BACKGROUND AND AIMS:Artificial intelligence (AI) is increasingly being applied in various fields of medicine, including inflammatory bowel diseases (IBD). This systematic review, conducted as part of the ECCO 9th Scientific Workshop on AI in IBD, explores AI applications in multiomics precision medicine, large language models (LLMs) for textual tasks, and utilization of wearable and remote care technologies. METHODS:A comprehensive systematic analysis of the literature was undertaken, emphasizing three topics: multiomics predictive models in IBD; natural language processing (NLP) and LLMs for clinical practice, research and patient communication; and the role of remote monitoring and wearable devices. RESULTS:Key areas of promise include the implementation of NLP and LLMs for case identification and differentiation, tracking disease activity, pharmacovigilance, quality assurance, and patient support. Multiomic approaches, integrating genomics, transcriptomics, proteomics, metabolomics, and metagenomics, show potential for developing more accurate diagnostic and risk prediction models and improving treatment response prediction and detection of actionable drug targets for future therapeutics. Wearables and remote monitoring technologies can transform IBD management from episodic assessments to continuous, less biased tracking of patient-reported outcomes and physiological biomarkers. CONCLUSIONS:While AI and multiomics approaches hold substantial promise for advancing IBD management and research, further refinement is necessary to ensure content validity and address safety concerns, thereby allowing integration of AI into clinical workflows and safeguarding of data privacy. Future research should prioritize the integration of diverse omic data, conduct of longitudinal studies, and validation in large and diverse cohorts.

In this review, a comprehensive overview of the current state of artificial intelligence (AI) research in inflammatory bowel disease (IBD) diagnostics in the domains of endoscopy, radiology, and histology is presented. Moreover, key considerations for the development of AI algorithms in medical image analysis are discussed. AI presents a potential breakthrough in real-time, objective, and rapid endoscopic assessment, with implications for predicting disease progression. It is anticipated that, by harmonizing multimodal data, AI will transform patient care through early diagnosis, accurate patient profiling, and therapeutic response prediction. The ability of AI in cross-sectional medical imaging to improve diagnostic accuracy, automate and enable objective assessment of disease activity, and predict clinical outcomes highlights its transformative potential. AI models have consistently outperformed traditional methods of image interpretation, particularly in complex areas such as differentiating IBD subtypes, identifying disease progression, and complications. The use of AI in histology is a particularly dynamic research field. Implementation of AI algorithms in clinical practice is still lagging, a major hurdle being the lack of a digital workflow in many pathology institutes. Adoption is likely to start with implementation of automatic disease activity scoring. Beyond matching pathologist performance, algorithms may teach us more about the pathophysiology of IBD. While AI is set to substantially advance IBD diagnostics, various challenges such as heterogeneous datasets, retrospective designs, and assessment of different endpoints must be addressed. Implementation of novel standards of reporting may drive an increase in research quality and overcome these obstacles.

In this narrative review we present the current status of developments in artificial intelligence (AI) in the field of inflammatory bowel disease (IBD) surgery. We lay the foundations for how IBD surgery can implement the potential opportunities offered by AI technology. The main areas of potential utility are in the areas of surgical training, risk prediction in the pre-, intra-, and postoperative period in IBD patients undergoing surgery, and in IBD surgical research. We need to be mindful of the potential challenges in implementation and acceptability of these technological advances and put in mitigating measures to ensure transparency and equitable access. Global collaboration will be the cornerstone for such ventures.

With the rapid growth of artificial intelligence (AI) applications in the field of inflammatory bowel disease (IBD), an increasing number of regulatory and methodological considerations have become apparent. Currently, there remains much uncertainty and limited experience in the field of IBD regarding some of the regulatory and methodological pitfalls to be considered when developing and deploying AI applications for positive clinical and health system impact. Accordingly, an expert panel was convened by the European Crohn's and Colitis Organisation to review the published literature and provide an overview of key regulatory aspects for the application of AI in IBD. This article discusses and, where possible, provides guidance on key methodological and regulatory considerations for AI in IBD. Topics covered include: potential clinical application-focused algorithm design; ethical, moral and legal considerations; regulatory agency perspectives; an overview of regulatory submission and consideration of reimbursement. By providing clinicians with a primer to key regulatory and methodological considerations, we hope to accelerate knowledge translation and implementation of AI-enabled digital health innovations in clinical practice and ultimately improve outcomes for people living with and caring for those living with IBD.

