Using Computer Vision to Improve Endoscopic Disease Quantification in Therapeutic Clinical Trials of Ulcerative Colitis.

BACKGROUND & AIMS: Endoscopic assessment of ulcerative colitis (UC) typically reports only the maximum severity observed. Computer vision methods may better quantify mucosal injury detail, which varies among patients. METHODS: Endoscopic video from the UNIFI clinical trial (A Study to Evaluate the Safety and Efficacy of Ustekinumab Induction and Maintenance Therapy in Participants With Moderately to Severely Active Ulcerative Colitis) comparing ustekinumab and placebo for UC were processed in a computer vision analysis that spatially mapped Mayo Endoscopic Score (MES) to generate the Cumulative Disease Score (CDS). CDS was compared with the MES for differentiating ustekinumab vs placebo treatment response and agreement with symptomatic remission at week 44. Statistical power, effect, and estimated sample sizes for detecting endoscopic differences between treatments were calculated using both CDS and MES measures. Endoscopic video from a separate phase 2 clinical trial replication cohort was performed for validation of CDS performance. RESULTS: Among 748 induction and 348 maintenance patients, CDS was lower in ustekinumab vs placebo users at week 8 (141.9 vs 184.3; P < .0001) and week 44 (78.2 vs 151.5; P < .0001). CDS was correlated with the MES (P < .0001) and all clinical components of the partial Mayo score (P < .0001). Stratification by pretreatment CDS revealed ustekinumab was more effective than placebo (P < .0001) with increasing effect in severe vs mild disease (-85.0 vs -55.4; P < .0001). Compared with the MES, CDS was more sensitive to change, requiring 50% fewer participants to demonstrate endoscopic differences between ustekinumab and placebo (Hedges' g = 0.743 vs 0.460). CDS performance in the JAK-UC replication cohort was similar to UNIFI. CONCLUSIONS: As an automated and quantitative measure of global endoscopic disease severity, the CDS offers artificial intelligence enhancement of traditional MES capability to better evaluate UC in clinical trials and potentially practice.

Diffusion of an innovation: growth in video capsule endoscopy in the U.S. Medicare population from 2003 to 2019.

BACKGROUND: Video capsule endoscopy (VCE), approved by the U.S. Food and Drug Administration (FDA) in 2001, represented a disruptive technology that transformed evaluation of the small intestine. Adoption of this technology over time and current use within the U.S. clinical population has not been well described. METHODS: To assess the growth of capsule endoscopy within the U.S. Medicare provider population (absolute growth and on a population-adjusted basis), characterize the providers performing VCE, and describe potential regional differences in use. Medicare summary data from 2003 to 2019 were used to retrospectively analyze capsule endoscopy use in a multiple cross-sectional design. In addition, detailed provider summary files were used from 2012 to 2018 to characterize provider demographics. RESULTS: VCE use grew rapidly from 2003 to 2008 followed by a plateau from 2008 to 2019. There was significant variation in use of VCE between states, with up to 10-fold variation between states (14.6 to 156.1 per 100,000 enrollees in 2018). During this time, the adjusted VCE use on a population-adjusted basis declined, reflecting saturation of growth. CONCLUSIONS: Growth of VCE use over time follows an S-shaped diffusion of innovation curve demonstrating a successful diffusion of innovation within gastroenterology. The lack of additional growth since 2008 suggests that current levels of use are well matched to overall population need within the constraints of reimbursement. Future studies should examine whether this lack of growth has implications for access and healthcare inequities.

Fully automated endoscopic disease activity assessment in ulcerative colitis.

BACKGROUND AND AIMS: Endoscopy is essential for disease assessment in ulcerative colitis (UC), but subjectivity threatens accuracy and precision. We aimed to pilot a fully automated video analysis system for grading endoscopic disease in UC. METHODS: A developmental set of high-resolution UC endoscopic videos were assigned Mayo endoscopic scores (MESs) provided by 2 experienced reviewers. Video still-image stacks were annotated for image quality (informativeness) and MES. Models to predict still-image informativeness and disease severity were trained using convolutional neural networks. A template-matching grid search was used to estimate whole-video MESs provided by human reviewers using predicted still-image MES proportions. The automated whole-video MES workflow was tested using unaltered endoscopic videos from a multicenter UC clinical trial. RESULTS: The developmental high-resolution and testing multicenter clinical trial sets contained 51 and 264 videos, respectively. The still-image informative classifier had excellent performance with a sensitivity of 0.902 and specificity of 0.870. In high-resolution videos, fully automated methods correctly predicted MESs in 78% (41 of 50, κ = 0.84) of videos. In external clinical trial videos, reviewers agreed on MESs in 82.8% (140 of 169) of videos (κ = 0.78). Automated and central reviewer scoring agreement occurred in 57.1% of videos (κ = 0.59), but improved to 69.5% (107 of 169) when accounting for reviewer disagreement. Automated MES grading of clinical trial videos (often low resolution) correctly distinguished remission (MES 0,1) versus active disease (MES 2,3) in 83.7% (221 of 264) of videos. CONCLUSIONS: These early results support the potential for artificial intelligence to provide endoscopic disease grading in UC that approximates the scoring of experienced reviewers.

