Impact of Artificial Intelligence on Colonoscopy Surveillance After Polyp Removal: A Pooled Analysis of Randomized Trials

Current status of artificial intelligence colonoscopy on improving adenoma detection rate based on systematic review of multiple metanalysis

BACKGROUND

Colorectal cancer (CRC) can be prevented by screening and early detection. Colonoscopy is used for screening, and adenoma detection rate (ADR) is used as a key quality indicator of sufficient colonoscopy. However, ADR can vary significantly among endoscopists, leading to missed polyps or cancer. Artificial intelligence (AI) has shown promise in improving ADR by assisting in real-time polyp identification or diagnosis. While multiple randomized controlled trials (RCTs) and metanalyses highlight the benefits of AI in increasing detection rates and reducing missed polyps, concerns remain about its real-world applicability, impact on procedure time, and cost-effectiveness.

AIM

To explore the current status of AI assistance colonoscopy in adenoma detection and improving quality of colonoscopy.

METHODS

This systematic review followed PRISMA guidelines, both PubMed and Web of Science databases were used for articles search. Metanalyses and systematic reviews that assessed AI's role during colonoscopy. English article only published between January 2000 and January 2025 were included. Articles related to non-adenoma indications were excluded. Data extraction was independently performed by two researchers for accuracy and consistency.

RESULTS

22 articles met the inclusion criteria, with significant heterogeneity (I² = 28%-91%) observed in multiple studies. The number of studies per metanalysis ranged from 5 to 33, with higher heterogeneity in analyses involving more than 18 RCTs. AI demonstrated improvement in ADR, with an approximate 20% increase across multiple studies. However, its effectiveness in detecting flat or serrated adenomas remains unproven. Endoscopists with low ADR benefit more from AI-colonoscopies, while expert endoscopists outperformed AI in ADR, adenoma miss rate, and the identification of advanced lesions. No significant change in withdrawal time was observed when comparing AI-assisted colonoscopy to conventional endoscopy.

CONCLUSION

While AI-assisted colonoscopy has been shown to improve procedural quality, particularly for junior endoscopists and those with lower ADR, its performance decreases when compared to expert endoscopists in real-time clinical practice. This is especially evident in non-randomized studies, where AI demonstrates limited real-world benefits despite its benefit in controlled settings. Furthermore, no meta-analyses have specifically examined AI's impact on the learning experience of fellows and residents. Some experts caution that reliance on AI may prevent trainees from developing essential observational skills, potentially leading to less thorough examinations. Further research is needed to determine the actual benefits of AI-colonoscopy, particularly its role in cancer prevention. As technology advances, improved outcomes are expected, especially in detecting small, flat, and lesions at difficult anatomical locations.

Artificial intelligence for reducing missed detection of adenomas and polyps in colonoscopy: A systematic review and meta-analysis

BACKGROUND

Colorectal cancer has a high incidence and mortality rate, and the effectiveness of routine colonoscopy largely depends on the endoscopist’s expertise. In recent years, computer-aided detection (CADe) systems have been increasingly integrated into colonoscopy to improve detection accuracy. However, while most studies have focused on adenoma detection rate (ADR) as the primary outcome, the more sensitive adenoma miss rate (AMR) has been less frequently analyzed.

AIM

To evaluate the effectiveness of CADe in colonoscopy and assess the advantages of AMR over ADR.

METHODS

A comprehensive literature search was conducted in PubMed, Embase, and the Cochrane Central Register of Controlled Trials using predefined search strategies to identify relevant studies published up to August 2, 2024. Statistical analyses were performed to compare outcomes between groups, and potential publication bias was assessed using funnel plots. The quality of the included studies was evaluated using the Cochrane Risk of Bias tool and the Grading of Recommendations, Assessment, Development, and Evaluation approach.

RESULTS

Five studies comprising 1624 patients met the inclusion criteria. AMR was significantly lower in the CADe-assisted group than in the routine colonoscopy group (147/927, 15.9% vs 345/960, 35.9%; P < 0.01). However, CADe did not provide a significant advantage in detecting advanced adenomas or lesions measuring 6-9 mm or ≥ 10 mm. The polyp miss rate (PMR) was also lower in the CADe-assisted group [odds ratio (OR), 0.35; 95% confidence interval (CI): 0.23-0.52; P < 0.01]. While the overall ADR did not differ significantly between groups, the ADR during the first-pass examination was higher in the CADe-assisted group (OR, 1.37; 95%CI: 1.10-1.69; P = 0.004). The level of evidence for the included randomized controlled trials was graded as moderate.

CONCLUSION

CADe can significantly reduce AMR and PMR while improving ADR during initial detection, demonstrating its potential to enhance colonoscopy performance. These findings highlight the value of CADe in improving the detection of colorectal neoplasms, particularly small and histologically distinct adenomas.

