Evaluation of the Potential Utility of an Artificial Intelligence Chatbot in Gastroesophageal Reflux Disease Management

INTRODUCTION

Artificial intelligence chatbots could serve as an information resource for patients and a tool for clinicians. Their ability to respond appropriately to questions regarding gastroesophageal reflux disease is unknown.

METHODS

Twenty-three prompts regarding gastroesophageal reflux disease management were submitted to ChatGPT, and responses were rated by 3 gastroenterologists and 8 patients.

RESULTS

ChatGPT provided largely appropriate responses (91.3%), although with some inappropriateness (8.7%) and inconsistency. Most responses (78.3%) contained at least some specific guidance. Patients considered this a useful tool (100%).

DISCUSSION

ChatGPT's performance demonstrates the potential for this technology in health care, although also its limitations in its current state.

Speedometer for withdrawal time monitoring during colonoscopy: a clinical implementation trial

OBJECTIVES

Meticulous inspection of the mucosa during colonoscopy, represents a lengthier withdrawal time, but has been shown to increase adenoma detection rate (ADR). We investigated if artificial intelligence-aided speed monitoring can improve suboptimal withdrawal time.

METHODS

We evaluated the implementation of a computer-aided speed monitoring device during colonoscopy at a large academic endoscopy center. After informed consent, patients ≥18 years undergoing colonoscopy between 5 March and 29 April 2021 were examined without the use of the speedometer, and with the speedometer between 29 April and 30 June 2021. All colonoscopies were recorded, and withdrawal time was assessed based on the recordings in a blinded fashion. We compared mean withdrawal time, percentage of withdrawal time ≥6 min, and ADR with and without the speedometer.

RESULTS

One hundred sixty-six patients in each group were eligible for analyses. Mean withdrawal time was 9 min and 6.6 s (95% CI: 8 min and 34.8 s to 9 min and 39 s) without the use of the speedometer, and 9 min and 9 s (95% CI: 8 min and 45 s to 9 min and 33.6 s) with the speedometer; difference 2.3 s (95% CI: -42.3-37.7, p = 0.91). The ADRs were 45.2% (95% CI: 37.6-52.8) without the speedometer as compared to 45.8% (95% CI: 38.2-53.4) with the speedometer (p = 0.91). The proportion of colonoscopies with withdrawal time ≥6 min without the speedometer was 85.5% (95% CI: 80.2-90.9) versus 86.7% (95% CI: 81.6-91.9) with the speedometer (p = 0.75).

CONCLUSIONS

Use of speed monitoring during withdrawal did not increase withdrawal time or ADR in colonoscopy.

CLINICALTRIALS.GOV IDENTIFIER

NCT04710251.

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

BACKGROUND AND AIMS

Artificial intelligence (AI) tools aimed at improving polyp detection have been shown to increase the adenoma detection rate during colonoscopy. However, it is unknown how increased polyp detection rates by AI affect the burden of patient surveillance after polyp removal.

METHODS

We conducted a pooled analysis of 9 randomized controlled trials (5 in China, 2 in Italy, 1 in Japan, and 1 in the United States) comparing colonoscopy with or without AI detection aids. The primary outcome was the proportion of patients recommended to undergo intensive surveillance (ie, 3-year interval). We analyzed intervals for AI and non-AI colonoscopies for the U.S. and European recommendations separately. We estimated proportions by calculating relative risks using the Mantel-Haenszel method.

RESULTS

A total of 5796 patients (51% male, mean 53 years of age) were included; 2894 underwent AI-assisted colonoscopy and 2902 non-AI colonoscopy. When following U.S. guidelines, the proportion of patients recommended intensive surveillance increased from 8.4% (95% CI, 7.4%-9.5%) in the non-AI group to 11.3% (95% CI, 10.2%-12.6%) in the AI group (absolute difference, 2.9% [95% CI, 1.4%-4.4%]; risk ratio, 1.35 [95% CI, 1.16-1.57]). When following European guidelines, it increased from 6.1% (95% CI, 5.3%-7.0%) to 7.4% (95% CI, 6.5%-8.4%) (absolute difference, 1.3% [95% CI, 0.01%-2.6%]; risk ratio, 1.22 [95% CI, 1.01-1.47]).

