Comparative Performance of Artificial Intelligence Optical Diagnosis Systems for Leaving in Situ Colorectal Polyps

Hassan, Cesare; Sharma, Prateek; Mori, Yuichi; Bretthauer, Michael; Rex, Douglas K.; Repici, Alessandro; Spadaccini, Marco; Selvaggio, Carmelo; Antonelli, Giulio; Khalaf, Kareem; Rizkala, Tommy; Ferrara, E.C.; Savevski, Victor; Maselli, Roberta; Fugazza, Alessandro; Capogreco, Antonio; Poletti, Valeria; Ferretti, Silvia; Alkandari, Asma; Correale, Loredana

doi:10.1053/j.gastro.2022.10.021

Cited by 23 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Overall, false positives were found to impact on less than 1% of total withdrawal time. Recently, another study from the same group compared false positives from 2 different systems, with similar results [ 21 ], suggesting that the difference in the perception phase between AI and human endoscopist minimizes the negative effect of false-positive activations. That is, the human brain of a trained endoscopist effectively and quickly dismisses most false-positive activations, with no apparent negative effect on colonoscopy safety and duration.…”

Section: Cadementioning

confidence: 75%

Current and future implications of artificial intelligence in colonoscopy

Antonelli¹

2023

aog

View full text Add to dashboard Cite

Gastrointestinal endoscopy has proved to be a perfect context for the development of artificial intelligence (AI) systems that can aid endoscopists in many tasks of their daily activities. Lesion detection (computer-aided detection, CADe) and lesion characterization (computer-aided characterization, CADx) during colonoscopy are the clinical applications of AI in gastroenterology for which by far the most evidence has been published. Indeed, they are the only applications for which more than one system has been developed by different companies, is currently available on the market, and may be used in clinical practice. Both CADe and CADx, alongside hopes and hypes, come with potential drawbacks, limitations and dangers that must be known, studied and researched as much as the optimal uses of these machines, aiming to stay one step ahead of the possible misuse of what will always be an aid to the clinician and never a substitute. An AI revolution in colonoscopy is on the way, but the potential uses are infinite and only a fraction of them have currently been studied. Future applications can be designed to ensure all aspects of colonoscopy quality parameters and truly deliver a standardization of practice, regardless of the setting in which the procedure is performed. In this review, we cover the available clinical evidence on AI applications in colonoscopy and offer an overview of future directions.

show abstract

Section: Cadementioning

confidence: 75%

Current and future implications of artificial intelligence in colonoscopy

Antonelli¹

2023

aog

View full text Add to dashboard Cite

show abstract

“…82,83 The COMBO-CAD study also reported an agreement of 98.3% for both CADx systems evaluated with ESGE guidelines, although these systems did not reach the level of agreement recommended by PIVI thresholds with the USMTF guidelines. 81 In a real-world clinical validation study assessing the diagnostic performance of CADx in a clinical setting, CADx-based recommendations also met the PIVI threshold for agreement with surveillance intervals according to ESGE guidelines, but not with USMTF guidelines. 84 These studies support the use of CADx to promote the "resect and discard" strategy, at least when PIVI thresholds are evaluated against ESGE guidelines.…”

Section: Colorectal Polyps and Cancermentioning

confidence: 97%

“…In a study by Minegishi et al ., 80 the real‐time use of a CADx system when paired with endoscopist high‐confidence optical diagnosis using NBI achieved an NPV for adenomatous histology of 94.1% (95% CI 83.8–98.8%) in diminutive rectosigmoid colon polyps. The COMBO‐CAD study, 81 which was designed as a single‐center, head‐to‐head noninferiority comparison of two commercially available CADx systems, similarly demonstrated high NPVs for adenomatous histology in diminutive rectosigmoid colon polyps (97.0% and 97.7%). These studies show that CADx systems may play a role in precision endoscopy, thereby decreasing the need for resection of diminutive rectosigmoid colon polyps with predicted hyperplastic histology, which decreases the generation of GHG emissions and nonrecyclable waste associated with the production, use, and disposal of endoscopic accessories such as snares and biopsy forceps.…”