An emergency department-based intensive care unit is associated with decreased hospital length of stay for upper gastrointestinal bleeding.

INTRODUCTION: Upper gastrointestinal bleeding (UGIB) is associated with substantial morbidity, mortality, and intensive care unit (ICU) utilization. Initial risk stratification and disposition from the Emergency Department (ED) can prove challenging due to limited data points during a short period of observation. An ED-based ICU (ED-ICU) may allow more rapid delivery of ICU-level care, though its impact on patients with UGIB is unknown. METHODS: A retrospective observational study was conducted at a tertiary U.S. academic medical center. An ED-ICU (the Emergency Critical Care Center [EC3]) opened in February 2015. Patients presenting to the ED with UGIB undergoing esophagogastroduodenoscopy within 72 h were identified and analyzed. The Pre- and Post-EC3 cohorts included patients from 9/2/2012-2/15/2015 and 2/16/2015-6/30/2019. RESULTS: We identified 3788 ED visits; 1033 Pre-EC3 and 2755 Post-EC3. Of Pre-EC3 visits, 200 were critically ill and admitted to ICU [Cohort A]. Of Post-EC3 visits, 682 were critically ill and managed in EC3 [Cohort B], whereas 61 were critically ill and admitted directly to ICU without care in EC3 [Cohort C]. The mean interval from ED presentation to ICU level care was shorter in Cohort B than A or C (3.8 vs 6.3 vs 7.7 h, p < 0.05). More patients in Cohort B received ICU level care within six hours of ED arrival (85.3 vs 52.0 vs 57.4%, p < 0.05). Mean hospital length of stay (LOS) was shorter in Cohort B than A or C (6.2 vs 7.3 vs 10.0 days, p < 0.05). In the Post-EC3 cohort, fewer patients were admitted to an ICU (9.3 vs 19.4%, p < 0.001). The rate of floor admission with transfer to ICU within 24 h was similar. No differences in absolute or risk-adjusted mortality were observed. CONCLUSION: For critically ill ED patients with UGIB, implementation of an ED-ICU was associated with reductions in rate of ICU admission and hospital LOS, with no differences in safety outcomes.

A Deeper Look at the Small Bowel: Training Pathways in Video Capsule Endoscopy and Device-Assisted Enteroscopy.

BACKGROUND: Although there are guidelines for video capsule endoscopy (VCE) and device-assisted enteroscopy (DAE), little is known about fellowship training in these technologies. AIMS: The aims were to better characterize current small bowel endoscopy training in 3-year GI fellowship programs and 4th-year advanced endoscopy programs in the U.S. METHODS: We developed an online multiple-choice survey to assess current GI fellowship program training in small bowel endoscopy. The survey was distributed via email to GI fellowship program directors in the U.S. RESULTS: Of the 168 program directors contacted, 59 responded (response rate = 35.1%). There was no statistically significant difference in the availability of VCE or DAE between respondents and non-respondents. VCE training was universally available in 3-year training programs, with 84.8% (50/59) requiring it for fellows. The majority of 3-year GI fellows graduated with independence in VCE: 83.1% (49/59) of programs reported "most" or "all" graduates were able to read independently. DAE techniques were available in 86.4% of training programs (51/59). Training in DAE was more limited and shared between 3-year and 4th-year programs: 12.1% (7/58) of 3-year programs required training in DAE and 22.9% (8/35) of 4th-year programs required training in DAE . CONCLUSIONS: Training in VCE is widely available in U.S. GI fellowship programs, although programs have different ways of incorporating this training into the curriculum and of measuring competency. While DAE technology was available in the majority of programs, training was less frequently available, and training is shared between 3-year fellowship programs and 4th-year advanced endoscopy programs .

Family history in colonoscopy patients: feasibility and performance of electronic and paper-based surveys for colorectal cancer risk assessment in the outpatient setting.

BACKGROUND AND AIMS: Family history is crucial in stratifying patients' risk for colorectal cancer (CRC). Previous risk assessment tools developed for use in clinic or endoscopy settings have demonstrated suboptimal specificity for identifying patients with hereditary cancer syndromes. Our aim was to test the feasibility and performance of 2 family history surveys (paper and electronic) in individuals presenting for outpatient colonoscopy. METHODS: Patients presenting for outpatient colonoscopy at a tertiary care center were asked to complete a 5-question paper risk assessment survey (short paper survey) either alone or in conjunction with a second, comprehensive electronic family risk assessment survey (comprehensive tablet survey). Each subject's survey results, along with the electronic medical record, were reviewed, and 10 high-risk criteria and PREMM1,2,6 model scores (a predictive model for carrying a Lynch syndrome-associated gene mutation) were used to identify patients warranting genetic evaluation for suspected hereditary cancer syndromes. RESULTS: Six hundred patients completed the short paper survey (cohort 1), with an additional 100 patients completing both the short paper and comprehensive tablet survey (cohort 2). Using 10 high-risk criteria and/or a PREMM1,2,6 score ≥5%, we identified 10% and 9% of patients as high risk for CRC in cohorts 1 and 2, respectively. Of the 69 high-risk subjects, 23 (33%) underwent genetic evaluations and 7 (10%) carried germline mutations associated with cancer predisposition. Both patients and endoscopists reported the tools were user-friendly and helpful for CRC risk stratification. CONCLUSIONS: Systematic assessment of family history in colonoscopy patients is feasible and can help endoscopists identify high-risk patients who would benefit from genetic evaluation.

