau LBYen LMHoang VTVan Nuil JITrung TNVan NTTPaton CThu LNMHill-Cawthorne KThwaites GTurner HPisani LGeorgiou PPhuong LTEnglish MHagenah JVan Vinh Chau NVan Khoa LDNguyen NTDuong HTHNgoc NTThwaites LThao TTPKhanh PNQDung NTThao LTMZhu TXochicale MManzano JRTrinh NTDGeskus RVan Thanh Duoc NQui PTOanh PKNTrinh DHKTrieu HTCanas LVuong NLAnh NTKHolmes AKhiem DPHung TMQuyen NTHLam PKVITAL ConsortiumRollinson TViet NQTho PVKhanh LTTNhat PTHNghia HDTKestelyn ELu PRazavi RKarolcik SKien DTThuy DBHai HBMcbride AYacoub SKieu PTSchultz MModat MVan PTHThy DBXHuyen VNTKing APToan LMAli NClifton DGiang NTKing AThao NTPAn LPTam CTHuy NQTai LTHTran LHBLe Thanh NTKerdegari HfalseClinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients.Muscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the rectus femoris cross-sectional area (RFCSA), which is a subjective, time-consuming, and laborious task that requires significant expertise. We aimed to develop and evaluate an AI tool that performs automated recognition and measurement of RFCSA to support non-expert operators in measurement of the RFCSA using muscle ultrasound. Twenty patients were recruited between Feb 2023 and July 2023 and were randomized sequentially to operators using AI (n = 10) or non-AI (n = 10). Muscle loss during ICU stay was similar for both methods: 26 ± 15% for AI and 23 ± 11% for the non-AI, resp2024-01-01T00:00:00Z2024 Jun2026-06-02T21:17:34.122Z2025-04-04T21:21:53.361ZS-EPMC112084903892642710.1038/s41598-024-64564-w