A nomogram model integrating ultrasound-based multimodal radiomics features and clinical indexes for diagnosing significant hepatic fibrosis in AILD patients.

OBJECTIVE

To develop a prediction model combining radiomics features from 2D ultrasound (2D-US) and shear wave elastography (SWE) with clinical indicators for assessing significant hepatic fibrosis (S2-4) in autoimmune liver diseases (AILDs).

METHODS

A total of 147 biopsy-confirmed AILD patients were classified into non-significant (S0-1, n = 44) and significant fibrosis (S2-4, n = 103) groups based on Scheuer's classification, and randomly divided into training (n = 102) and validation (n = 45) cohorts. Radiomics features with interclass correlation coefficient > 0.75 were selected. Ten non-zero coefficient features were identified using least absolute shrinkage and selection operator (LASSO) regression. Six machine learning algorithms were evaluated. A nomogram integrating optimal radiomics features and clinical indexes was developed and assessed via ROC, calibration curve, and decision curve analysis.

RESULTS

Logistic regression demonstrated the best performance among all algorithms. Platelet count (PLT, OR = 0.992) and shear wave velocity (Vs, OR = 3.855) were identified as independent predictors for diagnosing S2-4 stage fibrosis (P < 0.05). The combined nomogram achieved AUCs of 0.860 in the training set and 0.912 in the validation set, demonstrating significantly superior diagnostic performance compared to the single radiomics model, FIB-4 index, and APRI index (P < 0.05). In subgroup analyses across various AILD subtypes and different ALT levels, the nomogram model consistently showed the best diagnostic performance.

CONCLUSION

This study combined the radiomics of two-dimensional ultrasound and shear wave elastography and clinical indicators to construct a nomogram model, which can effectively achieve non-invasive diagnosis of AILDs fibrosis and accurately identify significant fibrosis, providing a more reliable quantitative tool for individualized assessment and clinical decision-making.