CONCLUSIONS

The use of AI during colonoscopy increased the proportion of patients requiring intensive colonoscopy surveillance by approximately 35% in the United States and 20% in Europe (absolute increases of 2.9% and 1.3%, respectively). While this may contribute to improved cancer prevention, it significantly adds patient burden and healthcare costs.

Impact of second-generation transoral incisionless fundoplication on atypical GERD symptoms: a systematic review and meta-analysis

BACKGROUND AND AIMS

Transoral incisionless fundoplication (TIF) using the EsophyX device (EndoGastric Solutions, Inc, Redmond, Wash, USA) is a minimally invasive endoscopic fundoplication technique. Our study aimed to assess the efficacy of TIF for atypical GERD symptoms in patients with chronic or refractory GERD.

METHODS

A systematic search of 4 major databases was performed. All original studies assessing atypical GERD using a validated symptom questionnaire (the reflux symptom index [RSI]) were included. The RSI score was assessed before and after TIF at a 6- and 12-month follow-up. Data on technical success rate, adverse events, proton pump inhibitor (PPI) use, and patient satisfaction were also collected. Only TIF procedures currently in practice using the EsophyX device (ie, TIF 2.0) and TIF with concomitant hiatal hernia repair were included in the review.

RESULTS

Ten studies (564 patients) were included. At the 6- and 12- month follow-up, there was a mean reduction of 15.72 (95% confidence interval, 12.15-19.29) and 14.73 (95% confidence interval, 11.74-17.72) points, respectively, in the RSI score post-TIF, with a technical success rate of 99.5% and a pooled adverse event rate of 1%. At both time intervals, more than two-thirds of the patients were satisfied with their health condition and roughly three-fourths of the patients were off daily PPIs.

CONCLUSIONS

Our study shows that TIF using the EsophyX device is safe and effective in reducing atypical GERD symptoms at 6 and 12 months of follow-up. It improves patient-centered outcomes and can be a minimally invasive therapeutic option for patients suffering from atypical GERD symptoms on chronic medical therapy.

Deep Learning Computer-aided Polyp Detection Reduces Adenoma Miss Rate: A United States Multi-center Randomized Tandem Colonoscopy Study (CADeT-CS Trial)

BACKGROUND & AIMS

Artificial intelligence-based computer-aided polyp detection (CADe) systems are intended to address the issue of missed polyps during colonoscopy. The effect of CADe during screening and surveillance colonoscopy has not previously been studied in a United States (U.S.) population.

METHODS

We conducted a prospective, multi-center, single-blind randomized tandem colonoscopy study to evaluate a deep-learning based CADe system (EndoScreener, Shanghai Wision AI, China). Patients were enrolled across 4 U.S. academic medical centers from 2019 through 2020. Patients presenting for colorectal cancer screening or surveillance were randomized to CADe colonoscopy first or high-definition white light (HDWL) colonoscopy first, followed immediately by the other procedure in tandem fashion by the same endoscopist. The primary outcome was adenoma miss rate (AMR), and secondary outcomes included sessile serrated lesion (SSL) miss rate and adenomas per colonoscopy (APC).

RESULTS

A total of 232 patients entered the study, with 116 patients randomized to undergo CADe colonoscopy first and 116 patients randomized to undergo HDWL colonoscopy first. After the exclusion of 9 patients, the study cohort included 223 patients. AMR was lower in the CADe-first group compared with the HDWL-first group (20.12% [34/169] vs 31.25% [45/144]; odds ratio [OR], 1.8048; 95% confidence interval [CI], 1.0780-3.0217; P = .0247). SSL miss rate was lower in the CADe-first group (7.14% [1/14]) vs the HDWL-first group (42.11% [8/19]; P = .0482). First-pass APC was higher in the CADe-first group (1.19 [standard deviation (SD), 2.03] vs 0.90 [SD, 1.55]; P = .0323). First-pass ADR was 50.44% in the CADe-first group and 43.64 % in the HDWL-first group (P = .3091).

CONCLUSION

In this U.S. multicenter tandem colonoscopy randomized controlled trial, we demonstrate a decrease in AMR and SSL miss rate and an increase in first-pass APC with the use of a CADe-system when compared with HDWL colonoscopy alone.

