2026 Critical Care Congress Skip to main content
2026 Critical Care Congress Main banner
Final Program


Advance Program
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Session Icons
Thought Leader Session
Thought Leader Session
Guidelines Session
Guidelines Session
Aging Adult Track
Aging Adult Track
Additional Registration Fee
Additional Registration Fee

Research Snapshot Theater: Epidemiology - Outcomes, Adult I

Development of a Machine Learning Model Using Ultrasound and Clinical Metrics to Predict ICUAW

Monday, March 23, 2026
2:30 PM - 3:30 PM Central Time
Location: Connections Central - RST 01

  • tongjuan zou, n/a (she/her/hers)

    West China Hospital Sichuan University, China (People's Republic)

    Disclosure(s): No relevant financial relationship(s) to disclose.

  • XC

    Xuehua Chen, n/a

    Dr.
    Fourth People's Hospital of Zigong City

    Disclosure information not submitted.

  • JL

    Jun Li, n/a

    Dr.
    The First People's Hospital of Longquanyi District, Chengdu, PR China

    Disclosure information not submitted.

  • XL

    Xianying Lei, n/a

    Dr.
    The Affiliated Hospital of Southwest Medical University

    Disclosure information not submitted.

  • HC

    Hengyu Cai, N/A

    Dr.
    West China Hospital, Sichuan University, Sichuan, China (People's Republic)

    Disclosure information not submitted.

  • LZ

    Li Zhang, N/A

    Dr.
    West China School of Public Health and West China Fourth Hospital of Sichuan University, Sichuan, China (People's Republic)

    Disclosure information not submitted.

  • LZ

    Li Zhang, N/A

    Dr.
    Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China (People's Republic)

    Disclosure information not submitted.

  • Xueying Zeng, n/a (she/her/hers)

    Sichuan, China (People's Republic)

    Disclosure(s): No relevant financial relationship(s) to disclose.

  • QD

    Qionglan Dong, n/a

    Dr.
    The Third Hospital of Mianyang

    Disclosure information not submitted.

  • SZ

    Shurong Zhang, n/a

    Dr.
    West China Hospital, Sichuan University

    Disclosure information not submitted.

  • YL

    Yi Li, N/A

    Associate chief physician
    West China Hospital Sichuan University

    Disclosure information not submitted.

  • Yao Qin, n/a (she/her/hers)

    Sichuan, China (People's Republic)

    Disclosure(s): No relevant financial relationship(s) to disclose.

  • ZHOU RAN, n/a (she/her/hers)

    West China Hospital, Sichuan, China (People's Republic)

    Disclosure(s): No relevant financial relationship(s) to disclose.

  • YK

    Yan Kang, N/A

    Prof.
    Department of Critical Care Medicine, West China School of Medicine, West China Hospital, Sichuan University

    Disclosure information not submitted.

  • BW

    Bo Wang, N/A

    Dr.
    West China Hospital, Sichuan University, Sichuan, China (People's Republic)

    Disclosure information not submitted.

  • ZZ

    Zhongwei Zhang, N/A

    Dr.
    West China Hospital, Sichuan University, Sichuan, China (People's Republic)

    Disclosure information not submitted.

  • XJ

    Xiaodong Jin, N/A

    Dr.
    West China Hospital, Sichuan University, Sichuan, China (People's Republic)

    Disclosure information not submitted.

  • XX

    Xiaoqi Xie, N/A

    Dr.
    West China Hospital, Sichuan University, Sichuan, China (People's Republic)

    Disclosure information not submitted.

  • WY

    Wanhong Yin, n/a

    Dr.
    West China Hospital

    Disclosure information not submitted.

Introduction: Intensive care unit-acquired Weakness (ICUAW) significantly affects patient prognosis and quality of life. This study aimed to develop a machine learning (ML) model that integrates bedside muscle ultrasound measurements and clinical features for early ICUAW prediction and to identify key predictors that could guide targeted interventions.


Methods: This prospective multicenter cohort study enrolled 1203 adult ICU patients. Within 24 hours of ICU admission, we measured the thickness of the rectus femoris (RF) and vastus intermedius (VI) muscles, as well as the RF cross-sectional area (CSA), using bedside ultrasound under both pressurized and unpressurized conditions. Relevant clinical features were recorded concurrently. Nine ML algorithms were trained to develop predictive models incorporating both muscle ultrasound and clinical data. We selected the best-performing model and evaluated its performance on an independent external validation set.


Results: Between September 2023 and May 2024, 858 patients from 16 tertiary hospitals comprised the training cohort, and an additional 345 patients (June 2024- April 2025) comprised the external validation cohort. The random forest model demonstrated superior performance, achieving an area under the curve (AUC) of 0.914 (95% CI: 0.891-0.936) and 0.907 (95% CI: 0.882-0.931) for the unpressurized and pressurized models, respectively. In the external validation, the unpressurized model achieved a sensitivity of 0.983 (95% CI: 0.952-0.997) and specificity of 0.726 (95% CI: 0.651-0.792). The pressurized model achieved a sensitivity of 0.978 (95% CI: 0.944-0.994) and a specificity of 0.506 (95% CI: 0.427-0.585). Key predictors identified in the unpressurized model included the Sequential Organ Failure Assessment (SOFA) score, VI or RF muscle thickness, albumin, and fraction of inspired oxygen (FiO2). In the pressurized model, the prominent predictors were SOFA score, VI thickness, Interleukin-6 (IL-6), and creatinine.


Conclusions: The random forest-based machine learning model effectively predicted ICUAW using bedside ultrasound and clinical features, demonstrating high accuracy and suggesting potential clinical utility for early risk stratification and intervention.