LIVER CANCER PREDICTION USING MACHINE LEARNING (ML) MODELS

A comparative evaluation of machine learning models for predicting liver cancer risk was performed using an open structured clinical dataset. A Kaggle dataset was used in the study (N=5000): target variable Liver_cancer, 13 features (9 numerical, 4 categorical), with class imbalance (0: 78.22%, 1: 21.78%). Data preprocessing, model training and evaluation were carried out within a unified experimental protocol. Numerical variables were normalized via standardization; categorical variables were encoded in binary format.

The comparative analysis included Logistic Regression, Support Vector Machine with an RBF kernel, k-Nearest Neighbors, Random Forest, and Gradient Boosting. All models were evaluated using accuracy, precision, recall (sensitivity), specificity, F1-score, and the area under the ROC curve (ROC-AUC).

Gradient Boosting achieved the highest overall performance: ROC-AUC=0.999498, Accuracy=0.9754, Precision=0.998967, Sensitivity=0.887971, Specificity=0.999744, F1=0.940204. Although SVM (RBF) and Random Forest demonstrated stable discrimination, they underperformed compared to Gradient Boosting in terms of sensitivity and F1. The results indicate that selecting a model based on structured clinical features requires a comprehensive multi-metric assessment; key limitations include class imbalance and the absence of external validation.

1. Global Cancer Observatory (GCO). Liver and intrahepatic bile ducts: Fact sheet. GLOBOCAN 2022. – Lyon: International Agency for Research on Cancer (IARC), 2024. https://gco.iarc.who.int/media/globocan/factsheets/cancers/11-liver-and-intrahepatic-bile-ductsfact-sheet.pdf (accessed date: 21.02.2026)

2. Hepatocellular Carcinoma: A Comprehensive Review / N. Amin et al // Diseases. – 2025. – Vol. 13, № 7. – Art. 207. https://doi.org/10.3390/diseases13070207.

3. European Association for the Study of the Liver. EASL Clinical Practice Guidelines: Management of hepatocellular carcinoma // Journal of Hepatology. – 2018. – Vol. 69, № 1. – P. 182- 236. https://doi.org/10.1016/j.jhep.2018.03.019.

4. Current Status and Analysis of Machine Learning in Hepatocellular Carcinoma / S. Feng et al // Journal of Clinical and Translational Hepatology. – 2023. – Vol. 11, № 5. – P. 1184-1191. https://doi.org/10.14218/JCTH.2022.00077S.

5. Novel machine learning models outperform risk scores in predicting hepatocellular carcinoma in patients with chronic viral hepatitis / G.L.-H. Wong et al // JHEP Reports. – 2022. – Vol. 4, № 3. – Art. 100441. https://doi.org/10.1016/j.jhepr.2022.100441.

6. An artificial intelligence model to predict hepatocellular carcinoma risk in Korean and Caucasian patients with chronic hepatitis B / H.Y. Kim et al // Journal of Hepatology. – 2022. – Vol. 76, № 2. – P. 311-318. https://doi.org/10.1016/j.jhep.2021.09.025.

7. Machine-learning Approach for the Development of a Novel Predictive Model for the Diagnosis of Hepatocellular Carcinoma / M. Sato et al // Scientific Reports. – 2019. – Vol. 9, № 1. – Art. 7704. https://doi.org/10.1038/s41598-019-44022-8.

8. Machine Learning Prediction Models for Diagnosing Hepatocellular Carcinoma with HCVrelated Chronic Liver Disease / S. Hashem et al // Computer Methods and Programs in Biomedicine. – 2020. – Vol. 196. – Art. 105551. https://doi.org/10.1016/j.cmpb.2020.105551.

9. Feature reduction for hepatocellular carcinoma prediction using machine learning algorithms / G. Mostafa et al // Journal of Big Data. – 2024. – Vol. 11. – Art. 88. https://doi.org/10.1186/s40537-024-00944-3.

10. Machine learning model using immune indicators to predict outcomes in early liver cancer / Y. Zhang et al // World Journal of Gastroenterology. – 2025. – Vol. 31, № 5. – Art. 101722. https://doi.org/10.3748/wjg.v31.i5.101722.

11. Deep learning-based classification and mutation prediction from histopathological images of hepatocellular carcinoma / H. Liao et al // Clinical and Translational Medicine. – 2020. – Vol. 10, № 2. – Art. e102. https://doi.org/10.1002/ctm2.102.

12. A machine-learning model to predict hepatocellular carcinoma response to transcatheter arterial chemoembolization / A. Morshid et al // Radiology: Artificial Intelligence. – 2019. – Vol. 1, № 5. – Art. e180021. https://doi.org/10.1148/ryai.2019180021.

13. Serologic Detection of Hepatocellular Carcinoma: Application of Machine Learning and Implications for Diagnostic Models / P.J. Johnson et al // JCO Clinical Cancer Informatics. – 2024. – Vol. 8. – Art. e2300199. https://doi.org/10.1200/CCI.23.00199.

14. miadul. Predict Liver Cancer from & Clinical Features [Electronic resource] – Kaggle Datasets, 2024. – URL: https://www.kaggle.com/datasets/miadul/predict-liver-cancer-from-and-clinicalfeatures (accessed date: 20.02.2026).

15. Reporting of prognostic clinical prediction models based on machine learning methods in oncology: a systematic review / P. Dhiman et al // Diagnostic and Prognostic Research. – 2022. – Vol. 6, № 1. – Art. 13. https://doi.org/10.1186/s41512-022-00126-w.

16. Development of an Early Lung Cancer Diagnosis Method Based on a Neural Network / I. Karymsakova et al // Computers. – 2025. – Vol. 14. – Art. 397. https://doi.org/10.3390/computers14090397.