Performance of a Deep Learning Model vs Human Reviewers in Grading Endoscopic Disease Severity of Patients With Ulcerative Colitis.

Importance: Assessing endoscopic disease severity in ulcerative colitis (UC) is a key element in determining therapeutic response, but its use in clinical practice is limited by the requirement for experienced human reviewers. Objective: To determine whether deep learning models can grade the endoscopic severity of UC as well as experienced human reviewers. Design, Setting, and Participants: In this diagnostic study, retrospective grading of endoscopic images using the 4-level Mayo subscore was performed by 2 independent reviewers with score discrepancies adjudicated by a third reviewer. Using 16 514 images from 3082 patients with UC who underwent colonoscopy at a single tertiary care referral center in the United States between January 1, 2007, and December 31, 2017, a 159-layer convolutional neural network (CNN) was constructed as a deep learning model to train and categorize images into 2 clinically relevant groups: remission (Mayo subscore 0 or 1) and moderate to severe disease (Mayo subscore, 2 or 3). Ninety percent of the cohort was used to build the model and 10% was used to test it; the process was repeated 10 times. A set of 30 full-motion colonoscopy videos, unseen by the model, was then used for external validation to mimic real-world application. Main Outcomes and Measures: Model performance was assessed using area under the receiver operating curve (AUROC), sensitivity and specificity, positive predictive value (PPV), and negative predictive value (NPV). Kappa statistics (κ) were used to measure agreement of the CNN relative to adjudicated human reference cores. Results: The authors included 16 514 images from 3082 unique patients (median [IQR] age, 41.3 [26.1-61.8] years, 1678 [54.4%] female), with 3980 images (24.1%) classified as moderate-to-severe disease by the adjudicated reference score. The CNN was excellent for distinguishing endoscopic remission from moderate-to-severe disease with an AUROC of 0.966 (95% CI, 0.967-0.972); a PPV of 0.87 (95% CI, 0.85-0.88) with a sensitivity of 83.0% (95% CI, 80.8%-85.4%) and specificty of 96.0% (95% CI, 95.1%-97.1%); and NPV of 0.94 (95% CI, 0.93-0.95). Weighted κ agreement between the CNN and the adjudicated reference score was also good for identifying exact Mayo subscores (κ = 0.84; 95% CI, 0.83-0.86) and was similar to the agreement between experienced reviewers (κ = 0.86; 95% CI, 0.85-0.87). Applying the CNN to entire colonoscopy videos had similar accuracy for identifying moderate to severe disease (AUROC, 0.97; 95% CI, 0.963-0.969). Conclusions and Relevance: This study found that deep learning model performance was similar to experienced human reviewers in grading endoscopic severity of UC. Given its scalability, this approach could improve the use of colonoscopy for UC in both research and routine practice.

Characterizing intestinal inflammation and fibrosis in Crohn's disease by photoacoustic imaging: feasibility study.

The pathology of Crohn's disease (CD) is characterized by obstructing intestinal strictures because of inflammation (with high levels of hemoglobin), fibrosis (high levels of collagen), or a combination of both. The accurate characterization of the strictures is critical for the management of CD. This study examines the feasibility of characterizing intestinal strictures by Photoacoustic imaging (PAI) without extrapolation from superficial biopsies. Ex vivo normal rat colon tissue, inflammatory and fibrotic intestinal strictures in rat trinitrobenzene sulfonic acid (TNBS) model were first differentiated by a PA-US parallel imaging system. Surgically removed human intestinal stricture specimens were afterwards imaged by a multiwavelength acoustic resolution PA microscope (ARPAM). The experiment results suggest that PAI is a potential tool for the diagnosis of the diseased conditions in intestinal strictures.

TRII: A Probabilistic Scoring of Drosophila melanogaster Translation Initiation Sites.

Relative individual information is a measurement that scores the quality of DNA- and RNA-binding sites for biological machines. The development of analytical approaches to increase the power of this scoring method will improve its utility in evaluating the functions of motifs. In this study, the scoring method was applied to potential translation initiation sites in Drosophila to compute Translation Relative Individual Information (TRII) scores. The weight matrix at the core of the scoring method was optimized based on high-confidence translation initiation sites identified by using a progressive partitioning approach. Comparing the distributions of TRII scores for sites of interest with those for high-confidence translation initiation sites and random sequences provides a new methodology for assessing the quality of translation initiation sites. The optimized weight matrices can also be used to describe the consensus at translation initiation sites, providing a quantitative measure of preferred and avoided nucleotides at each position.