Colon Cancer Screening, Surveillance, and Treatment: Novel Artificial Intelligence Driving Strategies in the Management of Colon Lesions

Colonoscopy, a crucial procedure for detecting and removing colorectal polyps, has seen transformative advancements through the integration of artificial intelligence, specifically in computer-aided detection (CADe) and diagnosis (CADx). These tools enhance real-time detection and characterization of lesions, potentially reducing human error, and standardizing the quality of colonoscopy across endoscopists. CADe has proven effective in increasing adenoma detection rate, potentially reducing long-term colorectal cancer incidence. However, CADe's benefits are accompanied by challenges, such as potentially longer procedure times, increased non-neoplastic polyp resections, and a higher surveillance burden. CADx, although promising in differentiating neoplastic and non-neoplastic diminutive polyps, encounters limitations in accuracy, particularly in the proximal colon. Real-world data also revealed gaps between trial efficacy and practical outcomes, emphasizing the need for further research in uncontrolled settings. Moreover, CADx limited specificity and binary output underscore the necessity for explainable artificial intelligence to gain endoscopists' trust. This review aimed to explore the benefits, harms, and limitations of artificial intelligence for colon cancer screening, surveillance, and treatment focusing on CADe and CADx systems for lesion detection and characterization, respectively, while addressing challenges in integrating these technologies into clinical practice.

AI and Polyp Detection During Colonoscopy

Colorectal cancer (CRC) prevention depends on effective colonoscopy; yet variability in adenoma detection rates (ADRs) and missed lesions remain significant hurdles. Artificial intelligence-powered computer-aided detection (CADe) systems offer promising advancements in enhancing polyp detection. This review examines the role of CADe in improving ADR and reducing adenoma miss rates (AMRs) while addressing its broader clinical implications. CADe has demonstrated consistent improvements in ADRs and AMRs; largely by detecting diminutive polyps, but shows limited efficacy in identifying advanced adenomas or sessile serrated lesions. Challenges such as operator deskilling and the need for enhanced algorithms persist. Combining CADe with adjunctive techniques has shown potential for further optimizing performance. While CADe has standardized detection quality; its long-term impact on CRC incidence and mortality remains inconclusive. Future research should focus on refining CADe technology and assessing its effectiveness in reducing the global burden of CRC.

Variability in computer-aided detection effect on adenoma detection rate in randomized controlled trials: A meta-regression analysis

BACKGROUND

Computer-aided detection (CADe) systems may increase adenoma detection rate (ADR) during colonoscopy. However, the variable results of CADe effects in different RCTs warrant investigation into factors influencing these results.

AIMS

Investigate the different variables possibly affecting the impact of CADe-assisted colonoscopy and its effect on ADR.

METHODS

We searched MEDLINE, EMBASE, and Scopus databases until July 2023 for RCTs reporting performance of CADe systems in the detection of colorectal neoplasia. The main outcome was pooled ADR. A random-effects meta-analysis was performed to obtain the pooled risk ratios (RR) with 95 % confidence intervals (CI)). To explore sources of heterogeneity, we conducted a meta-regression analysis using both univariable and multivariable mixed-effects models. Potential explanatory variables included factors influencing adenoma prevalence, such as patient gender, age, and colonoscopy indication. We also included both key (ADR), and minor (Withdrawal time) performance measures considered as quality indicators for colonoscopy.

RESULTS

Twenty-three randomized controlled trials (RCTs) on 19,077 patients were include. ADR was higher in the CADe group (46 % [95 % CI 39-52]) than in the standard colonoscopy group (38 % [95 % CI 31-46]) with a risk ratio of 1.22 [95 % CI 1.14-1.29]); and a substantial level of heterogeneity (I2 = 67.69 %). In the univariable meta-regression analysis, patient age, ADR in control arms, and withdrawal time were the strongest predictors of CADe effect on ADR (P < .001). In multivariable meta-regression, ADR in control arms, and withdrawal time were simultaneous significant predictors of the proportion of the CADe effect on ADR.

CONCLUSION

The substantial level of heterogeneity found appeared to be associated with variability in colonoscopy quality performances across the studies, namely ADR in control arm, and withdrawal time.

Video recording in GI endoscopy

The current approach to procedure reporting in endoscopy aims to capture essential findings and interventions but inherently sacrifices the rich detail and nuance of the entire endoscopic experience. Endoscopic video recording (EVR) provides a complete archive of the procedure, extending the utility of the encounter beyond diagnosis and intervention, and potentially adding significant value to the care of the patient and the field in general. This white paper outlines the potential of EVR in clinical care, quality improvement, education, and artificial intelligence-driven innovation, and addresses critical considerations surrounding technology, regulation, ethics, and privacy. As with other medical imaging modalities, growing adoption of EVR is inevitable, and proactive engagement of professional societies and practitioners is essential to harness the full potential of this technology toward improving clinical care, education, and research.

