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

• Main Authors: Mohd Haniff, Nurin Syazwina, Ng, Kwan Hoong, Kamal, Izdihar, Mohd Zain, Norhayati, Abdul Karim, Muhammad Khalis
• Format: Article
• Language: English
• Published: Elsevier 2024
• Online Access: http://psasir.upm.edu.my/id/eprint/113777/1/113777.pdf; http://psasir.upm.edu.my/id/eprint/113777/; https://linkinghub.elsevier.com/retrieve/pii/S2405844024123444

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) was utilised to carry out a meta-analysis 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 feature selectors, 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 decision-making.