Browsing by Author "Horikawa, Arimitsu"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Publication Acute skeletal muscle wasting in patients with acute kidney injury requiring continuous kidney replacement therapy: A prospective multicenter study(2026) Mayer, Kirby; Teixeira, Pedro; González Seguel, Felipe; Tran, Vinh; Gross, Jessica; Horikawa, Arimitsu; Anil, Chaitanya; Shareef, Zan; Puffer, Hayley; Wen, Yuan; Griffin, Benjamin; Neyra, JavierPurpose: Acute kidney injury (AKI) requiring continuous kidney replacement therapy (CKRT) has been hypothesized to increase the risk of developing intensive care unit-associated weakness (ICU-AW), but prospective data are lacking. Materials and methods: This prospective observational study evaluated critically ill adults with AKI requiring CKRT at two U.S. academic hospitals. Using ultrasonography (US), we quantified changes in rectus femoris (RF) muscle mass and quality in the first week after CKRT initiation. At hospital discharge, we assessed for ICU-AW, physical function, and frailty. Results: Twenty-three patients with median age 56 [IQR 47-60] years, BMI 29 [26-36] kg/m2, and Charlson Comorbidity Index 3 [1.5-5] were enrolled. The baseline Sequential Organ Failure Assessment (SOFA) score was 9 [7.5-11.5] and CKRT duration was 4 [1-7] days. Six (26 %) patients died in the ICU and one (4 %) transitioned to comfort measures before study completion. Substantial muscle wasting occurred between Day 1 and Day 7: RF muscle thickness (mT) decreased by 10 % [3 %-20 %]; RF cross-sectional area (CSA) decreased by 19 % [12 %-22 %]; and echo intensity (EI) increased (implying worse muscle quality) by 14 % [5 %-25 %]. A significant effect of time within subjects was observed for all three ultrasound measures (CSA: F = 66.2, p < 0.001; mT: F = 27.1, p < 0.001; EI: F = 22.5, p < 0.001). At hospital discharge, 67 % of survivors (n = 10/15) met criteria for ICU-AW. Conclusions: Patients with AKI requiring CKRT experienced significant muscle wasting in the first week following CKRT initiation and had high rate of ICU-AW at hospital discharge. Trial registration: NCT05287204, Registered 20 October 2021.Publication Development of an artificial intelligence powered software for automated analysis of skeletal muscle ultrasonography(2025) Calulo, Zoe; González Seguel, Felipe; Horikawa, Arimitsu; Granger, Catherine; Sarwal, Aarti; Dha, Sanjay; Ntoumenopoulos, George; Chen, Jin; Bumgardner, V K; Parry, Selina; Mayer, Kirby; Wen, YuanMuscle ultrasound has high utility in clinical practice and research; however, the main challenges are the training and time required for manual analysis to achieve objective quantification of muscle size and quality. We aimed to develop and validate a software tool powered by artificial intelligence (AI) by measuring its consistency and comparability of expert manual analysis quantifying lower limb muscle ultrasound images. Quadriceps complex (QC) and tibialis anterior (TA) muscle images of healthy, intensive care unit, and/or lung cancer participants were captured with portable devices. Manual analyses of muscle size and quality were performed by experienced physiotherapists taking approximately 24 h to analyze all 180 images, while automated analyses were performed using a custom-built deep-learning model (MyoVision-US), taking 247 s (saving time = 99.8%). Consistency between the manual and automated analyses was good to excellent for all QC (ICC = 0.85-0.99) and TA (ICC = 0.93-0.99) measurements, even for critically ill (ICC = 0.91-0.98) and lung cancer (ICC = 0.85-0.99) images. The comparability of MyoVision-US was moderate to strong for QC (adj. R2 = 0.56-0.94) and TA parameters (adj. R2 = 0.81-0.97). The application of AI automating lower limb muscle ultrasound analyses showed excellent consistency and strong comparability compared with human analysis across healthy, acute, and chronic population.