A Narrative Review on the Role of Artificial Intelligence (AI) in Colorectal Cancer Management

The role of artificial intelligence (AI) tools and deep learning in medical practice in the management of colorectal cancer has gathered significant attention in recent years. Colorectal cancer, being the third most common type of malignancy, requires an innovative approach to augment early detection and advanced surgical techniques to reduce morbidity and mortality. With its emerging potential, AI improves colorectal cancer management by assisting with accuracy in screening, pathology evaluation, precision, and postoperative care. Evidence suggests that AI minimizes missed cases during colorectal cancer screening, plays a promising role in pathology and imaging diagnoses, and facilitates accurate staging. In surgical management, AI demonstrates comparable or superior outcomes to laparoscopic approaches, with reduced hospital stays and conversion rates. However, these outcomes are influenced by clinical expertise and other dependable factors, including expertise in implementing AI-based software and detecting possible errors. Despite these advancements, limited multicenter studies and randomized trials restrict the comprehensive evaluation of AI's true potential and integration into standard practice. We used Pubmed, Google Scholar, Cochrane Library, and Scopus databases for this review. The final number of articles selected, depending on inclusion and exclusion criteria, is 122. We included papers published in the English language, literature published in the last 10 years, and adult patient populations above 35 years with colorectal cancer. We thoroughly included randomized controlled trials, cohort studies, meta-analyses, systematic reviews, narrative reviews, and case-control studies. The use of AI paves the way for the adoption of more personalized medicine. This review highlights the advantages of AI at various disease stages for colorectal cancer patients and evaluates its potential for cost-effective implementation in clinical practice.

Benefits, burden, and harms of computer aided polyp detection with artificial intelligence in colorectal cancer screening: microsimulation modelling study

ABSTRACT

Objective

To estimate the benefits, burden, and harms of implementing computer aided detection (CADe) of polyps in colonoscopy of population based screening programmes for colorectal cancer.

Design

Microsimulation modelling study.

Setting

Cost effectiveness working package in the OperA (optimising colorectal cancer prevention through personalised treatment with artificial intelligence) project. A parallel guideline committee panel (BMJ Rapid recommendation) was consulted in defining the screening interventions and selection of outcome measures.

Population

Four cohorts of 100 000 European individuals aged 60-69 years.

Intervention

The intervention was one screening of colonoscopy and a screening of colonoscopy after faecal immunochemical test every other year with CADe. The comparison group had the same screening every other year without CADe.

Main outcome measures

Benefits (colorectal cancer incidence and death), burden (surveillance colonoscopies), and harms (colonoscopy related adverse events) over 10 years were measured. The certainty in each outcome was assessed by use of the GRADE (Grading of Recommendations Assessment, Development, and Evaluation) approach.

Results

For 100 000 individuals participating in colonoscopy screening, 824 (0.82%) were diagnosed with colorectal cancer within 10 years without CADe versus 713 (0.71%) with CADe (risk difference -0.11% (95% CI -0.43% to 0.21%)). For faecal immunochemical test screening colonoscopy, the risk was 5.82% (n=5820) without CADe versus 5.77% (n=5770) with CADe (difference -0.05% (-0.33% to 0.15%)). The risk of surveillance colonoscopy increased from 26.45% (n=26 453) to 32.82% (n=32 819) (difference 6.37% (5.8% to 6.9%)) for colonoscopy screening and from 52.26% (n=52 263) to 53.08% (n=53 082) (difference 0.82% (0.38% to 1.26%)) for faecal immunochemical test screening colonoscopy. No significant differences were noted in adverse events related to the colonoscopy between CADe and no CADe. The model estimates were sensitive to the assumed effects of screening on colorectal cancer risk and of CADe on adenoma detection rates. All outcomes were graded as low certainty.

Conclusion

With low certainty of evidence, adoption of CADe in population based screening provides small and uncertain clinical meaningful benefit, no incremental harms, and increased surveillance burden after screening.

Validation of Artificial Intelligence Computer-Aided Detection of Colonic Neoplasm in Colonoscopy

BACKGROUND/OBJECTIVES

Controlling colonoscopic quality is important in the detection of colon polyps during colonoscopy as it reduces the overall long-term colorectal cancer risk. Artificial intelligence has recently been introduced in various medical fields. In this study, we aimed to validate a previously developed artificial intelligence (AI) computer-aided detection (CADe) algorithm called ALPHAON® and compare outcomes with previous studies that showed that AI outperformed and assisted endoscopists of diverse levels of expertise in detecting colon polyps.

METHODS

We used the retrospective data of 500 still images, including 100 polyp images and 400 healthy colon images. In addition, we validated the CADe algorithm and compared its diagnostic performance with that of two expert endoscopists and six trainees from Gachon University Gil Medical Center. After a washing-out period of over 2 weeks, endoscopists performed polyp detection on the same dataset with the assistance of ALPHAON®.

RESULTS

The CADe algorithm presented a high capability in detecting colon polyps, with an accuracy of 0.97 (95% CI: 0.96 to 0.99), sensitivity of 0.91 (95% CI: 0.85 to 0.97), specificity of 0.99 (95% CI: 0.97 to 0.99), and AUC of 0.967. When evaluating and comparing the polyp detection ability of ALPHAON® with that of endoscopists with different levels of expertise (regarding years of endoscopic experience), it was found that ALPHAON® outperformed the experts in accuracy (0.97, 95% CI: 0.96 to 0.99), sensitivity (0.91, 95% CI: 0.85 to 0.97), and specificity (0.99, 95% CI: 0.97 to 0.99). After a washing-out period of over 2 weeks, the overall capability significantly improved for both experts and trainees with the assistance of ALPHAON®.

