Tariq, Raseen

INTRODUCTION: Clostridioides difficile infection (CDI) presents a significant challenge in patients with inflammatory bowel disease (IBD), with high recurrence rates and complications. Predicting recurrent CDI (rCDI) in patients with IBD is crucial for implementing targeted interventions to improve patient outcomes. This study aimed to develop and validate a predictive model (RecurCDI-IBD) using supervised machine learning to identify patients with IBD at high risk of developing rCDI. METHODS: Data were collected from adult patients with IBD diagnosed with CDI between 2013 and 2021. Inclusion criteria included adult patients with a confirmed diagnosis of CDI and a history of IBD. The Gradient Boosting Machine learning model (XGBoost) was used to train a binary classification model. Feature engineering included demographic data (age and sex), clinical data (IBD subtype, medication use, and comorbidities), and laboratory data. The primary outcome was the occurrence of rCDI within 60 days of the initial CDI episode. RESULTS: The RecurCDI-IBD model achieved an accuracy of 80.05% and an Area Under the Curve of 0.88 for predicting rCDI. Key predictive features included IBD subtype, sex, specific medications (such as steroids and anti-TNF agents), and comorbidities (such as chronic pulmonary and renal disease). DISCUSSION: The RecurCDI-IBD model demonstrates good discriminatory ability with balanced precision and recall in identifying patients with IBD at higher risk for rCDI. These findings highlight the potential of data-driven approaches to support clinical risk assessment. Further studies incorporating larger and more diverse cohorts and prospective external validation are needed to confirm generalizability and optimize clinical applicability.

Lay Summary This multicenter study evaluated clinical outcomes in pregnancy for women with ulcerative colitis and an ileal pouch-anal anastomosis. Close monitoring is needed with a multidisciplinary team for management of inflammatory complications of the pouch such as pouchitis in pregnancy and postpartum.

Abstract Background The term “incomplete microscopic colitis” (MCi) has been suggested to define patients with chronic watery diarrhea not fulfilling the complete histologic criteria for MC. There are inconsistent data on the epidemiology of MCi and the optimal management of these patients. Methods A systematic search of randomized control trials (RCTs) and observational studies of adults with biopsy-proven MCi (incomplete lymphocytic colitis and collagenous colitis) was conducted using Cochrane, Medline, Scopus, and Embase from inception to May 6, 2025. Data were extracted on (1) incidence and prevalence of MCi, (2) patient features and risk factors, (3) clinical response with treatment, and (4) relapse after treatment cessation. Data were pooled using the random-effects model to calculate weighted pooled estimates and 95% confidence intervals (CIs). Results Of 136 potentially relevant publications identified, 49 passed abstract screening, and 17 studies (1 RCT and 16 observational) were included, with a total of 1370 patients with MCi (median age of 62 years and 69.6% women). The incidence rate of MCi ranged from 0.96 to 5.0 cases per 100 000 person-years. The pooled proportion of concurrent autoimmune disease with MCi was 18% (95% confidence interval [CI], 0.07-0.28; I2 = 95%), and 46% (95% CI, 0.28-0.64; I2 = 95%) were on medications associated with microscopic colitis (MC). The pooled clinical remission rate with any induction therapy was 78% (95% CI, 0.68-0.89; I2 = 81%) and 85% (95% CI, 0.72-0.98; I2 = 88%) with budesonide. Conclusions Patients with MCi share similar characteristics with full MC including demographics, risk factors, and response to therapy, indicating that the histologic criteria for MC should potentially be broadened.

Background: Clostridioides difficile infection (CDI) treated with bezlotoxumab (BEZ) has been demonstrated to have a lower recurrence rate than placebo in clinical trials. However, real-world data on BEZ’s effectiveness remain limited and heterogeneous. Objectives: To evaluate the real-world effectiveness of BEZ in preventing CDI recurrence through a single-center retrospective cohort and a meta-analysis. Design: A retrospective cohort study and a meta-analysis. Methods: A retrospective study of patients treated with BEZ from 2017 to 2021 was performed at the Mayo Clinic. Demographics, CDI diagnostics, and several prespecified risk factors were analyzed. A literature search was conducted in August 2024 utilizing the Cochrane Central Register of Controlled Trials, Embase, Medline, Scopus, and Web of Science Core Collection. Studies reporting CDI resolution rates with BEZ were included. The random-effects model described by DerSimonian and Laird was used to calculate weighted pooled resolution rates (WPR) with 95% confidence intervals (CI). We assessed heterogeneity with the inconsistency index ( I 2 ) statistic. Results: Across 28 studies and our retrospective cohort, 2639 CDI patients were analyzed. Among 1786 patients treated with BEZ, 1450 achieved clinical resolution (WPR: 81.6%, 95% CI 77.2–85.6%), with significant heterogeneity ( I ² = 77.3%). In subgroup analysis, the pooled relative risk of recurrence was 0.56 (95% CI 0.36–0.88; p < 0.01) for BEZ with SoC compared to SoC alone. A WPR of 83.3% (95% CI 75.5%–91.1%) for patients receiving BEZ with SoC was observed when compared with a WPR of 70.8% (95% CI 62.7%–78.8%) in patients receiving SoC alone on subgroup analysis. In our cohort of 47 patients, the CDI resolution rate was 72.3% (34/47). Conclusion: Our retrospective study and meta-analysis demonstrate the real-world efficacy of BEZ in reducing CDI recurrence. The higher recurrence rates in our cohort likely reflect the high-risk nature of the population, including a greater proportion of immunocompromised patients.

