Malik, Sheza

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.

Abstract Background and Aims: Recent systematic reviews and meta-analyses (SRMAs) have shown inconsistent effectiveness of FMT among IBD patients. This study aimed to appraise the evidence for clinically relevant outcomes with FMT in IBD patients using published SRMAs. Methods: We searched major databases from inception through Nov 2023 to identify SRMAs assessing the effectiveness of FMT in IBD patients. Primary outcomes included clinical remission, clinical response, endoscopic remission/response, a composite endpoint, and adverse effects. We included SRMAs investigating FMT's effect in IBD patients using RCTs and observational studies data. Methodological quality and evidence certainty were assessed using AMSTAR 2 and GRADE. Results: Out of 106 citations, 16 SRMAs were included with varying study sizes (2 to 60 primary studies) and participants (112 to 1169 per SRMA). Five SRMAs assessed FMT in IBD, while 11 focused on Ulcerative Colitis (UC). Seven SRMAs included RCTs only, and nine included both RCTs and observational studies. Methodological quality was critically low in 9 SRMAs (56%) and low in 7 studies (44%). FMT showed clinical remission benefit in all 16 SRMAs, with varying certainty: 3 high, 4 moderate, 4 low, and 5 very low. Endoscopic remission/response was reported in 5 meta-analyses on UC, with 1 high, 3 moderate, and 1 very low certainty. Combined clinical remission and endoscopic response were reported in 3 SRMAs on UC, with 1 low and 2 moderate certainty. Adverse events were reported in 6 SRMAs, with 1 high, 3 moderate, 1 low, and 1 very low certainty. Conclusion: Current evidence shows potential benefits of FMT in IBD, particularly UC, supported by significant associations in 16 meta-analyses. However, poor methodological quality and variability in evidence certainty call for high-quality RCTs to strengthen the evidence.

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.