CONCLUSIONS

The high performance of the CADe algorithm system in colon polyp detection during colonoscopy was verified. The sensitivity of ALPHAON® led to it outperforming the experts, and it demonstrated the ability to enhance the polyp detection ability of both experts and trainees, which suggests a significant possibility of ALPHAON® being able to provide endoscopic assistance.

Artificial Intelligence-Assisted Colonoscopy for Polyp Detection : A Systematic Review and Meta-analysis

BACKGROUND

Randomized clinical trials (RCTs) of computer-aided detection (CADe) system-enhanced colonoscopy compared with conventional colonoscopy suggest increased adenoma detection rate (ADR) and decreased adenoma miss rate (AMR), but the effect on detection of advanced colorectal neoplasia (ACN) is unclear.

PURPOSE

To conduct a systematic review to compare performance of CADe-enhanced and conventional colonoscopy.

DATA SOURCES

Cochrane Library, Google Scholar, Ovid EMBASE, Ovid MEDLINE, PubMed, Scopus, and Web of Science Core Collection databases were searched through February 2024.

STUDY SELECTION

Published RCTs comparing CADe-enhanced and conventional colonoscopy.

DATA EXTRACTION

Average adenoma per colonoscopy (APC) and ACN per colonoscopy were primary outcomes. Adenoma detection rate, AMR, and ACN detection rate (ACN DR) were secondary outcomes. Balancing outcomes included withdrawal time and resection of nonneoplastic polyps (NNPs). Subgroup analyses were done by neural network architecture.

DATA SYNTHESIS

Forty-four RCTs with 36 201 cases were included. Computer-aided detection-enhanced colonoscopies have higher average APC (12 090 of 12 279 [0.98] vs. 9690 of 12 292 [0.78], incidence rate difference [IRD] = 0.22 [95% CI, 0.16 to 0.28]) and higher ADR (7098 of 16 253 [44.7%] vs. 5825 of 15 855 [36.7%], rate ratio [RR] = 1.21 [CI, 1.15 to 1.28]). Average ACN per colonoscopy was similar (1512 of 9296 [0.16] vs. 1392 of 9121 [0.15], IRD = 0.01 [CI, -0.01 to 0.02]), but ACN DR was higher with CADe system use (1260 of 9899 [12.7%] vs. 1119 of 9746 [11.5%], RR = 1.16 [CI, 1.02 to 1.32]). Using CADe systems resulted in resection of almost 2 extra NNPs per 10 colonoscopies and longer total withdrawal time (0.53 minutes [CI, 0.30 to 0.77]).

LIMITATION

Statistically significant heterogeneity in quality and sample size and inability to blind endoscopists to the intervention in included studies may affect the performance estimates.

CONCLUSION

Computer-aided detection-enhanced colonoscopies have increased APC and detection rate but no difference in ACN per colonoscopy and a small increase in ACN DR. There is minimal increase in procedure time and no difference in performance across neural network architectures.

PRIMARY FUNDING SOURCE

None. (PROSPERO: CRD42023422835).

Creating a standardized tool for the evaluation and comparison of artificial intelligence-based computer-aided detection programs in colonoscopy: a modified Delphi approach

BACKGROUND AND AIMS

Multiple computer-aided detection (CADe) software programs have now achieved regulatory approval in the United States, Europe, and Asia and are being used in routine clinical practice to support colorectal cancer screening. There is uncertainty regarding how different CADe algorithms may perform. No objective methodology exists for comparing different algorithms. We aimed to identify priority scoring metrics for CADe evaluation and comparison.

METHODS

A modified Delphi approach was used. Twenty-five global leaders in CADe in colonoscopy, including endoscopists, researchers, and industry representatives, participated in an online survey over the course of 8 months. Participants generated 121 scoring criteria, 54 of which were deemed within the study scope and distributed for review and asynchronous e-mail-based open comment. Participants then scored criteria in order of priority on a 5-point Likert scale during ranking round 1. The top 11 highest priority criteria were re-distributed, with another opportunity for open comment, followed by a final round of priority scoring to identify the final 6 criteria.

RESULTS

Mean priority scores for the 54 criteria ranged from 2.25 to 4.38 after the first ranking round. The top 11 criteria after round 1 of ranking yielded mean priority scores ranging from 3.04 to 4.16. The final 6 highest priority criteria, including a tie for first-place ranking, were (1, tied) sensitivity (average, 4.16) and (1, tied) separate and independent validation of the CADe algorithm (average, 4.16); (3) adenoma detection rate (average, 4.08); (4) false-positive rate (average, 4.00); (5) latency (average, 3.84); and (6) adenoma miss rate (average, 3.68).

CONCLUSIONS

This is the first reported international consensus statement of priority scoring metrics for CADe in colonoscopy. These scoring criteria should inform CADe software development and refinement. Future research should validate these metrics on a benchmark video data set to develop a validated scoring instrument.