Scoping out the future: The application of artificial intelligence to gastrointestinal endoscopy

Artificial intelligence (AI) is a quickly expanding field in gastrointestinal endoscopy. Although there are a myriad of applications of AI ranging from identification of bleeding to predicting outcomes in patients with inflammatory bowel disease, a great deal of research has focused on the identification and classification of gastrointestinal malignancies. Several of the initial randomized, prospective trials utilizing AI in clinical medicine have centered on polyp detection during screening colonoscopy. In addition to work focused on colorectal cancer, AI systems have also been applied to gastric, esophageal, pancreatic, and liver cancers. Despite promising results in initial studies, the generalizability of most of these AI systems have not yet been evaluated. In this article we review recent developments in the field of AI applied to gastrointestinal oncology.

Charting a path forward for clinical research in artificial intelligence and gastroenterology

Gastroenterology has been an early leader in bridging the gap between artificial intelligence (AI) model development and clinical trial validation, and in recent years we have seen the publication of several randomized clinical trials examining the role of AI in gastroenterology. As AI applications for clinical medicine advance rapidly, there is a clear need for guidance surrounding AI-specific study design, evaluation, comparison, analysis and reporting of results. Several initiatives are in the publication or pre-publication phase including AI-specific amendments to minimum reporting guidelines for clinical trials, society task force initiatives aimed at priority use cases and research priorities, and minimum reporting guidelines that guide the reporting of clinical prediction models. In this paper, we examine applications of AI in clinical trials and discuss elements of newly published AI-specific extensions to the Consolidated Standards of Reporting Trials and Standard Protocol Items: Recommendations for Interventional Trials statements that guide clinical trial reporting and development. We then review AI applications at the pre-trial level in both endoscopy and other subfields of gastroenterology and explore areas where further guidance is needed to supplement the current guidance available at the pre-trial level.

Preloaded 22-gauge fine-needle system facilitates placement of a higher number of fiducials for image-guided radiation therapy compared with traditional backloaded 19-gauge approach

BACKGROUND AND AIMS

Image-guided radiation therapy (IGRT) often relies on EUS-guided fiducial markers. Previously used manually backloaded fiducial needles have multiple potential limitations including safety and efficiency concerns. Our aim was to evaluate the efficacy, feasibility, and safety of EUS-guided placement of gold fiducials using a novel preloaded 22-gauge needle compared with a traditional, backloaded 19-gauge needle.

METHODS

This was a single-center comparative cohort study. Patients with pancreatic and hepatobiliary malignancy who underwent EUS-guided fiducial placement (EUS-FP) between October 2014 and February 2018 were included. The main outcome was the technical success of fiducial placement. Secondary outcomes were mean procedure time, fiducial visibility during IGRT, technical success of IGRT delivery, and adverse events.

RESULTS

One hundred fourteen patients underwent EUS-FP during the study period. Of these, 111 patients had successful placement of a minimum of 2 fiducials. Fifty-six patients underwent placement using a backloaded 19-gauge needle and 58 patients underwent placement using a 22-gauge preloaded needle. The mean number of fiducials placed successfully at the target site was significantly higher in the 22-gauge group compared with the 19-gauge group (3.53 ± .96 vs 3.11 ± .61, respectively; P = .006). In the 22-gauge group, the clinical goal of placing 4 fiducials was achieved in 78%, compared with 23% in the 19-gauge group (P < .001). In univariate analyses, gender, age, procedure time, tumor size, and location did not influence the number of successfully placed fiducials. Technical success of IGRT with fiducial tracking was high in both the 19-gauge (51/56, 91%) and the 22-gauge group (47/58, 81%; P = .12).

CONCLUSIONS

EUS-FP using a preloaded 22-gauge needle is feasible, effective, and safe and allows for a higher number of fiducials placed when compared with the traditional backloaded 19-gauge needle.

Adoption of New Technologies: Artificial Intelligence

Over the past decade, artificial intelligence (AI) has been broadly applied to many aspects of human life, with recent groundbreaking successes in facial recognition, natural language processing, autonomous driving, and medical imaging. Gastroenterology has applied AI to a vast array of clinical problems, and some of the earliest prospective trials examining AI in medicine have been in computer vision applied to endoscopy. Evidence is mounting for 2 broad areas of AI as applied to gastroenterology: computer-aided detection and computer-aided diagnosis.