The expanding portfolio of targeted therapies for ulcerative colitis (UC) suggests that a more precise approach to defining disease activity will aid clinical decision-making. This prospective study used genome-wide microarrays to characterize gene expression in biopsies from the most inflamed colon segments from patients with UC and analyzed associations between molecular changes and short-term outcomes while on standard-of-care treatment. We analyzed 141 biopsies—128 biopsies from 112 UC patients and 13 biopsies from eight inflammatory bowel disease unclassified (IBDU) patients. Endoscopic disease was associated with expression of innate immunity transcripts, e.g. complement factor B (CFB); inflammasome genes (ZBP1 and PIM2); calprotectin (S100A8 and S100A9); and inflammation-, injury-, and innate immunity-associated pathway analysis terms. A cross-validated molecular machine learning classifier trained on the endoscopic Mayo subscore predicted the endoscopic Mayo subscore with area-under-the-curve of 0.85. A molecular calprotectin transcript score showed strong associations with fecal calprotectin and the endoscopic Mayo subscore. Logistic regression models showed that molecular features (e.g. molecular classifier and molecular calprotectin scores) improved the prediction of disease progression over conventional, clinical features alone (e.g. total Mayo score, fecal calprotectin, physician global assessment). The molecular features of UC showed strong correlations with disease activity and permitted development of machine-learning predictive disease classifiers that can be applied to expanded testing in diverse cohorts.

Ustekinumab dose escalation (DE) may be an effective strategy to recapture clinical response in patients with ulcerative colitis (UC). The aim of this study was to assess the real-world long-term effectiveness and safety outcomes following ustekinumab DE in patients with moderate-to-severe UC. This multicenter retrospective cohort study included patients with moderate-to-severe UC who received at least one IV induction ustekinumab dose between January 2016 and November 2021. We compared ustekinumab DE to no DE, examining clinical, biochemical, and endoscopic disease outcomes. The primary endpoint was corticosteroid-free clinical remission (partial Mayo score ≤ 2 without systemic corticosteroids) at the end of follow-up. Cox proportional hazards regression analysis was performed for factors associated with time to DE, and a Kaplan–Meier plot was created for visualizing drug persistence probabilities. We enrolled 121 patients. Eighty-one patients (67

Imaging is crucial to assess disease extent, activity, and outcomes in inflammatory bowel disease (IBD). Artificial intelligence (AI) image interpretation requires automated exploitation of studies at scale as an initial step. Here we evaluate natural language processing to classify Crohn's disease (CD) on CTE. From our population representative IBD registry a sample of CD patients (male: 44.6%, median age: 50 IQR37-60) and controls (n = 981 each) CTE reports were extracted and split into training- (n = 1568), development- (n = 196), and testing (n = 198) datasets each with around 200 words and balanced numbers of labels, respectively. Predictive classification was evaluated with CNN, Bi-LSTM, BERT-110M, LLaMA-3.3-70B-Instruct and DeepSeek-R1-Distill-LLaMA-70B. While our custom IBDBERT finetuned on expert IBD knowledge (i.e. ACG, AGA, ECCO guidelines), outperformed rule- and rationale extraction-based classifiers (accuracy 88.6% with pre-tuning learning rate 0.00001, AUC 0.945) in predictive performance, LLaMA, but not DeepSeek achieved overall superior results (accuracy 91.2% vs. 88.9%, F1 0.907 vs. 0.874).

We detect and interactively visualize occurrence, frequency, sequence, and clustering of extraintestinal manifestations (EIM) and associated immune disorders (AID) in 30,334 inflammatory bowel disease (IBD) patients (Crohn’s disease (CD) n = 15924, ulcerative colitis (UC) n = 11718, IBD unclassified, IBD-U n = 2692, 52% female, median age 40 years (IQR: 25)) with artificial intelligence (AI). 57% (CD > UC 60% vs. 54%, p < 0.00001) had one or more EIM and/or AID. Mental, musculoskeletal and genitourinary disorders were most frequently associated with IBD: 18% (CD vs. UC 19% vs. 16%, p < 0.00001), 17% (CD vs. UC 20% vs. 15%, p < 0.00001) and 11% (CD vs. UC 13% vs. 9%, p < 0.00001), respectively. AI detected 4 vs. 5 vs. 5 distinct EIM/AID communities with 420 vs. 396 vs. 467 nodes and 11,492 vs. 9116 vs. 16,807 edges (links) in CD vs. UC vs. IBD, respectively. Our newly developed interactive free web app shows previously unknown communities, relationships, and temporal patterns—the diseasome and interactome.

