Citations

INTRODUCTION: The American College of Gastroenterology assembled a multidisciplinary task force to evaluate the current state and future direction of artificial intelligence (AI) in gastroenterology, hepatology, and endoscopy leading to the development of consensus-based recommendations for responsible AI integration in clinical practice. METHODS: A total of 32 subject-matter experts and 12 industry partners, representing diverse practice settings and expertise, conducted subgroup literature reviews across 5 key areas (endoscopy, practice management clinical applications, training and education, inflammatory bowel disease and liver disease, ethics and equity). Draft statements were developed and rated on a 5-point Likert scale using a modified Delphi process. A consensus was set at ≥70% combined agreement. Nonconsensus items were revised and revoted electronically. RESULTS: A total of 43 statements, 40 (93%) reached consensus in round 1 and the remaining 3 achieved consensus after round 2. Evidence supports computer-aided detection improving adenoma detection rate and miss rate in controlled studies, with mixed real-world impact and insufficient long-term outcomes (e.g., interval colon cancer rate). Recommendations emphasize thorough validation and reduction of bias by heterogeneous Data sets. Outside endoscopy, ambient AI scribes, natural language processing (NLP)-enabled coding, workflow optimization, and previous authorization support show potential. Training recommendations endorse a structured AI curriculum while preserving independent procedural competence to avoid deskilling. In inflammatory bowel disease and hepatology, AI could help improve diagnostic accuracy, help predict risk of disease progression, and help guide therapy. Equity, governance, and reimbursement statements call for chain-of-custody data protections, specialty-society oversight, and payment models that reward quality and cost reduction. DISCUSSION: This consensus outlines how AI can augment rather than replace clinical expertise while promoting safety, transparency, interoperability, and equity. Priorities include pragmatic and prospective trials, multi-institutional data-sharing consortia, bias mitigation, and workforce training to enable trustworthy and clinically impactful AI adoption in gastroenterology, liver, and endoscopy care.

INTRODUCTION: High-quality colonoscopy requires accurate risk stratification for surveillance per the 2020 US Multi-Society Task Force guidelines and adherence to 2024 American College of Gastroenterology/American Society for Gastrointestinal Endoscopy quality benchmarks. Both are operationally challenging in clinical practice. We developed and validated Colon-Pilot, a large language model—powered clinical decision support system using GPT-4o to automate and standardize both functions. METHODS: The system was evaluated in 2 operational modes: (i) a human-in-the-loop clinical decision support validation of surveillance recommendations for 596 colonoscopies, comparing concordance with 2020 US Multi-Society Task Force guidelines against expert consensus, and (ii) an automated administrative audit applying Colon-Pilot to 42,632 colonoscopies across the Mayo Clinic Health System to calculate 2024 American College of Gastroenterology/American Society for Gastrointestinal Endoscopy priority quality indicators. Recommendations were autogenerated unless predefined safety criteria triggered manual review. RESULTS: Colon-Pilot issued recommendations for 522 of 596 cases (87.6%) and flagged 12.4% for manual review. For automated cases, guideline-concordant accuracy was 97.5% (Cohen κ = 0.970) versus 69.7% (κ = 0.781) for original endoscopist recommendations. Discordant artificial intelligence (AI) cases (n = 13) most often recommended longer-than-appropriate intervals (62%). Applied to the enterprise data set, Colon-Pilot calculated performance exceeding 2024 targets: adenoma detection rate 49.8% (≥35%), sessile serrated lesion detection rate 17.7% (≥6%), bowel preparation adequacy 91.8% (≥90%), and cecal intubation rate 97.4% (≥95%). DISCUSSION: Colon-Pilot demonstrated high fidelity in applying surveillance guidelines and automated quality benchmarking, outperforming unassisted endoscopists in guideline adherence. By combining safety protocols with large-scale automated reporting, it offers a scalable solution for improving both efficiency and quality in colorectal cancer prevention.

Abstract Recurrence scores based on a 21-gene assay are clinically useful for predicting prognosis and chemotherapy benefit in postmenopausal node-positive breast cancer patients, but its performance in premenopausal patients is inconsistent. Here, we evaluated Ataraxis Breast RISK (ATX), an AI test that predicts recurrence risk, and compared it with the genomic assay. ATX identified high risk patients misclassified as low risk by the genomic assay and therefore may refine selection of patients for adjuvant chemotherapy.

The NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) for Vaginal Cancer outline the recommended diagnostic workup, staging considerations, and treatment options for this rare malignancy. Because vaginal cancer is uncommon and shares many biologic and clinical characteristics with cervical cancer, several management recommendations, particularly systemic therapy, are extrapolated from evidence and practices established for cervical cancer. This guideline excerpt summarizes key components of management, including diagnostic evaluation and workup, principles of staging, pathology considerations, radiation therapy principles, and primary treatment recommendations for both early-stage and advanced disease. It also details approaches to manage relapses, including locoregional recurrence and distant metastases, and provides an in-depth overview of systemic therapy recommendations for vaginal cancer.

BACKGROUND: Bicuspid aortic valve (BAV) is a frequent congenital heart defect with a high heritability. Despite this, only a limited number of genes have been associated with the disease, and the molecular mechanisms remain unexplained in most cases. This study aimed to further understand the genetic architecture of BAV. METHODS: A genome-wide association study meta-analysis including 9631 cases among 65 677 participants was performed. Genes were prioritized using transcriptomic analyses based on RNA sequencing in relevant tissues, including human fetal and adult aortic valves. The impact of the knockdown or knockout of 4 candidate genes on cardiac development was verified in zebrafish. A polygenic risk score was developed, its association with BAV was evaluated in an independent cohort, and its association with a wide range of phenotypes (n=976) was evaluated in UK Biobank (n=355 618 individuals). RESULTS: Thirty-six genomic loci were identified, including 32 that were not described previously. Among the prioritized genes, KANK2 and ERBB4 were identified as potentially causal through transcriptomic analyses, colocalization, and Mendelian randomization based on gene expression in human aortic valves (n=484), whereas PRDM6 and STRN were prioritized using similar analyses from aortic (n=326) and left ventricular tissues (n=326), respectively. Targeting 4 candidate genes ( WNT4 , LEF1 , STRN , and KANK2 ) in zebrafish led to disruption in cardiac development. A polygenic risk score was associated with an odds ratio of 2.07 (95% CI, 1.90–2.25; P =5.43×10 -62 ) per SD for BAV and significantly associated with thoracic aortic aneurysm and atrial fibrillation in UK Biobank. CONCLUSIONS: This study supports a significant polygenic contribution to BAV, where the combination of multiple common variants in genes involved in heart morphogenesis disrupts aortic valve development.

Abstract Background Cardiovascular disease (CVD) is the leading cause of death globally for both men and women, yet women remain historically underrepresented in cardiovascular clinical trials (CV trials), despite facing a disproportionately high burden of morbidity and mortality in many forms of CVD. Purpose We aim to determine the representation of women across a broad range of CV trials. Methods The participation of women in CV trials registered on ClinicalTrials.gov from 2017 to 2023 was systematically determined through the extraction of publicly available information. Data was extracted to identify the country of study, disease type, trial size, clinical intervention and age of the participants. We calculated the proportion of women and the ratio of number of females to male participants (F:M ratio) for each trial. The female participation to prevalence ratio (PPR) was estimated for each trial based on the relative prevalence of the disease by sex in the specified region. Results We identified 1,079 registered CV trials, which included 1,396,104 participants, of whom 571,641 (41.0%) were women. The median F:M ratio was significantly lower for studies on arrhythmia (0.5), coronary heart disease (CHD) (0.39), acute coronary syndrome (ACS) (0.32) and heart failure (HF) (0.51), but was higher for obesity (1.44) and pulmonary hypertension (PH) (2.86) CV trials. F:M ratio was higher for trials on lifestyle intervention (1.51) than for drug trials. PPRs were low for clinical trials on CHD (0.66), ACS (0.79), and stroke (0.74). There was a trend to increasing PPR from 2017 to 2023, p=0.056. Conclusion Representation of women in CV trials varies by disease state, region, intervention, and sponsor type. Better understanding of reasons for these differences may enable more tailored interventions to improve representation of women globally and across therapeutic areas.Figure 1 Figure 2