Impact of Artificial Intelligence on Polyp Size and Surveillance Colonoscopy: A Phantom Study

Background Artificial intelligence (AI) is a hot topic in the world of medicine. AI may be useful in identifying and sizing polyps, which influence surveillance intervals. Therefore, we examined polyp size estimation by AI using a survey study. Methods A survey study was performed using a phantom colon model. Eleven videos were produced in the colon phantom using a colonoscope. Gastroenterologists were compared to a new AI system (Argus) for sizing polyps and their impact on surveillance intervals. Results Eleven gastroenterologists completed the survey with a mean age of 51.1 ± 8.1 years and an average of 19.3 ± 10 years of experience. Mean accuracy rates for gastroenterologists were 76% ± 0.1% (range 54-89%) compared to 96% ± 0.05% for Argus. Endoscopists estimated polyp size within ± 1 mm 44 times (36%) versus 9 times (82%) with Argus. Endoscopists' surveillance recommendations were significantly more often inappropriate compared to Argus (34 vs 0). The interval of next colonoscopy was too short for 27 endoscopists (22%) and too long for seven endoscopists (6%). Conclusions AI appears to be more accurate in estimating polyp size than experienced endoscopists. Given the potential impact on surveillance intervals, AI may result in cost savings.

The 2023 top 10 list of endoscopy topics in medical publishing: an annual review by the American Society for Gastrointestinal Endoscopy Editorial Board

Using a systematic literature search of original articles published during 2023 in Gastrointestinal Endoscopy (GIE) and other high-impact medical and gastroenterology journals, the GIE Editorial Board of the American Society for Gastrointestinal Endoscopy compiled a list of the top 10 most significant topic areas in general and advanced GI endoscopy during the year. Each GIE Editorial Board member was directed to consider 3 criteria in generating candidate topics-significance, novelty, and impact on global clinical practice-and subject matter consensus was facilitated by the Chair through electronic voting and a meeting of the entire GIE Editorial Board. The 10 identified areas collectively represent advances in the following endoscopic spheres: GI bleeding, endohepatology, endoscopic palliation, artificial intelligence and polyp detection, artificial intelligence beyond the colon, better polypectomy and EMR, how to make endoscopy units greener, high-quality upper endoscopy, endoscopic tissue apposition and closure devices, and endoscopic submucosal dissection. Each board member was assigned a topic area around which to summarize relevant important articles, thereby generating this overview of the "top 10" endoscopic advances of 2023.

An artificial intelligence-assisted system versus white light endoscopy alone for adenoma detection in individuals with Lynch syndrome (TIMELY): an international, multicentre, randomised controlled trial

BACKGROUND

Computer-aided detection (CADe) systems for colonoscopy have been shown to increase small polyp detection during colonoscopy in the general population. People with Lynch syndrome represent an ideal target population for CADe-assisted colonoscopy because adenomas, the primary cancer precursor lesions, are characterised by their small size and higher likelihood of showing advanced histology. We aimed to evaluate the performance of CADe-assisted colonoscopy in detecting adenomas in individuals with Lynch syndrome.

METHODS

TIMELY was an international, multicentre, parallel, randomised controlled trial done in 11 academic centres and six community centres in Belgium, Germany, Italy, and Spain. We enrolled individuals aged 18 years or older with pathogenic or likely pathogenic MLH1, MSH2, MSH6, or EPCAM variants. Participants were consecutively randomly assigned (1:1) to either CADe (GI Genius) assisted white light endoscopy (WLE) or WLE alone. A centre-stratified randomisation sequence was generated through a computer-generated system with a separate randomisation list for each centre according to block-permuted randomisation (block size 26 patients per centre). Allocation was automatically provided by the online AEG-REDCap database. Participants were masked to the random assignment but endoscopists were not. The primary outcome was the mean number of adenomas per colonoscopy, calculated by dividing the total number of adenomas detected by the total number of colonoscopies and assessed in the intention-to-treat population. This trial is registered with ClinicalTrials.gov, NCT04909671.

FINDINGS

Between Sept 13, 2021, and April 6, 2023, 456 participants were screened for eligibility, 430 of whom were randomly assigned to receive CADe-assisted colonoscopy (n=214) or WLE (n=216). 256 (60%) participants were female and 174 (40%) were male. In the intention-to-treat analysis, the mean number of adenomas per colonoscopy was 0·64 (SD 1·57) in the CADe group and 0·64 (1·17) in the WLE group (adjusted rate ratio 1·03 [95% CI 0·72-1·47); p=0·87). No adverse events were reported during the trial.

INTERPRETATION

In this multicentre international trial, CADe did not improve the detection of adenomas in individuals with Lynch syndrome. High-quality procedures and thorough inspection and exposure of the colonic mucosa remain the cornerstone in surveillance of Lynch syndrome.

FUNDING

Spanish Gastroenterology Association, Spanish Society of Digestive Endoscopy, European Society of Gastrointestinal Endoscopy, Societat Catalana de Digestologia, Instituto Carlos III, Beca de la Marato de TV3 2020. Co-funded by the European Union.