Background Evaluating small bowel Crohn’s disease (SBCD) often relies on cross-sectional imaging (eg, computed tomography enterography [CTE]) and small bowel endoscopy (eg, balloon-assisted enteroscopy [BAE]). The accuracy of CTE for evaluating SBCD compared to BAE remains unclear and is assessed in this study. Methods This single-centre retrospective study included patients with SBCD who underwent both CTE and BAE within 6 months. Findings of active inflammation, long-segment disease, skip-segments, and presence of both strictures and high-grade strictures (HGS) were extracted from CTE and BAE reports and analyzed using BAE as the reference standard. Results Sixty-three CTE and BAE pairings were identified. CTE was sensitive for assessing active inflammation (80.0%) and all strictures (92.1%) and specific for long-segment inflammation (95.0%) and HGS (87.2%). Sensitivity was low for HGS (60.9%) and long-segment inflammation (50.0%), with poor specificity for all strictures (68.4%). In surgically naïve bowel, accuracy improved for active inflammation (sensitivity: 83.3%, specificity: 100%) and worsened for HGS (sensitivity: 42.9%, specificity: 84.2%). In postsurgical bowel, CTE sensitivity for HGS improved to 68.8%. Conclusion Computed tomography enterography accurately detected active inflammation and fibrostenotic disease but may not be sufficient to rule out clinically significant findings such as HGS. The accuracy of CTE varied between surgically naïve and postsurgical bowel. CTE remains an important modality for evaluation of SBCD and should be used in combination with BAE when clinical discrepancy arises.

Background: Despite recent emerging literature involving the utility of endoscopic balloon dilation (EBD) of strictures via balloon-assisted endoscopy (BAE), specifically regarding the management of Crohn’s disease (CD), the optimal clinical approach with balloon systems has been largely neglected in academic literature. Objectives: This study assesses the intra-procedural success and safety of EBD via BAE for small bowel CD strictures while detailing our clinical approach and technique. Secondarily, we compare the single-balloon endoscope (SBE) and double-balloon endoscope (DBE) systems for EBD-related outcomes. Design: Retrospective consecutive patient cohort analysis. Methods: We retrospectively assessed a consecutive small bowel CD patient cohort undergoing BAE at the University of Alberta Hospital endoscopy unit from 2013 to 2020. The primary endpoint discerned the safety and immediate success rate of EBD during endoscopy, and comparisons of the dilation parameters and efficacy of SBE versus DBE were assessed as secondary outcomes. Results: During the study period, 87 patients (44 male) with a mean age of 56 ± 14.7 years underwent 179 endoscopic procedures (92 DBE and 87 SBE). Of 358 strictures encountered, 320 (89.4%) were successfully dilated and traversed. The mean maximum dilation diameter was 15.76 ± 2.10 mm. There were no perforations or major adverse events. Conclusion: EBD via BAE is a safe procedure in small bowel CD with a high intraprocedural success rate. Overall, SBE had a higher success rate in traversing strictures before and after dilation using our technique. This analysis is limited by the retrospective nature of our study and must be balanced against the inherent benefits of the DBE system. Keywords balloon-assisted , Crohn’s disease , endoscopy , small bowel , stricture dilation