Introduction: Machine learning (ML) has become increasingly pivotal in health care, particularly in colorectal cancer (CRC) detection and diagnosis with the use of predictive models and artificial intelligence-assisted colonoscopies. This study evaluates the efficacy of ML models in predicting the risk for CRC and advanced colorectal polyps (ACP) before colonoscopy. Methods: A systematic literature review was conducted following PRISMA guidelines, focusing on studies using ML for CRC and ACP prediction. Data extraction regarding study type, ML methodology, quality of data, and bias assessment was in line with the CHARMS checklist. Meta-analysis was also performed to assess the performance of models for the prediction of CRC, adenoma, or both. Results: This systematic review included 14 studies with 3618 median patients (333 to 263,879). Our study demonstrated considerable heterogeneity in methodologies and outcomes, with area under the receiver operating characteristic (AUROC) ranging from 0.6 to 1. The derivation+validation cohorts showed a pooled sensitivity of 0.832 (95% CI: 0.755-0.889) and specificity of 0.802 (95% CI: 0.722-0.863), with an overall AUROC of 0.883. Conclusion: The review underscores the significant role of ML in CRC and ACP diagnosis and its routine use could efficiently direct high-risk patients to timely colonoscopies and spare the low-risk ones from unnecessary procedures. Despite the promise shown, the variability in methodologies and outcomes highlights the need for standardized approaches and further investigation in this field.

INTRODUCTION: Bile acid sequestrants (BAS) are an option for microscopic colitis (MC) refractory or intolerant to budesonide. There are inconsistent data on the prevalence of bile acid malabsorption (BAM) and utility of bile acid testing in MC. The aim of this systematic review and meta-analysis was to evaluate these outcomes. METHODS: A systematic search of randomized control trials and observational studies of adults with MC treated with BAS was conducted using MEDLINE, Embase, Cochrane, and Scopus from inception to January 22, 2024. Data were extracted on (i) prevalence of BAM, (ii) clinical response and adverse events, and (iii) recurrence after BAS discontinuation. Data were pooled using random-effects models to determine weighted pooled estimates and 95% confidence intervals (CIs). RESULTS: We included 23 studies (1 randomized control trial, 22 observational), with 1,011 patients with MC assessed for BAM and 771 treated with BAS. The pooled prevalence of BAM was 34% (95% CI 0.26–0.42, I 2 = 81%). The pooled response rate with BAS induction for all patients with MC, irrespective of BAM, was 62% (95% CI 0.55–0.70, I 2 = 71%). There was a higher pooled response rate in patients with BAM compared with those without BAM ( P < 0.0001). The pooled rate of BAS-related adverse effects was 9% (95% CI 0.05–0.14, I 2 = 58%). DISCUSSION: One-third of patients with MC had BAM, and almost two-thirds of all patients responded to BAS with limited side effects. Patients with MC and BAM were more likely to respond to therapy, supporting the value of bile acid testing.

INTRODUCTION: Despite research efforts, predicting Clostridioides difficile incidence and its outcomes remains challenging. The aim of this systematic review was to evaluate the performance of machine learning (ML) models in predicting C. difficile infection (CDI) incidence and complications using clinical data from electronic health records. METHODS: We conducted a comprehensive search of databases (OVID, Embase, MEDLINE ALL, Web of Science, and Scopus) from inception up to September 2023. Studies employing ML techniques for predicting CDI or its complications were included. The primary outcome was the type and performance of ML models assessed using the area under the receiver operating characteristic curve. RESULTS: Twelve retrospective studies that evaluated CDI incidence and/or outcomes were included. The most commonly used ML models were random forest and gradient boosting. The area under the receiver operating characteristic curve ranged from 0.60 to 0.81 for predicting CDI incidence, 0.59 to 0.80 for recurrence, and 0.64 to 0.88 for predicting complications. Advanced ML models demonstrated similar performance to traditional logistic regression. However, there was notable heterogeneity in defining CDI and the different outcomes, including incidence, recurrence, and complications, and a lack of external validation in most studies. DISCUSSION: ML models show promise in predicting CDI incidence and outcomes. However, the observed heterogeneity in CDI definitions and the lack of real-world validation highlight challenges in clinical implementation. Future research should focus on external validation and the use of standardized definitions across studies.