Efficient artificial intelligence-based assessment of the gastroesophageal valve with Hill classification through active learning

Standardized assessment of the gastroesophageal valve during endoscopy, attainable via the Hill classification, is important for clinical assessment and therapeutic decision making. The Hill classification is associated with the presence of hiatal hernia (HH), a common endoscopic finding connected to gastro-esophageal reflux disease. A novel efficient medical artificial intelligence (AI) training pipeline using active learning (AL) is designed. We identified 21,970 gastroscopic images as training data and used our AL to train a model for predicting the Hill classification and detecting HH. Performance of the AL and traditionally trained models were evaluated on an external expert-annotated image collection. The AL model achieved accuracy of 76%. A traditionally trained model with 125% more training data achieved 77% accuracy. Furthermore, the AL model achieved higher precision than the traditional one for rare classes, with 0.54 versus 0.39 (p < 0.05) for grade 3 and 0.72 versus 0.61 (p < 0.05) for grade 4. In detecting HH, the AL model achieved 94% accuracy, 0.72 precision and 0.74 recall. Our AL pipeline is more efficient than traditional methods in training AI for endoscopy.

Enhancing human-AI collaboration: The case of colonoscopy

Diagnostic errors impact patient health and healthcare costs. Artificial Intelligence (AI) shows promise in mitigating this burden by supporting Medical Doctors in decision-making. However, the mere display of excellent or even superhuman performance by AI in specific tasks does not guarantee a positive impact on medical practice. Effective AI assistance should target the primary causes of human errors and foster effective collaborative decision-making with human experts who remain the ultimate decision-makers. In this narrative review, we apply these principles to the specific scenario of AI assistance during colonoscopy. By unraveling the neurocognitive foundations of the colonoscopy procedure, we identify multiple bottlenecks in perception, attention, and decision-making that contribute to diagnostic errors, shedding light on potential interventions to mitigate them. Furthermore, we explored how existing AI devices fare in clinical practice and whether they achieved an optimal integration with the human decision-maker. We argue that to foster optimal Human-AI collaboration, future research should expand our knowledge of factors influencing AI's impact, establish evidence-based cognitive models, and develop training programs based on them. These efforts will enhance human-AI collaboration, ultimately improving diagnostic accuracy and patient outcomes. The principles illuminated in this review hold more general value, extending their relevance to a wide array of medical procedures and beyond.

Enhancing artificial intelligence-doctor collaboration for computer-aided diagnosis in colonoscopy through improved digital literacy

Establishing appropriate trust and maintaining a balanced reliance on digital resources are vital for accurate optical diagnoses and effective integration of computer-aided diagnosis (CADx) in colonoscopy. Active learning using diverse polyp image datasets can help in developing precise CADx systems. Enhancing doctors' digital literacy and interpreting their results is crucial. Explainable artificial intelligence (AI) addresses opacity, and textual descriptions, along with AI-generated content, deepen the interpretability of AI-based findings by doctors. AI conveying uncertainties and decision confidence aids doctors' acceptance of results. Optimal AI-doctor collaboration requires improving algorithm performance, transparency, addressing uncertainties, and enhancing doctors' optical diagnostic skills.

Colorectal cancer screening: A review of current knowledge and progress in research

Colorectal cancer (CRC) is one of the most prevalent malignancies worldwide, being the third most commonly diagnosed malignancy and the second leading cause of cancer-related deaths globally. Despite the progress in screening, early diagnosis, and treatment, approximately 20%-25% of CRC patients still present with metastatic disease at the time of their initial diagnosis. Furthermore, the burden of disease is still expected to increase, especially in individuals younger than 50 years old, among whom early-onset CRC incidence has been increasing. Screening and early detection are pivotal to improve CRC-related outcomes. It is well established that CRC screening not only reduces incidence, but also decreases deaths from CRC. Diverse screening strategies have proven effective in decreasing both CRC incidence and mortality, though variations in efficacy have been reported across the literature. However, uncertainties persist regarding the optimal screening method, age intervals and periodicity. Moreover, adherence to CRC screening remains globally low. In recent years, emerging technologies, notably artificial intelligence, and non-invasive biomarkers, have been developed to overcome these barriers. However, controversy exists over the actual impact of some of the new discoveries on CRC-related outcomes and how to effectively integrate them into daily practice. In this review, we aim to cover the current evidence surrounding CRC screening. We will further critically assess novel approaches under investigation, in an effort to differentiate promising innovations from mere novelties.

Effect of Real-Time Computer-Aided Polyp Detection System (ENDO-AID) on Adenoma Detection in Endoscopists-in-Training: A Randomized Trial

BACKGROUND

The effect of computer-aided polyp detection (CADe) on adenoma detection rate (ADR) among endoscopists-in-training remains unknown.

METHODS

We performed a single-blind, parallel-group, randomized controlled trial in Hong Kong between April 2021 and July 2022 (NCT04838951). Eligible subjects undergoing screening/surveillance/diagnostic colonoscopies were randomized 1:1 to receive colonoscopies with CADe (ENDO-AID[OIP-1]) or not (control) during withdrawal. Procedures were performed by endoscopists-in-training with <500 procedures and <3 years' experience. Randomization was stratified by patient age, sex, and endoscopist experience (beginner vs intermediate level, <200 vs 200-500 procedures). Image enhancement and distal attachment devices were disallowed. Subjects with incomplete colonoscopies or inadequate bowel preparation were excluded. Treatment allocation was blinded to outcome assessors. The primary outcome was ADR. Secondary outcomes were ADR for different adenoma sizes and locations, mean number of adenomas, and non-neoplastic resection rate.

