1. Conventional small-bowel capsule endoscopy reading versus proprietary artificial intelligence auxiliary systems:a systematic review with meta-analysis
- Author
-
Pablo Cortegoso Valdivia, Stefano Fantasia, Stefano Kayali, Ulrik Deding, Noemi Gualandi, Mauro Manno, Ervin Toth, Xavier Dray, Shiming Yang, and Anastasios Koulaouzidis
- Subjects
Diseases of the digestive system. Gastroenterology ,RC799-869 - Abstract
Background: 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 (CNN) and 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 aims to evaluate the performance of proprietary AI auxiliary platforms in SBCE compared to conventional, human-only reading. Methods: A systematic literature search was conducted to identify studies comparing AI-assisted SBCE readings to conventional readings by gastroenterologists. Performance measures such as accuracy, sensitivity, specificity, and reading times were extracted and analyzed. The methodological transparency was assessed using the Methodological Index for Non-randomized Studies (MINORS) assessment tool. Results: Of 669 identified studies, 104 met the inclusion criteria and 6 were included in the analysis. The quality assessment revealed high methodological transparency for all included studies. The 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. Additionally, AI integration substantially reduced in reading times, with a mean decrease of 12-fold compared to conventional reading. Conclusions: 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 services' workload and supporting novice readers' training.
- Full Text
- View/download PDF