Section: Colorectal Polyps and Cancermentioning

confidence: 98%

Precision endoscopy in the era of climate change and sustainability

Ueda,

Li,

et al. 2023

J of Gastro and Hepatol

View full text Add to dashboard Cite

Global warming caused by increased greenhouse gas (GHG) emissions has a direct impact on human health. Gastrointestinal (GI) endoscopy contributes significantly to GHG emissions due to energy consumption, reprocessing of endoscopes and accessories, production of equipment, safe disposal of biohazardous waste, and travel by patients. Moreover, GHGs are also generated in histopathology through tissue processing and the production of biopsy specimen bottles. The reduction in unnecessary surveillance endoscopies and biopsies is a practical approach to decrease GHG emissions without affecting disease outcomes. This narrative review explores the role of precision medicine in GI endoscopy, such as image‐enhanced endoscopy and artificial intelligence, with a focus on decreasing unnecessary endoscopic procedures and biopsies in the surveillance and diagnosis of premalignant lesions in the esophagus, stomach, and colon. This review offers strategies to minimize unnecessary endoscopic procedures and biopsies, decrease GHG emissions, and maintain high‐quality patient care, thereby contributing to sustainable healthcare practices.

show abstract

“…More than 10 randomized controlled trials have shown that the use of AI, when compared with standard colonoscopy, reduces the miss rate for colorectal neoplasia by approximately 50%, corresponding to an approximate 30% increase in adenoma detection rate (ADR). Similarly, several large-scale prospective studies investigating AI for polyp characterization have also shown a 90%–95% NPV in identifying neoplastic change in diminutive colorectal polyps (6–10). Overall, these data indicate benefits of AI in colonoscopy in the clinical setting.…”

Section: The Pros Of Aimentioning

confidence: 97%

The Pros and Cons of Artificial Intelligence in Endoscopy

2023

Self Cite

View full text Add to dashboard Cite

The potential benefit of artificial intelligence (AI) in optimizing the quality of care provided to patients has generated significant interest among gastroenterologists. However, incorporation of AI in the clinical workflow (R1-2) is a challenge because it is not yet clear whether its implementation will lead to better outcomes for the patients, practitioners, and the healthcare system. Because new medical interventions generally have both positive and negative consequences, it is important that the rightful enthusiasm toward an innovation such as AI does not make us overlook potential downfalls. We aim to provide a balanced view on what to expect from the use of AI in endoscopy, the area where its clinical implementation is most advanced within gastroenterology. THE PROS OF AI Human pitfallsMultiple studies have shown that endoscopists have clinically relevant miss rates of gastrointestinal (GI) neoplasia and a suboptimal accuracy in the optical diagnosis of detected lesions. Recently published studies estimate a 15%-30% miss rate for colorectal polyps and Barrett neoplasia (1,2). In addition, a recent systematic analysis showed that European endoscopists had a 75% sensitivity in detecting upper GI neoplasia, whereas another study showed a 76% negative predictive value (NPV) in identifying adenomatous histology of diminutive colorectal polyps (3). The use of AI is expected to benefit these scenarios by improving operator-dependent procedures, leading to a reduction in adenoma miss rates and an increased NPV (R1-1) for rectosigmoid polyps (Table 1).

show abstract

Comparative Performance of Artificial Intelligence Optical Diagnosis Systems for Leaving in Situ Colorectal Polyps

Cited by 23 publications

References 10 publications

Current and future implications of artificial intelligence in colonoscopy

Current and future implications of artificial intelligence in colonoscopy

Precision endoscopy in the era of climate change and sustainability

The Pros and Cons of Artificial Intelligence in Endoscopy

Contact Info

Product

Resources

About