Systematic review and meta-analysis on the classification metrics of machine learning algorithm based radiomics in hepatocellular carcinoma diagnosis

Aug 5, 2026

Upload by Aria

The aim of this systematic review and meta-analysis is to evaluate classification metrics of machine learning-driven radiomics for diagnosing hepatocellular carcinoma (HCC). Following PRISMA, searches across PubMed, ScienceDirect, and Scopus (2018–2022) identified 436 relevant articles, with 34 selected after screening. Study-level AUC, accuracy, specificity, and sensitivity were assessed, and Jamovi was used to meta-analyze 12 cohort studies. Pooled results showed AUC 0.86, accuracy 0.83, sensitivity 0.80, and specificity 0.84. Logistic Regression with LASSO feature selection was most suitable for binary tasks, and radiomics features supported accurate discrimination, with clinical features further improving decision support.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

Introduction

Background and clinical need for early HCC detection

Role of precision medicine and medical imaging

Radiomics and machine learning overview

Heliyon 10 (2024) e36313 Contents lists available at ScienceDirect Heliyon journal [homepage:](homepage: www.cell.com/heliyon)[ www.cell.com/heliyon](homepage: www.cell.com/heliyon) | Research article
Systematic review and meta-analysis on the classification metrics of machine learning algorithm based radiomics in hepatocellular carcinoma diagnosis | | | | | --- | --- | --- | --- | | Nurin Syazwina Mohd Haniffa , Kwan Hoong Ngb , Izdihar Kamala, c, * , Norhayati Mohd Zainc , Muhammad Khalis Abdul Karim a
a Department of Physics, Faculty of Science, Universiti Putra Malaysia, UPM, 43400 Serdang, Selangor, Malaysia b Department of Biomedical Imaging, Universiti Malaya, 50603 Kuala Lumpur, Malaysia
c Research Management Centre, KPJ Healthcare University, 71800, Nilai, Negeri Sembilan, Malaysia | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords: ystematic review PRISMARadiomics Machine learning
Hepatocellular carcinoma Meta-analysis | | The aim of this systematic review and meta-analysis is to evaluate the performance of classification metrics of machine learning-driven radiomics in diagnosing hepatocellular carcinoma (HCC). Following the PRISMA guidelines, a comprehensive search was conducted across three major scientific databases—PubMed, ScienceDirect, and Scopus—from 2018 to 2022. The search yielded a total of 436 articles pertinent to the application of machine learning and deep learning for HCC prediction. These studies collectively reflect the burgeoning interest and rapid advancements in employing artificial intelligence (AI)-driven radiomics for enhanced HCC diagnostic capabilities. After the screening process, 34 of these articles were chosen for the study. The area under curve (AUC), accuracy, specificity, and sensitivity of the proposed and basic models were assessed in each of the studies. Jamovi (version [1.1.9.0](1.1.9.0)) was utilised to carry out a metaanalysis of 12 cohort studies to evaluate the classification accuracy rate. The risk of bias was estimated, and Logistic Regression was found to be the most suitable classifier for binary problems, with least absolute shrinkage and selection operator (LASSO) as the feature selector. The pooled proportion for HCC prediction classification was high for all performance metrics, with an AUC value of 0.86 (95 % CI: 0.83–0.88), accuracy of 0.83 (95 % CI: 0.78–0.88), sensitivity of 0.80 (95 % CI: 0.75–0.84) and specificity of 0.84 (95 % CI: 0.80–0.88). The performance of featureselectors, classifiers, and input features in detecting HCC and related factors was evaluated and it was observed that radiomics features extracted from medical images were adequate for AI to accurately distinguish the condition. HCC based radiomics has favourable predictive performance especially with addition of clinical features that may serve as tool that support clinical decisionmaking. | | 1. Introduction Hepatocellular carcinoma (HCC) is a form of liver cancer that is among the main causes of cancer-related fatalities globally [1]. Despite the availability of hepatectomy surgery, liver transplantation, radiofrequency ablation, and chemotherapy, the survival rate of * Corresponding author. Department of Physics, Faculty of Science, Universiti Putra Malaysia, UPM, 43400 Serdang, Selangor, Malaysia. E-mail address: [izdiharkamal@upm.edu.my](izdiharkamal@upm.edu.my) (I. Kamal). [https://doi.org/10.1016/j.heliyon.2024.e36313](https://doi.org/10.1016/j.heliyon.2024.e36313) Received 21 September 2023; Received in revised form 13 August 2024; Accepted 13 August 2024 Available online 14 August 2024 2405-8440/© 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC license ([http://creativecommons.org/licenses/by-nc/4.0/](http://creativecommons.org/licenses/by-nc/4.0/)). HCC patients can be improved significantly through early detection and treatment [2,3]. With the emergence of precision medicine, the di

FAQs

What is the purpose of this systematic review and meta-analysis?

To evaluate how well classification metrics perform when using machine learning-driven radiomics to diagnose hepatocellular carcinoma (HCC).

Which data sources and time range were used for the literature search?

PubMed, ScienceDirect, and Scopus were searched from 2018 to 2022 following PRISMA guidelines.

What pooled diagnostic performance metrics were reported?

The pooled estimates reported AUC 0.86, accuracy 0.83, sensitivity 0.80, and specificity 0.84 across the included cohort studies.

Aug 5, 2026

Upload by Aria