Benchmarking definitions of false-positive alerts during computer-aided polyp detection in colonoscopy

BACKGROUND

The occurrence of false-positive alerts is an important outcome measure in computer-aided colon polyp detection (CADe) studies. However, there is no consensus definition of a false positive in clinical trials evaluating CADe in colonoscopy. We aimed to study the diagnostic performance of CADe based on different threshold definitions for false-positive alerts.

METHODS

A previously validated CADe system was applied to screening/surveillance colonoscopy videos. Different thresholds for false-positive alerts were defined based on the time an alert box was continuously traced by the system. Primary outcomes were false-positive results and specificity using different threshold definitions of false positive.

RESULTS

62 colonoscopies were analyzed. CADe specificity and accuracy were 93.2 % and 97.8 %, respectively, for a threshold definition of ≥ 0.5 seconds, 98.6 % and 99.5 % for a threshold definition of ≥ 1 second, and 99.8 % and 99.9 % for a threshold definition of ≥ 2 seconds.

CONCLUSION

Our analysis demonstrated how different threshold definitions of false positive can impact the reported diagnostic performance of CADe for colon polyp detection.

The single-monitor trial: an embedded CADe system increased adenoma detection during colonoscopy: a prospective randomized study

BACKGROUND

Computer-aided detection (CADe) of colon polyps has been demonstrated to improve colon polyp and adenoma detection during colonoscopy by indicating the location of a given polyp on a parallel monitor. The aim of this study was to investigate whether embedding the CADe system into the primary colonoscopy monitor may serve to increase polyp and adenoma detection, without increasing physician fatigue level.

METHODS

Consecutive patients presenting for colonoscopies were prospectively randomized to undergo routine colonoscopy with or without the assistance of a real-time polyp detection CADe system. Fatigue level was evaluated from score 0 to 10 by the performing endoscopists after each colonoscopy procedure. The main outcome was adenoma detection rate (ADR).

RESULTS

Out of 790 patients analyzed, 397 were randomized to routine colonoscopy (control group), and 393 to a colonoscopy with computer-aided diagnosis (CADe group). The ADRs were 20.91% and 29.01%, respectively (OR = 1.546, 95% CI 1.116-2.141, p = 0.009). The average number of adenomas per colonoscopy (APC) was 0.29 and 0.48, respectively (Change Folds = 1.64, 95% CI 1.299-2.063, p < 0.001). The improvement in polyp detection was mainly due to increased detection of non-advanced diminutive adenomas, serrated adenoma and hyperplastic polyps. The fatigue score for each procedure was 3.28 versus 3.40 for routine and CADe group, p = 0.357.

CONCLUSIONS

A real-time CADe system employed on the primary endoscopy monitor may lead to improvements in ADR and polyp detection rate without increasing fatigue level during colonoscopy. The integration of a low-latency and high-performance CADe systems may serve as an effective quality assurance tool during colonoscopy. www.chictr.org.cn number, ChiCTR1800018058.

Lower Adenoma Miss Rate of Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light Colonoscopy in a Prospective Tandem Study

BACKGROUND AND AIMS

Up to 30% of adenomas might be missed during screening colonoscopy-these could be polyps that appear on-screen but are not recognized by endoscopists or polyps that are in locations that do not appear on the screen at all. Computer-aided detection (CADe) systems, based on deep learning, might reduce rates of missed adenomas by displaying visual alerts that identify precancerous polyps on the endoscopy monitor in real time. We compared adenoma miss rates of CADe colonoscopy vs routine white-light colonoscopy.

METHODS

We performed a prospective study of patients, 18-75 years old, referred for diagnostic, screening, or surveillance colonoscopies at a single endoscopy center of Sichuan Provincial People's Hospital from June 3, 2019 through September 24, 2019. Same day, tandem colonoscopies were performed for each participant by the same endoscopist. Patients were randomly assigned to groups that received either CADe colonoscopy (n=184) or routine colonoscopy (n=185) first, followed immediately by the other procedure. Endoscopists were blinded to the group each patient was assigned to until immediately before the start of each colonoscopy. Polyps that were missed by the CADe system but detected by endoscopists were classified as missed polyps. False polyps were those continuously traced by the CADe system but then determined not to be polyps by the endoscopists. The primary endpoint was adenoma miss rate, which was defined as the number of adenomas detected in the second-pass colonoscopy divided by the total number of adenomas detected in both passes.

