Kufel Jakub, Czogalik Łukasz, Bielówka Michał, Magiera Mikołaj, Mitręga Adam, Dudek Piotr, Bargieł-Łączek Katarzyna, Stencel Magdalena, Bartnikowska Wiktoria, Mielcarska Sylwia, Modlińska Sandra, Nawrat Zbigniew, Cebula Maciej, Gruszczyńska Katarzyna
Department of Radiology and Nuclear Medicine, Faculty of Medical Sciences in Katowice, Medical University of Silesia, Medyków 14, 40-752 Katowice, Poland.
Students' Scientific Association of Computer Analysis and Artificial Intelligence, Department of Radiology and Nuclear Medicine, Medical University of Silesia in Katowice, 40-752 Katowice, Poland.
J Clin Med. 2024 Aug 8;13(16):4659. doi: 10.3390/jcm13164659.
Chest X-rays (CXRs) are pivotal in clinical diagnostics, particularly in assessing cardiomegaly through the cardiothoracic ratio (CTR). This systematic review and meta-analysis evaluate the efficacy of artificial intelligence (AI) in automating CTR determination to enhance patient care and streamline diagnostic processes. They are concentrated on comparing the performance of AI models in determining the CTR against human assessments, identifying the most effective models for potential clinical implementation. This study was registered with PROSPERO (no. CRD42023437459). No funding was received. A comprehensive search of medical databases was conducted in June 2023. The search strategy adhered to the PICO framework. Inclusion criteria encompassed original articles from the last decade focusing on AI-assisted CTR assessment from standing-position CXRs. Exclusion criteria included systematic reviews, meta-analyses, conference abstracts, paediatric studies, non-original articles, and studies using imaging techniques other than X-rays. After initial screening, 117 articles were reviewed, with 14 studies meeting the final inclusion criteria. Data extraction was performed by three independent investigators, and quality assessment followed PRISMA 2020 guidelines, using tools such as the JBI Checklist, AMSTAR 2, and CASP Diagnostic Study Checklist. Risk of bias was assessed according to the Cochrane Handbook guidelines. Fourteen studies, comprising a total of 70,472 CXR images, met the inclusion criteria. Various AI models were evaluated, with differences in dataset characteristics and AI technology used. Common preprocessing techniques included resizing and normalization. The pooled AUC for cardiomegaly detection was 0.959 (95% CI 0.944-0.975). The pooled standardized mean difference for CTR measurement was 0.0353 (95% CI 0.147-0.0760). Significant heterogeneity was found between studies (I 89.97%, < 0.0001), with no publication bias detected. Standardizing methodologies is crucial to avoid interpretational errors and advance AI in medical imaging diagnostics. Uniform reporting standards are essential for the further development of AI in CTR measurement and broader medical imaging applications.
胸部X光片（CXR）在临床诊断中至关重要，尤其是通过心胸比率（CTR）评估心脏肥大。本系统评价和荟萃分析评估了人工智能（AI）在自动测定CTR以改善患者护理和简化诊断流程方面的有效性。研究集中于比较AI模型在测定CTR方面与人工评估的性能，确定最有效的模型以供潜在的临床应用。本研究已在国际前瞻性系统评价注册库（PROSPERO）注册（编号CRD42023437459）。未获得资金资助。2023年6月对医学数据库进行了全面检索。检索策略遵循PICO框架。纳入标准包括过去十年中关注站立位胸部X光片AI辅助CTR评估的原创文章。排除标准包括系统评价、荟萃分析、会议摘要、儿科研究、非原创文章以及使用X光以外成像技术的研究。初步筛选后，对117篇文章进行了审查，14项研究符合最终纳入标准。由三名独立研究人员进行数据提取，并按照PRISMA 2020指南，使用如JBI清单、AMSTAR 2和CASP诊断研究清单等工具进行质量评估。根据Cochrane手册指南评估偏倚风险。14项研究共纳入70472张胸部X光片图像，符合纳入标准。评估了各种AI模型，数据集特征和所使用的AI技术存在差异。常见的预处理技术包括调整大小和归一化。心脏肥大检测的合并曲线下面积（AUC）为0.959（95%可信区间0.944 - 0.975）。CTR测量的合并标准化均差为0.0353（95%可信区间0.147 - 0.0760）。研究间存在显著异质性（I² = 89.97%，P < 0.0001），未检测到发表偏倚。标准化方法对于避免解释错误和推动医学影像诊断中的AI发展至关重要。统一报告标准对于CTR测量及更广泛医学影像应用中AI的进一步发展必不可少。
