Could artificial intelligence-powered colonoscopies change the future of colorectal cancer screening?

Colorectal cancer is a major cause of cancer-related mortality worldwide, underscoring the importance of early and effective colorectal cancer screening to improve survival rates. Traditional colorectal cancer screening methods include non-invasive tests, such as the fecal immunochemical test (FIT), as well as diagnostic procedures like colonoscopy. Colonoscopy remains the gold standard for detecting and treating precancerous polyps and early-stage cancer, regardless of whether it is used as the first screening test or the second test following a positive FIT. However, its effectiveness can be affected by factors such as operator skill, patient variability, and limited lesion visibility, resulting in a significant rate of missed lesion rates and highlighting the need for more efficient and accurate screening techniques. This review is aimed to assess the current challenges of traditional screening methods with the impact of artificial intelligence (AI) in the diagnostic flow. The literature on AI-powered tools for colorectal cancer screening, including novel applications, emerging programs, and recent guidelines, has been reviewed to highlight both the advantages and limitations of implementing this technology in healthcare. Recent advances in AI have introduced soft AI colonoscopy, with the purpose of improving lesion recognition (computer-aided detection) and/or improving optical diagnosis (computer-aided diagnosis). AI-powered colonoscopy systems employ deep learning algorithms to analyze real-time endoscopic images, enhancing detection rates for adenomas, serrated lesions and cancer by reducing human error. AI-assisted colonoscopy enhances adenoma detection, enabling earlier intervention and improved patient outcomes. The benefits are particularly pronounced for less-experienced practitioners, as the detection rates for AI-assisted colonoscopy are similar to experts. AI integration also helps in the teaching process, in developing standardized procedures, and improving screening procedure accuracy and efficiency across different healthcare providers. However, there are challenges and limitations, such as the cost of AI implementation, data privacy concerns, and the need for extensive clinical validation. As AI technology continues to evolve, its transformation of the colorectal cancer screening system could revolutionize the field, making early detection more accessible and reducing mortality, on the condition that the above issues are addressed before widespread use.