RESULTS

The adenoma miss rate was significantly lower with CADe colonoscopy (13.89%; 95% CI, 8.24%-19.54%) than with routine colonoscopy (40.00%; 95% CI, 31.23%-48.77%, P<.0001). The polyp miss rate was significantly lower with CADe colonoscopy (12.98%; 95% CI, 9.08%-16.88%) than with routine colonoscopy (45.90%; 95% CI, 39.65%-52.15%) (P<.0001). Adenoma miss rates in ascending, transverse, and descending colon were significantly lower with CADe colonoscopy than with routine colonoscopy (ascending colon 6.67% vs 39.13%; P=.0095; transverse colon 16.33% vs 45.16%; P=.0065; and descending colon 12.50% vs 40.91%, P=.0364).

CONCLUSIONS

CADe colonoscopy reduced the overall miss rate of adenomas by endoscopists using white-light endoscopy. Routine use of CADe might reduce the incidence of interval colon cancers. chictr.org.cn study no: ChiCTR1900023086.

Training a computer-aided polyp detection system to detect sessile serrated adenomas using public domain colonoscopy videos

Background  Colorectal cancer (CRC) is a major public health burden worldwide, and colonoscopy is the most commonly used CRC screening tool. Still, there is variability in adenoma detection rate (ADR) among endoscopists. Recent studies have reported improved ADR using deep learning models trained on videos curated largely from private in-house datasets. Few have focused on the detection of sessile serrated adenomas (SSAs), which are the most challenging target clinically. Methods  We identified 23 colonoscopy videos available in the public domain and for which pathology data were provided, totaling 390 minutes of footage. Expert endoscopists annotated segments of video with adenomatous polyps, from which we captured 509 polyp-positive and 6,875 polyp-free frames. Via data augmentation, we generated 15,270 adenomatous polyp-positive images, of which 2,310 were SSAs, and 20,625 polyp-negative images. We used the CNN AlexNet and fine-tuned its parameters using 90 % of the images, before testing its performance on the remaining 10 % of images unseen by the model. Results  We trained the model on 32,305 images and tested performance on 3,590 images with the same proportion of SSA, non-SSA polyp-positive, and polyp-negative images. The overall accuracy of the model was 0.86, with a sensitivity of 0.73 and a specificity of 0.96. Positive predictive value was 0.93 and negative predictive value was 0.96. The area under the curve was 0.94. SSAs were detected in 93 % of SSA-positive images. Conclusions  Using a relatively small set of publicly-available colonoscopy data, we obtained sizable training and validation sets of endoscopic images using data augmentation, and achieved an excellent performance in adenomatous polyp detection.

Regulatory considerations for artificial intelligence technologies in GI endoscopy

Artificial intelligence (AI) technologies in clinical medicine have become the subject of intensive investigative efforts and popular attention. In domains ranging from pathology to radiology, AI has demonstrated the potential to improve clinical performance and efficiency. In gastroenterology, AI has been applied on multiple fronts, with particular progress seen in the areas of computer-aided polyp detection (CADe) and computer-aided polyp diagnosis (CADx), to assist gastroenterologists during colonoscopy. As clinical evidence accrues for CADe and CADx, our attention must also turn toward the unique challenges that this new wave of technologies represent for the U.S. Food and Drug Administration and other regulatory agencies, who are tasked with protecting public health by ensuring the safety of medical devices. In this review, we describe the current regulatory pathways for AI tools in gastroenterology and the expected evolution of these pathways.