Abstract Background Darvadstrocel (DVS), a suspension of expanded allogeneic adipose-derived mesenchymal stem cells, is approved for the treatment of complex Crohn’s perianal fistulas (CPF). INSPIRE (EUPAS24267) is a European observational post-approval study evaluating real-world effectiveness and safety of DVS in patients with complex CPF for up to 36 months. Here we report preliminary clinical and safety outcomes from INSPIRE. Methods Patients with complex CPF who had received DVS according to local standard practice were eligible to enrol. Clinical response (closure of ≥50% of external openings [EOs]) and clinical remission (closure of all EOs) of DVS-treated fistulas that were draining at baseline, were evaluated in the all-treated (AT; received ≥1 dose of DVS with an evaluation for fistula response after 6 months) and per-protocol (PP; received DVS as per label-approved guidelines) cohorts. Treatment-emergent adverse events (TEAEs), serious TEAEs and AEs of special interest were reported for the safety cohort (all patients treated with DVS). Results As of April 2023, 652 patients had enrolled (Table 1). Complete data to evaluate 12-month clinical response and remission were available for 134 (AT cohort) and 124 (PP cohort) patients, of whom 79.9% (AT, n = 107) and 79.8% (PP, n = 99) had a clinical response and 76.1% (AT, n = 102) and 76.6% (PP, n = 95) had clinical remission (Figure 1). From baseline to Month 12, there was a decrease in the mean (standard deviation [SD]) Perianal Disease Activity Index score (–3.5 [3.3]; n/N = 96/302 and –3.7 [3.2]; n/N = 89/249) and a decrease in the mean (SD) Harvey–Bradshaw Index for Crohn’s disease activity (-0.3 [2.8]; n/N = 102/302 and -0.4 [2.9]; n/N = 95/249) in the AT and PP cohorts, respectively. Complete safety data were available for 619 patients (median [min–max] follow-up 480 [6–1595]) days. Overall, 26% (n = 162) had ≥1 TEAE and 10% (n = 63) ≥1 serious TEAE. The most frequent TEAEs were anal abscess (6.9%), COVID-19 (1.9%) and proctalgia (1.1%). No deaths were reported. One breast cancer lymph node metastasis and one ovarian epithelial cancer were reported; both events were confounded by immunosuppressant treatment and were not considered related to DVS treatment. Conclusion These preliminary data are consistent with the pivotal ADMIRE-CD study and demonstrate a single dose of DVS in patients with complex CPF is associated with positive clinical outcomes in up to 80% of patients, and a favourable safety profile, both of which are maintained after 12 months. The inherent limitations of registry-based studies mean these data should be interpreted with caution. However, the ongoing INSPIRE study will provide longer follow-up data to confirm these observations with respect to any study limitations.

Background Clinical decision support systems (CDSSs) embedded in electronic medical records (EMRs), also called electronic health records, have the potential to improve the adoption of clinical guidelines. The University of Alberta Inflammatory Bowel Disease (IBD) Group developed a CDSS for patients with IBD who might be experiencing disease flare and deployed it within a clinical information system in 2 continuous time periods. Objective This study aims to evaluate the impact of the IBD CDSS on the adherence of health care providers (ie, physicians and nurses) to institutionally agreed clinical management protocols. Methods A 2-period interrupted time series (ITS) design, comparing adherence to a clinical flare management protocol during outpatient visits before and after the CDSS implementation, was used. Each interruption was initiated with user training and a memo with instructions for use. A group of 7 physicians, 1 nurse practitioner, and 4 nurses were invited to use the CDSS. In total, 31,726 flare encounters were extracted from the clinical information system database, and 9217 of them were manually screened for inclusion. Each data point in the ITS analysis corresponded to 1 month of individual patient encounters, with a total of 18 months of data (9 before and 9 after interruption) for each period. The study was designed in accordance with the Statement on Reporting of Evaluation Studies in Health Informatics (STARE-HI) guidelines for health informatics evaluations. Results Following manual screening, 623 flare encounters were confirmed and designated for ITS analysis. The CDSS was activated in 198 of 623 encounters, most commonly in cases where the primary visit reason was a suspected IBD flare. In Implementation Period 1, before-and-after analysis demonstrates an increase in documentation of clinical scores from 3.5% to 24.1% ( P <.001), with a statistically significant level change in ITS analysis ( P =.03). In Implementation Period 2, the before-and-after analysis showed further increases in the ordering of acute disease flare lab tests (47.6% to 65.8%; P <.001), including the biomarker fecal calprotectin (27.9% to 37.3%; P =.03) and stool culture testing (54.6% to 66.9%; P =.005); the latter is a test used to distinguish a flare from an infectious disease. There were no significant slope or level changes in ITS analyses in Implementation Period 2. The overall provider adoption rate was moderate at approximately 25%, with greater adoption by nurse providers (used in 30.5% of flare encounters) compared to physicians (used in 6.7% of flare encounters). Conclusions This is one of the first studies to investigate the implementation of a CDSS for IBD, designed with a leading EMR software (Epic Systems), providing initial evidence of an improvement over routine care. Several areas for future research were identified, notably the effect of CDSSs on outcomes and how to design a CDSS with greater utility for physicians. CDSSs for IBD should also be evaluated on a larger scale; this can be facilitated by regional and national centralized EMR systems.

