Prognostic Modeling of 1-Year Survival in Hepatocellular Carcinoma: A Comparative Evaluation of Machine Learning Methods with Class Balancing.
- 1Department of Quantitative and Systems Health Sciences, University of Texas at Austin Dell Medical School, Austin, TX 78712, USA.
- 2Department of Anesthesiology, McGovern Medical School UTHealth, Houston, TX 77030, USA.
Abstract
Objective
To develop and comparatively evaluate machine learning models for predicting 1-year survival in hepatocellular carcinoma (HCC) patients, focusing on the prognostic interplay between chronic liver diseases and diabetes aligned with the EASL Clinical Practice Guidelines (2018), and to assess the impact of class balancing via Synthetic Minority Oversampling Technique (SMOTE) on model performance.Methods
Retrospective analysis was performed on the UCI HCC Survival Dataset (N = 165). Following median/mode imputation of ~10% missing values, four classifiers were evaluated: Logistic Regression (LR), Multilayer Perceptron (MLP), Gradient Boosting (GB), and Random Forest (RF), each trained with and without SMOTE oversampling (eight variants total). Models were trained on 16 EASL-aligned clinical and biochemical features using a stratified 80/20 train/test split (training N = 132, held-out test N = 33). Performance was evaluated via accuracy, AUC-ROC (with 95% bootstrap confidence intervals across 1000 iterations), precision, recall, and macro F1-score. Stratified 5-fold cross-validation and multiple imputation sensitivity analyses (MissForest, KNN, MICE, complete-case) were conducted. SHAP (SHapley Additive exPlanations) was applied to the top-performing model to provide patient-level interpretability.Results
Diabetes was present in 33.9% of patients (56/165; 28/102 survivors [27.5%] vs. 28/63 non-survivors [44.4%]). Diabetes was significantly associated with 1-year mortality in univariate analysis (χ² = 5.02, p = 0.025) but not after multivariable adjustment (aOR = 0.50, 95% CI: 0.21-1.22, p = 0.129). GB + SMOTE achieved the highest discriminative ability (AUC-ROC: 0.727, 95% CI: 0.552-0.886), while LR + SMOTE yielded the highest overall accuracy (72.7%) and macro F1-score (0.723). Without SMOTE, all models exhibited poor minority-class detection (non-survival F1 range: 0.300-0.615). SMOTE markedly improved non-survival recall across LR (0.231 to 0.769) and GB (61.5% to 69.2%). Stratified 5-fold CV AUC on the training set was highest for RF (0.779 ± 0.100), followed by GB (0.744 ± 0.065). TreeSHAP analysis identified ECOG performance status (mean |SHAP| = 1.284) and ALT (1.060) as the most influential predictors; diabetes ranked 15th (mean |SHAP| = 0.014), consistent with minimal independent predictive contribution.Conclusions
Gradient boosting and regularized linear regression combined with SMOTE class balancing provide competitive, well-calibrated, and transparent risk stratification on small, imbalanced tabular HCC datasets, offering an exploratory proof-of-concept for personalized prognostic modeling that requires external validation.
Related
- Comparative Prognostic Value of AFP, PIVKA-II, and GPC-3 in Hepatocellular Carcinoma: A Real-World Multicenter Cohort Study
- Preoperative Zinc Deficiency as a Novel Prognostic Predictor for Postoperative Recurrence in Hepatocellular Carcinoma
- Leveraging deep learning for prognostic stratification of hepatocellular carcinoma using histopathological images
- Integrative Multi-Database Bioinformatics Characterization of FANCE in Hepatocellular Carcinoma: Prognostic, Epigenetic, Immune, and ncRNA Associations
- Early Prognostic Value of the Freiburg Index of Post-Transjugular Intrahepatic Portosystemic Shunt Survival in Patients With Hepatocellular Carcinoma Undergoing Liver Transplantation
BibTeX
@article{wang2026prognostic,
title = {{Prognostic Modeling of 1-Year Survival in Hepatocellular Carcinoma: A Comparative Evaluation of Machine Learning Methods with Class Balancing.}},
author = {Jinlian Wang and Hui Li and Changqing Ju and Hongfang Liu},
journal = {Diseases (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/diseases14100377},
url = {https://europepmc.org/article/MED/42930004},
note = {CC BY},
}
RIS
TY - JOUR
TI - Prognostic Modeling of 1-Year Survival in Hepatocellular Carcinoma: A Comparative Evaluation of Machine Learning Methods with Class Balancing.
AU - Jinlian Wang
AU - Hui Li
AU - Changqing Ju
AU - Hongfang Liu
PY - 2026
DA - 2026/10/13
JO - Diseases (Basel, Switzerland)
DO - 10.3390/diseases14100377
UR - https://europepmc.org/article/MED/42930004
AB - Objective To develop and comparatively evaluate machine learning models for predicting 1-year survival in hepatocellular carcinoma (HCC) patients, focusing on the prognostic interplay between chronic liver diseases and diabetes aligned with the EASL Clinical Practice Guidelines (2018), and to assess the impact of class balancing via Synthetic Minority Oversampling Technique (SMOTE) on model performance.Methods Retrospective analysis was performed on the UCI HCC Survival Dataset (N = 165). Following median/mode imputation of ~10% missing values, four classifiers were evaluated: Logistic Regression (LR), Multilayer Perceptron (MLP), Gradient Boosting (GB), and Random Forest (RF), each trained with and without SMOTE oversampling (eight variants total). Models were trained on 16 EASL-aligned clinical and biochemical features using a stratified 80/20 train/test split (training N = 132, held-out test N = 33). Performance was evaluated via accuracy, AUC-ROC (with 95% bootstrap confidence intervals across 1000 iterations), precision, recall, and macro F1-score. Stratified 5-fold cross-validation and multiple imputation sensitivity analyses (MissForest, KNN, MICE, complete-case) were conducted. SHAP (SHapley Additive exPlanations) was applied to the top-performing model to provide patient-level interpretability.Results Diabetes was present in 33.9% of patients (56/165; 28/102 survivors [27.5%] vs. 28/63 non-survivors [44.4%]). Diabetes was significantly associated with 1-year mortality in univariate analysis (χ² = 5.02, p = 0.025) but not after multivariable adjustment (aOR = 0.50, 95% CI: 0.21-1.22, p = 0.129). GB + SMOTE achieved the highest discriminative ability (AUC-ROC: 0.727, 95% CI: 0.552-0.886), while LR + SMOTE yielded the highest overall accuracy (72.7%) and macro F1-score (0.723). Without SMOTE, all models exhibited poor minority-class detection (non-survival F1 range: 0.300-0.615). SMOTE markedly improved non-survival recall across LR (0.231 to 0.769) and GB (61.5% to 69.2%). Stratified 5-fold CV AUC on the training set was highest for RF (0.779 ± 0.100), followed by GB (0.744 ± 0.065). TreeSHAP analysis identified ECOG performance status (mean |SHAP| = 1.284) and ALT (1.060) as the most influential predictors; diabetes ranked 15th (mean |SHAP| = 0.014), consistent with minimal independent predictive contribution.Conclusions Gradient boosting and regularized linear regression combined with SMOTE class balancing provide competitive, well-calibrated, and transparent risk stratification on small, imbalanced tabular HCC datasets, offering an exploratory proof-of-concept for personalized prognostic modeling that requires external validation.
SN - 2079-9721
ER -