Back to all available

Interpretable machine learning using routine clinical and laboratory data to predict hepatic steatosis in liver transplant donors

gastroenterology-and-hepatology
translational-medicine
metabolic-sciences
data-mining-and-machine-learning
data-science

Abstract

Background: Accurate assessment of hepatic steatosis is crucial for selecting suitable liver donors and predicting post-transplant outcomes. This study aimed to develop interpretable machine learning models for predicting hepatic steatosis using comprehensive clinical and biochemical features.

Methods: We retrospectively analyzed 306 adult donors. Twenty-six prespecified predictors (21 laboratory measures and 5 demographic/physiologic variables) were processed within cross-validated pipelines (median/mode imputation, IQR-based winsorization, collinearity screening). Five algorithms—decision tree, random forest, support vector machine, logistic regression, and gradient boosting—were tuned via five-fold cross-validation in the training set. Discrimination was evaluated on a stratified 70/30 hold-out test set using ROC AUC. Model explanations used Shapley Additive exPlanations (SHAP).

Results: Random forest achieved the highest ROC AUC (0.8148), followed by gradient boosting (0.7620). SVM and logistic regression yielded ROC AUCs of 0.6069 and 0.5136; the decision tree achieved 0.4721. Global SHAP analysis ranked uric acid (UA), high-density lipoprotein cholesterol (HDL-C; lower values), low-density lipoprotein cholesterol (LDL-C), and body mass index (BMI) as the most influential predictors.

Conclusions: Interpretable machine-learning models can effectively predict hepatic steatosis using readily available clinical and biochemical features. The random forest model showed the best discrimination (AUC-ROC=0.8148), and SHAP revealed UA, HDL-C (lower values), LDL-C, and BMI as key predictors.

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].