Our traditional approach to diagnosis, prognosis, and treatment, can no longer process and transform the enormous volume of information into therapeutic success, innovative discovery, and health economic performance. Precision health, i.e., the right treatment, for the right person, at the right time in the right place, is enabled through a learning health system, in which medicine and multidisciplinary science, economic viability, diverse culture, and empowered patient’s preferences are digitally integrated and conceptually aligned for continuous improvement and maintenance of health, wellbeing, and equity. Artificial intelligence (AI) has been successfully evaluated in risk stratification, accurate diagnosis, and treatment allocation, and to prevent health disparities. There is one caveat though: dependable AI models need to be trained on population-representative, large and deep data sets by multidisciplinary and multinational teams to avoid developer, statistical and social bias. Such applications and models can neither be created nor validated with data at the country, let alone institutional level and require a new dimension of collaboration, a cultural change with the establishment of trust in a precompetitive space. The Data for Health (#DFH23) conference in Berlin and the Follow-Up Workshop at Harvard University in Boston hosted a representative group of stakeholders in society, academia, industry, and government. With the momentum #DFH23 created, the European Health Data Space (EHDS) as a solid and safe foundation for consented collaborative health data use and the G7 Hiroshima AI process in place, we call on citizens and their governments to fully support digital transformation of medicine, research and innovation including AI.

The impact of ustekinumab (UST) on mucosal- and fistula healing and extraintestinal manifestations (EIM) in Crohn’s disease (CD) were not fully elucidated in the registration trials. In this prospective, multicenter study (EudraCT number: 2017-005151-83) we evaluated the German label real-world-effectiveness of UST to achieve the primary endpoint of combined clinical and endoscopic response at week 52 and several secondary endpoints. Of 79 screened we enrolled 52 patients (female n = 28, bionaïve n = 13, biologic n = 39). At week 52 (per protocol analysis), 52% (n = 13/25) of patients achieved the primary endpoint [50% (n = 3/6) in the bionaïve, 45.5% (n = 5/11) biologic, 62.5% (n = 5/8 ) multiple biologics cohorts, respectively with age as independent predictor [OR 95% CI 0.933 (0.873, 0.998) p = 0.043], 60% (n = 15/25) achieved endoscopic response [50% (n = 3/6) in the bionaïve, 54.5% (n = 6/11) biologic, 75% (n = 6/8) multiple biologics cohorts, respectively], 36% (n = 9/25) achieved endoscopic remission [50% (n = 3/6) in the bionaïve, 27.3% (n = 3/11) biologic, 37.5% (n = 3/8) multiple biologics cohorts, respectively], 48% (n = 12/25) achieved mucosal healing [50% (n = 3/6) in the bionaïve, 36.4% (n = 4/11) biologic, 62.5% (n = 5/8) multiple biologics cohorts, respectively]. All achieved a fistula response and 33.3% (n = 1/3) in the multiple biologics group fistula remission at week 52. EIM decreased (week 0 28.2% vs. week 52 8%). CRP, FCP, PRO-2, EQ-5D-5L improved throughout. 36 patients (69.2%) experienced ≥ 1 treatment emergent adverse event, in 8 (15.4%) cases rated as severe and in 5 (9.6%) leading to UST discontinuation, but no very severe events or deaths. The effectiveness of UST was better than in the registration trials.

Abstract Background Tofacitinib is an oral, small molecule Janus kinase inhibitor for the treatment of ulcerative colitis (UC). Patients with inflammatory bowel disease are susceptible to Clostridium difficile infection (CDI). Here, we evaluate CDI in the tofacitinib UC clinical program. Methods Events from 4 randomized, placebo-controlled studies (phase [P] 2 or P3 induction [NCT00787202; NCT01465763; NCT01458951], P3 maintenance [NCT01458574]) and an open-label, long-term extension (OLE) study (NCT01470612), were analyzed as 3 cohorts: Induction (P2/P3 induction), Maintenance (P3 maintenance), and Overall (patients receiving tofacitinib 5 or 10 mg twice daily [BID] in P2, P3, and OLE studies; including final data from the OLE study, as of August 24, 2020). Proportions and incidence rates (unique patients with events per 100 patient-years of exposure) of CDI were evaluated. Results The overall cohort comprised 1157 patients who received ≥1 dose of tofacitinib 5 or 10 mg BID, with a total of 2814.4 patient-years of tofacitinib exposure and up to 7.8 years of treatment. A total of 82.6% of patients received predominantly tofacitinib 10 mg BID. In the induction, maintenance, and overall cohorts, 3 (2 tofacitinib treated, 1 placebo treated), 3 (all placebo treated), and 9 patients had CDI, respectively; the overall cohort incidence rate was 0.31 (95% confidence interval, 0.14-0.59). CDI were all mild–moderate in severity and resolved with treatment in 8 patients. Six of 9 patients continued tofacitinib treatment without interruption. Two patients had events reported as serious due to hospitalization. Two patients were receiving corticosteroids when the CDI occurred. Conclusion CDIs among patients with UC receiving tofacitinib were infrequent, cases were mild–moderate in severity, and most resolved with treatment.

