Cortegoso Valdivia Pablo, Fantasia Stefano, Kayali Stefano, Deding Ulrik, Gualandi Noemi, Manno Mauro, Toth Ervin, Dray Xavier, Yang Shiming, Koulaouzidis Anastasios
Gastroenterology and Endoscopy Unit, University Hospital of Parma, Parma, Italy.
Department of Clinical Research, University of Southern Denmark, Odense, Denmark.
Endosc Int Open. 2025 Mar 14;13:a25442863. doi: 10.1055/a-2544-2863. eCollection 2025.
Small-bowel capsule endoscopy (SBCE) is the gold standard for diagnosing small bowel (SB) pathologies, but its time-consuming nature and potential for human error make it challenging. Several proprietary artificial intelligence (AI) auxiliary systems based on convolutional neural networks (CNNs) that are integrated into SBCE reading platforms are available on the market and offer the opportunity to improve lesion detection and reduce reading times. This meta-analysis aimed to evaluate performance of proprietary AI auxiliary platforms in SBCE compared with conventional, human-only reading.
A systematic literature search was conducted to identify studies comparing AI-assisted SBCE readings with conventional readings by gastroenterologists. Performance measures such as accuracy, sensitivity, specificity, and reading times were extracted and analyzed. Methodological transparency was assessed using the Methodological Index for Non-randomized Studies (MINORS) assessment tool.
Of 669 identified studies, 104 met the inclusion criteria and six were included in the analysis. Quality assessment revealed high methodological transparency for all included studies. Pooled analysis showed that AI-assisted reading achieved significantly higher sensitivity and comparable specificity to conventional reading, with a higher log diagnostic odds ratio and no substantial heterogeneity. In addition, AI integration substantially reduced reading times, with a mean decrease of 12-fold compared with conventional reading.
AI-assisted SBCE reading outperforms conventional human review in terms of detection accuracy and sensitivity, remarkably reducing reading times. AI in this setting could be a game-changer in reducing endoscopy service workload and supporting novice reader training.
小肠胶囊内镜检查（SBCE）是诊断小肠疾病的金标准，但其耗时且存在人为误差的可能性，使其具有挑战性。市场上有几种基于卷积神经网络（CNN）的专有人工智能（AI）辅助系统，这些系统集成到SBCE阅读平台中，为提高病变检测能力和缩短阅读时间提供了机会。本荟萃分析旨在评估专有AI辅助平台在SBCE中的性能，并与传统的仅由人工阅读进行比较。
进行系统的文献检索，以识别比较AI辅助的SBCE阅读与胃肠病学家的传统阅读的研究。提取并分析诸如准确性、敏感性、特异性和阅读时间等性能指标。使用非随机研究方法学指数（MINORS）评估工具评估方法学透明度。
在669项已识别的研究中，104项符合纳入标准，6项纳入分析。质量评估显示，所有纳入研究的方法学透明度都很高。汇总分析表明，AI辅助阅读的敏感性显著高于传统阅读，特异性相当，诊断比值比更高，且无实质性异质性。此外，AI集成显著缩短了阅读时间，与传统阅读相比平均减少了12倍。
在检测准确性和敏感性方面，AI辅助的SBCE阅读优于传统的人工审阅，显著缩短了阅读时间。在这种情况下，AI可能会改变内镜检查服务工作量，并支持新手读者培训。