RESULTS

A total of 386 and 380 subjects were randomized to CADe and control groups, respectively. The overall ADR was significantly higher in the CADe group than in the control group (57.5% vs 44.5%; adjusted relative risk, 1.41; 95% CI, 1.17-1.72; P < .001). The ADRs for <5 mm (40.4% vs 25.0%) and 5- to 10-mm adenomas (36.8% vs 29.2%) were higher in the CADe group. The ADRs were higher in the CADe group in both the right colon (42.0% vs 30.8%) and left colon (34.5% vs 27.6%), but there was no significant difference in advanced ADR. The ADRs were higher in the CADe group among beginner (60.0% vs 41.9%) and intermediate-level (56.5% vs 45.5%) endoscopists. Mean number of adenomas (1.48 vs 0.86) and non-neoplastic resection rate (52.1% vs 35.0%) were higher in the CADe group.

CONCLUSIONS

Among endoscopists-in-training, the use of CADe during colonoscopies was associated with increased overall ADR. (ClinicalTrials.gov, Number: NCT04838951).

AGA Clinical Practice Update on the Role of Artificial Intelligence in Colon Polyp Diagnosis and Management: Commentary

DESCRIPTION

The purpose of this American Gastroenterological Association (AGA) Institute Clinical Practice Update (CPU) is to review the available evidence and provide expert commentary on the current landscape of artificial intelligence in the evaluation and management of colorectal polyps.

METHODS

This CPU was commissioned and approved by the AGA Institute Clinical Practice Updates Committee (CPUC) and the AGA Governing Board to provide timely guidance on a topic of high clinical importance to the AGA membership and underwent internal peer review by the CPUC and external peer review through standard procedures of Gastroenterology. This Expert Commentary incorporates important as well as recently published studies in this field, and it reflects the experiences of the authors who are experienced endoscopists with expertise in the field of artificial intelligence and colorectal polyps.

Technical/Algorithm, Stakeholder, and Society (TASS) barriers to the application of artificial intelligence in medicine: A systematic review

INTRODUCTION

The use of artificial intelligence (AI), particularly machine learning and predictive analytics, has shown great promise in health care. Despite its strong potential, there has been limited use in health care settings. In this systematic review, we aim to determine the main barriers to successful implementation of AI in healthcare and discuss potential ways to overcome these challenges.

METHODS

We conducted a literature search in PubMed (1/1/2001-1/1/2023). The search was restricted to publications in the English language, and human study subjects. We excluded articles that did not discuss AI, machine learning, predictive analytics, and barriers to the use of these techniques in health care. Using grounded theory methodology, we abstracted concepts to identify major barriers to AI use in medicine.

RESULTS

We identified a total of 2,382 articles. After reviewing the 306 included papers, we developed 19 major themes, which we categorized into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). These themes included: Lack of Explainability, Need for Validation Protocols, Need for Standards for Interoperability, Need for Reporting Guidelines, Need for Standardization of Performance Metrics, Lack of Plan for Updating Algorithm, Job Loss, Skills Loss, Workflow Challenges, Loss of Patient Autonomy and Consent, Disturbing the Patient-Clinician Relationship, Lack of Trust in AI, Logistical Challenges, Lack of strategic plan, Lack of Cost-effectiveness Analysis and Proof of Efficacy, Privacy, Liability, Bias and Social Justice, and Education.

CONCLUSION

We identified 19 major barriers to the use of AI in healthcare and categorized them into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). Future studies should expand on barriers in pediatric care and focus on developing clearly defined protocols to overcome these barriers.

The Role of Artificial Intelligence in Colorectal Cancer Screening: Lesion Detection and Lesion Characterization

Colorectal cancer remains a leading cause of cancer-related morbidity and mortality worldwide, despite the widespread uptake of population surveillance strategies. This is in part due to the persistent development of 'interval colorectal cancers', where patients develop colorectal cancer despite appropriate surveillance intervals, implying pre-malignant polyps were not resected at a prior colonoscopy. Multiple techniques have been developed to improve the sensitivity and accuracy of lesion detection and characterisation in an effort to improve the efficacy of colorectal cancer screening, thereby reducing the incidence of interval colorectal cancers. This article presents a comprehensive review of the transformative role of artificial intelligence (AI), which has recently emerged as one such solution for improving the quality of screening and surveillance colonoscopy. Firstly, AI-driven algorithms demonstrate remarkable potential in addressing the challenge of overlooked polyps, particularly polyp subtypes infamous for escaping human detection because of their inconspicuous appearance. Secondly, AI empowers gastroenterologists without exhaustive training in advanced mucosal imaging to characterise polyps with accuracy similar to that of expert interventionalists, reducing the dependence on pathologic evaluation and guiding appropriate resection techniques or referrals for more complex resections. AI in colonoscopy holds the potential to advance the detection and characterisation of polyps, addressing current limitations and improving patient outcomes. The integration of AI technologies into routine colonoscopy represents a promising step towards more effective colorectal cancer screening and prevention.

