Related Experiment Video
Updated: May 17, 2026
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
Development and validation of an explainable machine learning model using routine laboratory biomarkers for
Jialin Wu1,2,3, Wenting Wei4, Terry Cheuk-Fung Yip5
1Department of Anatomical and Cellular Pathology, State Key Laboratory of Translational Oncology, Prince of Wales Hospital, The Chinese University of Hong Kong, Sir Y.K. Pao Cancer Center, Hong Kong, China.
Abstract:
Although many predictive models for metabolic dysfunction-associated steatotic liver disease (MASLD) have been developed, their performance remains suboptimal. We aimed to develop an interpretable machine learning (ML)-based plasma biomarker model for identifying prevalent MASLD. Data from the National Health and Nutrition Examination Survey (NHANES 2017-2020) were randomly divided into a training cohort (N = 2760) and an internal cohort (N = 1184). Eleven ML algorithms were employed to construct classification models. Model interpretability was visualized via the SHapley Additive exPlanations (SHAP) method. External validation of these models was further conducted using data from the Korea NHANES (KNHANES) 2019-2021. The association between the selected features and prevalent MASLD was evaluated using restricted cubic spline regression analysis. Feature selection was performed using LASSO regression and the Boruta algorithm. Key predictors included diabetes mellitus (DM), waist circumference (WC), age, hypertension, and atherogenic index of plasma (AIP). All evaluated ML algorithms demonstrated robust predictive capabilities, with areas under the curve (AUC) exceeding 0.70. Among these, the Extra Trees (ET) performed the best, achieving an AUC of 0.879 (95% CI 0.856-0.897) in the internal testing group and maintaining good performance in the external KNHANES cohort with an AUC of 0.822 (95% CI 0.815-0.829). The DeLong test revealed significant differences in AUC between ET and other algorithms. These findings suggest that age, WC, DM, hypertension, and AIP are informative features associated with prevalent MASLD. The ET model showed strong discriminative performance and may serve as a practical tool for MASLD screening.
Insights
A new machine learning model using plasma biomarkers effectively identifies metabolic dysfunction-associated steatotic liver disease (MASLD). Key predictors include diabetes, waist circumference, and hypertension, offering a practical screening tool.
Area of Science:
- Hepatology
- Machine Learning
- Biomarker Discovery
Background:
- Metabolic dysfunction-associated steatotic liver disease (MASLD) poses a significant health challenge.
- Existing predictive models for MASLD often exhibit suboptimal performance.
- Development of accurate and interpretable models for MASLD identification is crucial.
Purpose of the Study:
- To develop an interpretable machine learning (ML)-based plasma biomarker model for identifying prevalent MASLD.
- To evaluate the predictive performance of various ML algorithms for MASLD.
- To identify key clinical and biochemical predictors associated with prevalent MASLD.
Main Methods:
- Utilized data from the National Health and Nutrition Examination Survey (NHANES) 2017-2020 for training and internal validation.
- Employed eleven ML algorithms, including Extra Trees (ET), for classification model construction.
- Performed external validation using the Korea NHANES (KNHANES) 2019-2021 dataset and interpreted models using SHAP values.
Main Results:
- The Extra Trees (ET) model demonstrated superior performance with an AUC of 0.879 in the internal testing group and 0.822 in the external KNHANES cohort.
- Key predictors identified for prevalent MASLD included diabetes mellitus (DM), waist circumference (WC), age, hypertension, and atherogenic index of plasma (AIP).
- All evaluated ML algorithms achieved robust predictive capabilities, with AUCs exceeding 0.70.
Conclusions:
- The developed ET model, incorporating age, WC, DM, hypertension, and AIP, shows strong discriminative performance for prevalent MASLD.
- This interpretable ML-based biomarker model can serve as a practical tool for MASLD screening.
- The study highlights the utility of ML in identifying key factors associated with MASLD.