Physician sentiment toward artificial intelligence (AI) in colonoscopic practice: a survey of US gastroenterologists

Background and study aims  Early studies have shown that artificial intelligence (AI) has the potential to augment the performance of gastroenterologists during endoscopy. Our aim was to determine how gastroenterologists view the potential role of AI in gastrointestinal endoscopy. Methods  In this cross-sectional study, an online survey was sent to US gastroenterologists. The survey included questions about physician level of training, experience, and practice characteristics and physician perception of AI. Descriptive statistics were used to summarize sentiment about AI. Univariate and multivariate analyses were used to assess whether background information about physicians correlated to their sentiment. Results  Surveys were emailed to 330 gastroenterologists nationwide. Between December 2018 and January 2019, 124 physicians (38 %) completed the survey. Eighty-six percent of physicians reported interest in AI-assisted colonoscopy; 84.7 % agreed that computer-assisted polyp detection (CADe) would improve their endoscopic performance. Of the respondents, 57.2 % felt comfortable using computer-aided diagnosis (CADx) to support a "diagnose and leave" strategy for hyperplastic polyps. Multivariate analysis showed that post-fellowship experience of fewer than 15 years was the most important factor in determining whether physicians were likely to believe that CADe would lead to more removed polyps (odds ratio = 5.09; P  = .01). The most common concerns about implementation of AI were cost (75.2 %), operator dependence (62.8 %), and increased procedural time (60.3 %). Conclusions  Gastroenterologists have strong interest in the application of AI to colonoscopy, particularly with regard to CADe for polyp detection. The primary concerns were its cost, potential to increase procedural time, and potential to develop operator dependence. Future developments in AI should prioritize mitigation of these concerns.

Coeliac disease

Coeliac disease (CD) develops in genetically susceptible individuals who, in response to unclear environmental triggers, develop an immune response triggered by gluten ingestion. It is now recognised as a global disease affecting about 0.7% of the world's population. The clinical presentation ranges from malabsorption to asymptomatic individuals diagnosed by screening high-risk groups. Diagnosis requires the demonstration of small intestinal villous atrophy in the presence of circulating coeliac auto-antibodies and/or an unequivocal response to a gluten-free diet (GFD). Recent guidelines suggest that, in a subset of children, duodenal biopsies can be avoided in the presence of strict symptomatic and serological criteria. While the majority of patients respond to a GFD, up to 20% of patients with CD have persistent or recurrent symptoms. There are several aetiologies for residual or new symptoms in a patient with CD on a GFD, with inadvertent exposure to gluten being the most common. Following a GFD can be challenging for patients with CD and understanding the barriers/challenges faced by patients in maintaining a GFD is crucial for compliance. Abbreviations: AGA: anti-gliadin antibodies; Anti-DGP-ab: anti-deamidated gliadin peptide antibodies; Anti-tTG-ab: anti-tissue transglutaminase antibodies; ATD: auto-immune thyroid disorders; BMD: bone mineral density; CD: coeliac disease; DH: dermatitis herpetiformis; EMA: anti-endomysial antibodies; FDR: first-degree relatives; GFD: gluten-free diet; HbA1c: haemoglobin A1c; HLA: human leucocyte antigen; IBS: irritable bowel syndrome; LMIC: low- and middle-income countries; NPV: negative predictive value; NRCD: non-responsive coeliac disease; POCT: point-of-care tests; SDR: second-degree relatives; SIBO: small intestinal bacterial overgrowth; T1DM: type 1 diabetes mellitus; ULN: upper limit of normal.

Artificial intelligence in gastrointestinal endoscopy: The future is almost here

Artificial intelligence (AI) enables machines to provide unparalleled value in a myriad of industries and applications. In recent years, researchers have harnessed artificial intelligence to analyze large-volume, unstructured medical data and perform clinical tasks, such as the identification of diabetic retinopathy or the diagnosis of cutaneous malignancies. Applications of artificial intelligence techniques, specifically machine learning and more recently deep learning, are beginning to emerge in gastrointestinal endoscopy. The most promising of these efforts have been in computer-aided detection and computer-aided diagnosis of colorectal polyps, with recent systems demonstrating high sensitivity and accuracy even when compared to expert human endoscopists. AI has also been utilized to identify gastrointestinal bleeding, to detect areas of inflammation, and even to diagnose certain gastrointestinal infections. Future work in the field should concentrate on creating seamless integration of AI systems with current endoscopy platforms and electronic medical records, developing training modules to teach clinicians how to use AI tools, and determining the best means for regulation and approval of new AI technology.