Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Feb 9, 2025
Date Accepted: Jun 5, 2025
Effectiveness of Radiomics-based Machine Learning Models in Differentiating Pancreatitis and Pancreatic Ductal Adenocarcinoma: A Systematic Review and Meta-Analysis
ABSTRACT
Background:
Some investigators have explored radiomics-based machine learning (ML) models for distinguishing pancreatic ductal adenocarcinoma (PDAC) from mass-forming pancreatitis (MFP). However, systematic evidence supporting the feasibility of these models is insufficient, presenting a notable challenge for clinical application.
Objective:
This study intends to review the diagnostic performance of radiomics-based ML models in differentiating PDAC from MFP, summarize the methodological quality of the included studies, and provide evidence-based guidance for optimizing radiomics-based ML models and advancing their clinical use.
Methods:
PubMed, Embase, Cochrane, and Web of Science databases were retrieved for studies utilizing radiomics-based ML models to differentiate PDAC from MFP up to June 29, 2024. Methodological quality was appraised by means of the Radiomics Quality Score (RQS). Pooled sensitivity (SEN), specificity (SPE), area under the curve of summary receiver operating characteristics (AUC), likelihood ratios, and diagnostic odds ratio (DOR) were estimated through a bivariate mixed-effects model. Subgroup analysis was performed to appraise the diagnostic performance of radiomics-based ML models across various imaging modalities.
Results:
This meta-analysis included 24 studies with 14,406 cases, of which 7,635 were PDAC. The RQS scores of these studies ranged from 5 points (14%) to 17 points (47%), with an average score of 9 (25%). The radiomics-based ML models demonstrated high diagnostic performance. The pooled SEN, SPE, AUC, positive likelihood ratio, negative likelihood ratio, and DOR were 0.92 (95% CI: 0.91-0.94), 0.90 (95% CI: 0.85-0.94), 0.94 (95% CI: 0.74-0.99), 9.3 (95% CI: 6.0-14.2), 0.08 (95% CI: 0.07-0.11), and 110 (95% CI: 62-194), respectively.
Conclusions:
Radiomics-based ML models appear promising in differentiating PDAC from MFP, with notable diagnostic performance. These findings emphasize the potential of radiomics-based ML models in facilitating the screening and diagnosis of PDAC in clinical practice.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.