Detecting colorectal lesions with image-enhanced endoscopy: an updated review from clinical trials

Colonoscopy plays an important role in reducing the incidence and mortality of colorectal cancer by detecting adenomas and other precancerous lesions. Image-enhanced endoscopy (IEE) increases lesion visibility by enhancing the microstructure, blood vessels, and mucosal surface color, resulting in the detection of colorectal lesions. In recent years, various IEE techniques have been used in clinical practice, each with its unique characteristics. Numerous studies have reported the effectiveness of IEE in the detection of colorectal lesions. IEEs can be divided into two broad categories according to the nature of the image: images constructed using narrowband wavelength light, such as narrowband imaging and blue laser imaging/blue light imaging, or color images based on white light, such as linked color imaging, texture and color enhancement imaging, and i-scan. Conversely, artificial intelligence (AI) systems, such as computer-aided diagnosis systems, have recently been developed to assist endoscopists in detecting colorectal lesions during colonoscopy. To better understand the features of each IEE, this review presents the effectiveness of each type of IEE and their combination with AI for colorectal lesion detection by referencing the latest research data.

Effectiveness and application of artificial intelligence for endoscopic screening of colorectal cancer: the future is now

INTRODUCTION

Artificial intelligence (AI) in gastrointestinal endoscopy includes systems designed to interpret medical images and increase sensitivity during examination. This may be a promising solution to human biases and may provide support during diagnostic endoscopy.

AREAS COVERED

This review aims to summarize and evaluate data supporting AI technologies in lower endoscopy, addressing their effectiveness, limitations, and future perspectives.

EXPERT OPINION

Computer-aided detection (CADe) systems have been studied with promising results, allowing for an increase in adenoma detection rate (ADR), adenoma per colonoscopy (APC), and a reduction in adenoma miss rate (AMR). This may lead to an increase in the sensitivity of endoscopic examinations and a reduction in the risk of interval-colorectal cancer. In addition, computer-aided characterization (CADx) has also been implemented, aiming to distinguish adenomatous and non-adenomatous lesions through real-time assessment using advanced endoscopic imaging techniques. Moreover, computer-aided quality (CADq) systems have been developed with the aim of standardizing quality measures in colonoscopy (e.g. withdrawal time and adequacy of bowel cleansing) both to improve the quality of examinations and set a reference standard for randomized controlled trials.

Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement

The number of artificial intelligence (AI) tools for colonoscopy on the market is increasing with supporting clinical evidence. Nevertheless, their implementation is not going smoothly for a variety of reasons, including lack of data on clinical benefits and cost-effectiveness, lack of trustworthy guidelines, uncertain indications, and cost for implementation. To address this issue and better guide practitioners, the World Endoscopy Organization (WEO) has provided its perspective about the status of AI in colonoscopy as the position statement. WEO Position Statement: Statement 1.1: Computer-aided detection (CADe) for colorectal polyps is likely to improve colonoscopy effectiveness by reducing adenoma miss rates and thus increase adenoma detection; Statement 1.2: In the short term, use of CADe is likely to increase health-care costs by detecting more adenomas; Statement 1.3: In the long term, the increased cost by CADe could be balanced by savings in costs related to cancer treatment (surgery, chemotherapy, palliative care) due to CADe-related cancer prevention; Statement 1.4: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADe to support its use in clinical practice; Statement 2.1: Computer-aided diagnosis (CADx) for diminutive polyps (≤5 mm), when it has sufficient accuracy, is expected to reduce health-care costs by reducing polypectomies, pathological examinations, or both; Statement 2.2: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADx to support its use in clinical practice; Statement 3: We recommend that a broad range of high-quality cost-effectiveness research should be undertaken to understand whether AI implementation benefits populations and societies in different health-care systems.

Artificial intelligence and inflammatory bowel disease: Where are we going?

Inflammatory bowel diseases, namely ulcerative colitis and Crohn's disease, are chronic and relapsing conditions that pose a growing burden on healthcare systems worldwide. Because of their complex and partly unknown etiology and pathogenesis, the management of ulcerative colitis and Crohn's disease can prove challenging not only from a clinical point of view but also for resource optimization. Artificial intelligence, an umbrella term that encompasses any cognitive function developed by machines for learning or problem solving, and its subsets machine learning and deep learning are becoming ever more essential tools with a plethora of applications in most medical specialties. In this regard gastroenterology is no exception, and due to the importance of endoscopy and imaging numerous clinical studies have been gradually highlighting the relevant role that artificial intelligence has in inflammatory bowel diseases as well. The aim of this review was to summarize the most recent evidence on the use of artificial intelligence in inflammatory bowel diseases in various contexts such as diagnosis, follow-up, treatment, prognosis, cancer surveillance, data collection, and analysis. Moreover, insights into the potential further developments in this field and their effects on future clinical practice were discussed.