Dr Chris Paton

Abstract

Background 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 to support non-expert operators in measurement of the RFCSA using muscle ultrasound. Method This is a prospective study conducted in the ICU at the Hospital of Tropical Diseases (HTD), Ho Chi Minh city, Vietnam. Patients diagnosed with severe tetanus underwent three muscle ultrasound examinations of their Rectus Femoris muscle (on day 1, day 7 and ICU discharge). Patients were randomized to undergo the examinations performed by a group of non-expert users, with or without an AI tool for assistance. Results Twenty patients were recruited at the Adult ICU at HTD between Feb 2023 and July 2023 and were randomized sequentially to operators using AI (n = 10) or non-AI (n = 10). The median (IQR) ICU stay was 23 days (IQR 20–30). Muscle loss during ICU stay was similar for both methods: 26 ± 15% for AI and 23 ± 11% for the non-AI, respectively (p = 0.13). In total 59 ultrasound examinations were carried out (30 without AI and 29 with AI). When assisted by our AI tool, the operators showed less variability between measurements with higher intraclass correlation coefficients (ICCs 0.999 95%CI 0.998–0.999 vs. 0.982 95%CI 0.962–0.993) and lower Bland Altman limits of agreement (± 1.9% vs. ± 6.6%) compared to not using the AI tool. The time spent on scans reduced significantly from a median of 19.6 mins (IQR 16.9–21.7) to 9.4 mins (IQR 7.2–11.7) compared to when using the AI tool (p < 0.001). Conclusions AI-assisted muscle ultrasound removes the need for manual tracing, increases reproducibility and saves time. This system may aid monitoring muscle size in ICU patients assisting rehabilitation programmes.