{"title":"Diagnostic performance of AI-based models versus physicians among patients with hepatocellular carcinoma: a systematic review and meta-analysis.","authors":"Feras Al-Obeidat, Wael Hafez, Muneir Gador, Nesma Ahmed, Marwa Muhammed Abdeljawad, Antesh Yadav, Asrar Rashed","doi":"10.3389/frai.2024.1398205","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Hepatocellular carcinoma (HCC) is a common primary liver cancer that requires early diagnosis due to its poor prognosis. Recent advances in artificial intelligence (AI) have facilitated hepatocellular carcinoma detection using multiple AI models; however, their performance is still uncertain.</p><p><strong>Aim: </strong>This meta-analysis aimed to compare the diagnostic performance of different AI models with that of clinicians in the detection of hepatocellular carcinoma.</p><p><strong>Methods: </strong>We searched the PubMed, Scopus, Cochrane Library, and Web of Science databases for eligible studies. The R package was used to synthesize the results. The outcomes of various studies were aggregated using fixed-effect and random-effects models. Statistical heterogeneity was evaluated using I-squared (I<sup>2</sup>) and chi-square statistics.</p><p><strong>Results: </strong>We included seven studies in our meta-analysis;. Both physicians and AI-based models scored an average sensitivity of 93%. Great variation in sensitivity, accuracy, and specificity was observed depending on the model and diagnostic technique used. The region-based convolutional neural network (RCNN) model showed high sensitivity (96%). Physicians had the highest specificity in diagnosing hepatocellular carcinoma(100%); furthermore, models-based convolutional neural networks achieved high sensitivity. Models based on AI-assisted Contrast-enhanced ultrasound (CEUS) showed poor accuracy (69.9%) compared to physicians and other models. The leave-one-out sensitivity revealed high heterogeneity among studies, which represented true differences among the studies.</p><p><strong>Conclusion: </strong>Models based on Faster R-CNN excel in image classification and data extraction, while both CNN-based models and models combining contrast-enhanced ultrasound (CEUS) with artificial intelligence (AI) had good sensitivity. Although AI models outperform physicians in diagnosing HCC, they should be utilized as supportive tools to help make more accurate and timely decisions.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11368160/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/frai.2024.1398205","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Hepatocellular carcinoma (HCC) is a common primary liver cancer that requires early diagnosis due to its poor prognosis. Recent advances in artificial intelligence (AI) have facilitated hepatocellular carcinoma detection using multiple AI models; however, their performance is still uncertain.
Aim: This meta-analysis aimed to compare the diagnostic performance of different AI models with that of clinicians in the detection of hepatocellular carcinoma.
Methods: We searched the PubMed, Scopus, Cochrane Library, and Web of Science databases for eligible studies. The R package was used to synthesize the results. The outcomes of various studies were aggregated using fixed-effect and random-effects models. Statistical heterogeneity was evaluated using I-squared (I2) and chi-square statistics.
Results: We included seven studies in our meta-analysis;. Both physicians and AI-based models scored an average sensitivity of 93%. Great variation in sensitivity, accuracy, and specificity was observed depending on the model and diagnostic technique used. The region-based convolutional neural network (RCNN) model showed high sensitivity (96%). Physicians had the highest specificity in diagnosing hepatocellular carcinoma(100%); furthermore, models-based convolutional neural networks achieved high sensitivity. Models based on AI-assisted Contrast-enhanced ultrasound (CEUS) showed poor accuracy (69.9%) compared to physicians and other models. The leave-one-out sensitivity revealed high heterogeneity among studies, which represented true differences among the studies.
Conclusion: Models based on Faster R-CNN excel in image classification and data extraction, while both CNN-based models and models combining contrast-enhanced ultrasound (CEUS) with artificial intelligence (AI) had good sensitivity. Although AI models outperform physicians in diagnosing HCC, they should be utilized as supportive tools to help make more accurate and timely decisions.
背景:肝细胞癌(HCC)是一种常见的原发性肝癌,由于预后不良,需要早期诊断。人工智能(AI)的最新进展促进了多种人工智能模型对肝细胞癌的检测,但其性能仍不确定。目的:本荟萃分析旨在比较不同人工智能模型与临床医生在检测肝细胞癌方面的诊断性能:我们在 PubMed、Scopus、Cochrane Library 和 Web of Science 数据库中搜索了符合条件的研究。使用 R 软件包对结果进行综合。使用固定效应和随机效应模型对不同研究的结果进行汇总。统计异质性采用 I 平方(I2)和卡方统计进行评估:我们在荟萃分析中纳入了七项研究。医生和人工智能模型的平均灵敏度均为 93%。根据所用模型和诊断技术的不同,灵敏度、准确性和特异性也有很大差异。基于区域的卷积神经网络(RCNN)模型显示出较高的灵敏度(96%)。医生诊断肝细胞癌的特异性最高(100%);此外,基于模型的卷积神经网络也实现了高灵敏度。与医生和其他模型相比,基于人工智能辅助对比增强超声波(CEUS)的模型准确率较低(69.9%)。留空灵敏度显示了各研究之间的高度异质性,这代表了各研究之间的真实差异:结论:基于 Faster R-CNN 的模型在图像分类和数据提取方面表现出色,而基于 CNN 的模型以及将对比增强超声(CEUS)与人工智能(AI)相结合的模型都具有良好的灵敏度。虽然人工智能模型在诊断 HCC 方面优于医生,但应将其作为辅助工具来使用,以帮助做出更准确、更及时的决定。