In recent years, the development of artificial intelligence (AI) has brought significant changes to gastrointestinal endoscopy practice. This technology has rapidly evolved across various aspects, from lesion detection to clinical decision-making. Its presence not only improves the quality of examinations but also increasingly supports daily clinical practice.

One of the most widely adopted applications of AI is computer-aided detection (CADe), which assists in identifying polyps in real time during colonoscopy. In addition, computer-aided diagnosis (CADx) is being used to characterize lesions, including the estimation of invasion depth in colorectal cancer. With these tools, endoscopists can work more effectively, particularly in reducing the risk of missed lesions.

However, the implementation of AI in clinical practice is not without challenges. Several studies have shown that the improvement in adenoma detection rate (ADR) with AI in real-world settings is not always as significant as reported in controlled clinical trials. This highlights the continued importance of factors such as operator experience, procedural quality, and system integration.

On the other hand, AI also holds considerable potential in medical education. It can support less experienced endoscopists in achieving better performance, thereby contributing to a more consistent standard of care.

Ultimately, it is important to recognize that AI is not a replacement for clinicians. Rather, it serves as a supportive tool that complements clinical expertise. Clinical decisions must still be based on comprehensive judgment, taking into account the patient’s condition and the physician’s experience.

With the right approach, the integration of AI in endoscopy is expected to enhance diagnostic accuracy, procedural efficiency, and patient safety. The future of endoscopy is not solely defined by advancing technology, but by how wisely it is applied in clinical practice.

*This article has been reviewed by Dr. Rabbinu Rangga Pribadi, Consultant in Gastroenterohepatology

References:

D.Nemoto, K.Togashi, X.Zhu, S.Shinozaki, and T.Hikichi, “Artificial Intelligence-Based Prediction of Invasion Depth in Colorectal Cancer via Endoscopic Imaging (With Video): A Narrative Review,” Digestive Endoscopy38, no. 3 (2026): e70139, https://doi.org/10.1111/den.70139

Ali, H., Muzammil, M. A., Dahiya, D. S., Ali, F., Yasin, S., Hanif, W., Gangwani, M. K., Aziz, M., Khalaf, M., Basuli, D., & Al-Haddad, M. (2024). Artificial intelligence in gastrointestinal endoscopy: a comprehensive review. Annals of gastroenterology, 37(2), 133–141. https://doi.org/10.20524/aog.2024.0861

Wei, M. T., Fay, S., Yung, D., Ladabaum, U., & Kopylov, U. (2024). Artificial Intelligence-Assisted Colonoscopy in Real-World Clinical Practice: A Systematic Review and Meta-Analysis. Clinical and translational gastroenterology, 15(3), e00671. https://doi.org/10.14309/ctg.0000000000000671

Shiha, M. G., Oka, P., Raju, S. A., David Tai, F. W., Ching, H. L., Thoufeeq, M., Sidhu, R., McAlindon, M. E., & Sanders, D. S. (2023). Artificial intelligence-assisted colonoscopy for adenoma and polyp detection: an updated systematic review and meta-analysis. iGIE : innovation, investigation and insights, 2(3), 333–343.e8. https://doi.org/10.1016/j.igie.2023.05.001

Image Source: Getty Images