Abstract Background Nearly 40,000 people in the U.S. experience recurrent pericarditis with up to 90% of cases having no identifiable cause, often making the journey to diagnosis arduous. Understanding the challenges that patients and health care professionals (HCP) face will help address gaps and barriers in patient diagnosis and care. In addition, the lack of U.S. based guidelines for recurrent pericarditis clinical care, coupled with the time lapse from the last published European guideline, has created an opportunity to discover workflow solutions for U.S. based healthcare professionals. Purpose The American Heart Association’s (AHA) Addressing Recurrent Pericarditis Initiative is a three-year effort utilizing a quality improvement approach to address gaps/barriers in patient care, educate HCPs, and develop patient education resources to improve diagnosis, treatment, and quality of life. To accomplish this, the lived experiences and challenges patients face on their journey to diagnosis was integrated into the qualitative research process. Methods To assess quality improvement opportunities, the AHA engaged HCPs with recurrent pericarditis experience from 15 diverse health systems to participate in a learning collaborative strategy for quality improvement and implementation to share successful strategies, provide input on professional education topics, and participate in process mapping. Data collection strategies include 1:1 consultations, quarterly learning collaborative calls, surveys and questionnaire completion. To assess patient education needs, the AHA Market Research Team held 1-hour video interviews with ten diverse patients. Results AHA-led HCP interviews produced process maps of clinical workflows and identified opportunities for standardization to improve clinical workflow and patient outcomes (Figure 1). From these data collection methods, preliminary results include care coordination across clinical settings, exploring treatment options, standardization of follow-up cadence, and provider awareness of misdiagnoses/underdiagnosis rates. The patient interviews revealed that there is a lack of symptom recognition, persistent rate of misdiagnosis, delay in accurate diagnosis and treatment, and discrepancies in diagnosis and treatment for various demographics including female and younger adult patients (Figure 2). Conclusion(s) In Year 2 of this three-year initiative, we will continue to refine identified areas of opportunities to improve patient outcomes by creating and disseminating educational materials and launch awareness campaigns, while also producing a national education series for HCPs that provide guidance for system-level quality improvement to emphasize consistency in care and reductions in health inequities. Key findings from this study highlight the care coordination involved in the treatment of patients with recurrent pericarditis and the need to provide multidiscipline educational approaches to achieve this goal.Figure. 1 Summary of care pathway Figure. 2 Summary of patient interviews

Abstract Metabolic disorders such as obesity, type 2 diabetes, and dyslipidaemia are major drivers of cardiovascular risk and have reached epidemic levels in Western populations. Recent advances in clinical research have uncovered unexpected and often beneficial effects of pharmacological classes of metabolic drugs on cardiovascular outcomes, revealing complex interactions between metabolism and cardiac pathology. Despite their clinical efficacy, the molecular and cellular mechanisms through which many of these agents act remain only partially understood. This gap in knowledge underscores the urgent need for fundamental research that not only dissects the biology of metabolic disorders and cardiovascular disease but also reveals the mechanistic basis of existing and emerging therapies, thereby enabling rational therapeutic development. This scientific statement, developed by researchers from the European Society of Cardiology (ESC) Council on Basic Cardiovascular Science and several ESC Working Groups, provides a state-of-the-art overview of the emerging molecular and cellular pathways linking metabolic abnormalities with vascular and cardiac disease. By illuminating these critical connections and unresolved questions, this article aims to catalyse innovation in the prevention and management of cardiovascular disease in the context of metabolic dysfunction and to suggest new directions for future research.

ABSTRACT The goal of this radiomic analysis is to quantify the sensitivity of radiomic features on computed tomography (CT) image pre‐processing parameters and use machine learning (ML) techniques to identify the radiomic features that are highly predictive of shoulder arthroplasty outcomes. An ML framework auto‐segmented 3D masks of the deltoid muscle and scapula bone from pre‐operative CT images of 1949 primary anatomic total shoulder arthroplasty (aTSA)/reverse total shoulder arthroplasty (rTSA) patients. Radiomic features were extracted after various image pre‐processing protocols and assessed for reproducibility. The radiomic features deemed robust to image pre‐processing were used to train ML predictive outcomes models. Feature importance data were rank‐ordered to identify the radiomic features that were highly predictive of pain, motion, and function before and after aTSA/rTSA. A sensitivity analysis identified 37 deltoid muscle and 38 scapular bone radiomic features that were robust, reproducible, and unique across image pre‐processing parameters. The most predictive deltoid muscle radiomic measurements were normalized volume, elongation, flatness, fat percentage, sphericity, and max 2D diameter column. The most predictive scapular bone radiomic measurements were flatness, sphericity, elongation, max 2D diameter column, and max 2D diameter slice. Radiomic data of the deltoid and scapula were highly predictive of pain, motion, and function before and after aTSA and rTSA. Radiomic data were more predictive than patient comorbidities, diagnosis, and implant type/size data, but less predictive than pre‐operative active range of motion measurements and patient reported outcome measures, 3D measurements from planning software, or patient demographic data. Future work is required to clinically validate these radiomic features before they can be deployed in clinical decision support tools. Level of Evidence Level III, Retrospective Comparative Outcome Study.