Clinical 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, 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 min (IQR 16.9-21.7) to 9.4 min (IQR 7.2-11.7) compared to when using the AI tool (p < 0.001). 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.

Ventilator-associated respiratory infection in a resource-restricted setting: impact and etiology.

BACKGROUND: Ventilator-associated respiratory infection (VARI) is a significant problem in resource-restricted intensive care units (ICUs), but differences in casemix and etiology means VARI in resource-restricted ICUs may be different from that found in resource-rich units. Data from these settings are vital to plan preventative interventions and assess their cost-effectiveness, but few are available. METHODS: We conducted a prospective observational study in four Vietnamese ICUs to assess the incidence and impact of VARI. Patients ≥ 16 years old and expected to be mechanically ventilated > 48 h were enrolled in the study and followed daily for 28 days following ICU admission. RESULTS: Four hundred fifty eligible patients were enrolled over 24 months, and after exclusions, 374 patients' data were analyzed. A total of 92/374 cases of VARI (21.7/1000 ventilator days) were diagnosed; 37 (9.9%) of these met ventilator-associated pneumonia (VAP) criteria (8.7/1000 ventilator days). Patients with any VARI, VAP, or VARI without VAP experienced increased hospital and ICU stay, ICU cost, and antibiotic use (p < 0.01 for all). This was also true for all VARI (p < 0.01 for all) with/without tetanus. There was no increased risk of in-hospital death in patients with VARI compared to those without (VAP HR 1.58, 95% CI 0.75-3.33, p = 0.23; VARI without VAP HR 0.40, 95% CI 0.14-1.17, p = 0.09). In patients with positive endotracheal aspirate cultures, most VARI was caused by Gram-negative organisms; the most frequent were Acinetobacter baumannii (32/73, 43.8%) Klebsiella pneumoniae (26/73, 35.6%), and Pseudomonas aeruginosa (24/73, 32.9%). 40/68 (58.8%) patients with positive cultures for these had carbapenem-resistant isolates. Patients with carbapenem-resistant VARI had significantly greater ICU costs than patients with carbapenem-susceptible isolates (6053 USD (IQR 3806-7824) vs 3131 USD (IQR 2108-7551), p = 0.04) and after correction for adequacy of initial antibiotics and APACHE II score, showed a trend towards increased risk of in-hospital death (HR 2.82, 95% CI 0.75-6.75, p = 0.15). CONCLUSIONS: VARI in a resource-restricted setting has limited impact on mortality, but shows significant association with increased patient costs, length of stay, and antibiotic use, particularly when caused by carbapenem-resistant bacteria. Evidence-based interventions to reduce VARI in these settings are urgently needed.