Artificial Intelligence Applied to Colonoscopy: Is It Time to Take a Step Forward?

Abstract

Growing evidence indicates that artificial intelligence (AI) applied to medicine is here to stay. In gastroenterology, AI computer vision applications have been stated as a research priority. The two main AI system categories are computer-aided polyp detection (CADe) and computer-assisted diagnosis (CADx). However, other fields of expansion are those related to colonoscopy quality, such as methods to objectively assess colon cleansing during the colonoscopy, as well as devices to automatically predict and improve bowel cleansing before the examination, predict deep submucosal invasion, obtain a reliable measurement of colorectal polyps and accurately locate colorectal lesions in the colon. Although growing evidence indicates that AI systems could improve some of these quality metrics, there are concerns regarding cost-effectiveness, and large and multicentric randomized studies with strong outcomes, such as post-colonoscopy colorectal cancer incidence and mortality, are lacking. The integration of all these tasks into one quality-improvement device could facilitate the incorporation of AI systems in clinical practice. In this manuscript, the current status of the role of AI in colonoscopy is reviewed, as well as its current applications, drawbacks and areas for improvement.

Comparative Study of Predictive Models for the Detection of Patients at High Risk of Inadequate Colonic Cleansing

“…Factors related to adherence to the bowel preparation protocol, deliberated or not, and tolerance to the cleansing solution can be targeted by educational strategies [15]. Factors associated with deliberate non-compliance include a lack of willingness to adhere to the cleansing protocol, a belief that the cleansing protocol may pose health issues (for example, fasting for diabetic patients), or failure to adhere to the time interval between the intake of the cleansing preparation and the colonoscopy procedure (for example, in patients residing far from the hospital) [16]. Unintentional non-compliance may be motivated by a lack of understanding of the cleansing instructions, either due to the cultural level of the patients or the inadequate drafting and explanation of the instructions.…”

“…In such instances, it is advisable to choose low-volume bowel preparations or those with more appealing flavors. Some helpful tricks, such as chewing gum during bowel preparation, consuming beverages like orange or pineapple juice, or the use of Coca-Cola as a diluent for the cleansing solution, may enhance the likelihood of successfully ingesting the entire dose of the bowel solution [16]. Other factors are related to the lack of efficacy of the bowel solution, primarily associated with low bowel motility, such as factors leading to constipation, like abdominal surgeries, comorbidities (for example, diabetes mellitus), or being on treatment with opioids or tricyclic antidepressants.…”

“…Other factors are related to the lack of efficacy of the bowel solution, primarily associated with low bowel motility, such as factors leading to constipation, like abdominal surgeries, comorbidities (for example, diabetes mellitus), or being on treatment with opioids or tricyclic antidepressants. Patients with these factors could benefit from changes in the bowel cleansing protocol, such as increasing the volume of bowel preparation [16]. Precisely, the predictive models have been designed to identify patients who would benefit most from additional bowel preparation.…”

“…With all this evidence, in patients undergoing their first colonoscopy, the most effective strategy to ensure adequate bowel cleansing is likely a multitarget approach, focusing on compliance with instructions, improving tolerance to bowel preparation, and possibly increasing the quantity of solution in the presence of risk factors for poor bowel cleansing. For patients who had a previous colonoscopy with inadequate bowel preparation, it is important to investigate the potential reasons, primarily lack of adherence to preparation instructions, intolerance, or lack of efficacy, and then tailor an appropriate strategy accordingly [16].…”

Artificial Intelligence–Assisted Optical Diagnosis: A Comprehensive Review of Its Role in Leave-In-Situ and Resect-and-Discard Strategies in Colonoscopy

“…It is imperative to perform comprehensive and high-quality cost-effectiveness analyses of these AI devices in various health care systems with diverse reimbursement policies before integrating them into routine clinical practice. To tackle this obstacle, the development of multifunctional AI systems capable of performing multiple tasks with a single device holds promise ( 37 ).…”