Dual elastography ultrasound for classifying metabolic dysfunction-associated steatotic liver disease: a cross-sectional study within a prospective cohort.
Authors
Affiliations (13)
Affiliations (13)
- Department of Interventional Ultrasound, Fifth Medical Center of Chinese PLA General Hospital, Beijing, China.
- Departments of Ultrasound, Huashan Hospital, Fudan University, Shanghai, China.
- Departments of Ultrasound, Beijing Institute of Hepatoligy, Beijing Youan Hospital Capitial Medical University, Beijing, China.
- Departments of Ultrasound, China-Japan Friendship Hospital, Beijing, China.
- Departments of Ultrasound, Beijing Ditan Hospital Capital Medical University, Beijing, China.
- Departments of Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Guangxi, China.
- Departments of Ultrasound, The Fifth Affiliated Hospital of Guangxi Medical University, Guangxi, China.
- Departments of Ultrasound, Liuzhou People's Hospital, Guangxi, China.
- Departments of Ultrasound, The Second Hospital of Nanjing, Nanjing University of Chinese Medicine, Jiangsu, China.
- Departments of Ultrasound, The First Affiliated Hospital of Guangxi University of Chinses Medicine, Guangxi, China.
- Departments of Ultrasound, Huashan Hospital, Fudan University, Shanghai, China. [email protected].
- Department of Interventional Ultrasound, Fifth Medical Center of Chinese PLA General Hospital, Beijing, China. [email protected].
- Department of Interventional Ultrasound, Fifth Medical Center of Chinese PLA General Hospital, Beijing, China. [email protected].
Abstract
The binary diagnostic approach does not reflect the entire spectrum of metabolic dysfunction associated steatotic liver disease (MASLD. We used an elastography technology, dual elastography ultrasound (DEUS), to discriminate the different stages of MASLD. This prospective multicenter study was conducted from December 2020 to March 2022. All patients underwent DEUS scan, a liver biopsy, and a liver function laboratory test. The optimal model was developed (Model<sup>DEUSC</sup>) with 10 machine learning algorithms by combining DEUS and selected clinical parameters and tested the diagnostic accuracy for distinguishing the three progression stages of MASLD: low-, intermediate-, and high-risk. The diagnostic ability of Model<sup>DEUSC</sup> for MASH with advanced fibrosis (≥ F3) was compared with other four non-invasive tests. The study included 312 patients in the derivation cohort and 135 in the validation cohort (7:3). Combining DEUS and clinical parameters, a ternary classification of MASLD in the validation cohort achieved a macro-average AUC of 0.858 (95% CI: 0.793, 0.925). The AUC for the diagnosis of MASH with ≥ F3 fibrosis of Model<sup>DEUSC</sup> was 0.886 (95% CI: 0.813, 0.824), which was superior to FAST, FIB-4, NFS, and APRI (0.822, 0.657, 0.688, and 0.659). Moreover, Model<sup>DEUSC</sup> demonstrated favorable performance for distinguishing stages of liver fibrosis (F1 to F4), inflammation (G1 to G4), and steatosis (S1 to S4). Stratification analysis showed that the ability of Model<sup>DEUSC</sup> was not influenced by diabetes and obesity. Multicenter data analysis demonstrated DEUS' advanced ability in continuous stratification of MASLD, which will provide a low-cost, easily accessible, and accurate noninvasive tools (NIT) for MASLD.