Abstract Background Crohn’s disease (CD) is a chronic inflammatory condition which can affect the entire gastrointestinal tract with a wide variety of potential complications which may require endoscopic or surgical interventions. Small bowel CD beyond the reach of standard endoscopy poses a diagnostic obstacle and relies on cross sectional imaging ─ such as computed tomography enterography (CTE) ─ and balloon assisted endoscopy (BAE). BAE is the current diagnostic gold standard allowing for direct mucosal visualization as well as therapeutic capabilities; however, remains limited by access, cost, and requires specialized training. Alternatively, CTE in small bowel in CD is widely available, and less invasive than BAE. The diagnostic accuracy of CTE against the gold standard of BAE remains unclear. Purpose We aim to assess the sensitivity and specificity of CTE vs BAE in the diagnosis and evaluation of small bowel CD. Method Patients with an established diagnosis of Crohn’s disease who underwent a CTE and a BAE within 6 months between 2011 and 2018 were reviewed. Relevant findings of active inflammation (defined by mural hyperenhancement and thickening), long-segment disease (≥ 15 cm active disease), skip-segments, number of strictures, and presence of high-grade strictures (defined on BAE as inability to traverse with scope prior to dilation and on CTE as prestenotic luminal dilation ≥3cm and fecalization) were extracted from both reports and images of CTE and BAE by two independent reviewers. Sensitivity and specificity for each finding on CTE was calculated using BAE as the gold-standard diagnostic test. Result(s) A total of 42 patients with 65 corresponding CTE and BAE were identified between 2011 and 2018. CTE was found to be most sensitive for assessing presence of active inflammation and number of strictures at 75.6% [95% CI, 60.5-87.1%] and 71.4% [95% CI, 55.4-84.3], respectively. CTE was highly specific for findings of long-segment inflammation, skip lesions, number of strictures, and high-grade stricture with a specificity of 89.3% [95% CI, 78.1-96.0], 74.1% [95%, 67.2-94.7], 100% [97.5% CI, 73.5-100], and 84.4% [95% CI, 67.2-94.7] respectively. CTE showed poor specificity for active inflammation 45.0% [23.1-68.5%], and poor sensitivity for high grade strictures 54.5% [36.4-71.9] and skip lesions 54.5% [23.4-83.3] Image Conclusion(s) CTE is relatively sensitive in detecting active inflammation and number of strictures compared to BAE, but showed suboptimal sensitivity in detecting long segment inflammation, skip lesions, and high-grade strictures. CTE showed high specificity in identification of long segment inflammation, number of strictures, and high-grade strictures, but not active inflammation overall. CTE and BAE are complementary to one another and based utilized in combination to improve diagnostic accuracy. Future directions include prospective validation prospective studies to validate the results of this study looking at a broader population of Crohn’s disease patients. Please acknowledge all funding agencies by checking the applicable boxes below None Disclosure of Interest None Declared

Supplementary Table 1 from Systematic High-Content Proteomic Analysis Reveals Substantial Immunologic Changes in Colorectal Cancer

OBJECTIVES:The tracking and documentation of procedures in gastrointestinal endoscopy including therapeutic interventions is an essential but challenging process. The University of Alberta has developed a smartphone app to help facilitate this task. This study evaluated the functionality, usefulness, and user satisfaction of this app.METHODS:Four Gastroenterology (GI) residents and two therapeutic endoscopy fellows participated in the study. The trainees submitted all their data into the app from the procedures in which they participated hands-on for one year, data was collected and analyzed on the app and the website associated with it.RESULTS:Trainees were able to register the procedures immediately after each procedure without difficulty, this data was available to be reviewed at anytime in the app and associated website. Furthermore, the data collected was able to be transformed into tables and graphs on the app website. The total number of procedures and therapeutic interventions performed were easily accessed in the app and website at anytime. The app facilitated the calculation of the cecal intubation rate in colonoscopy and the cannulation rate in ERCP for the therapeutic endoscopy trainee. Trainees reported excellent experience with the app capabilities.CONCLUSIONS:A novel smartphone app was useful in collecting meaningful data submitted by gastrointestinal endoscopy trainees, furthermore, through an associated website, it was capable to create graphs and tables to show and facilitate the calculation of meaningful data such as key performance indicators.