Introduction

Artificial Intelligence (AI) assisted reading in Small Bowel Capsule Endoscopy (SBCE) has recently been shown to achieve comparable and potentially superior accuracy compared to standard clinician reading. In Colon Capsule Endoscopy (CCE), AI algorithms have also demonstrated promising results. However, the extent of AI-assisted reading's advantage remains unclear, particularly regarding its performance across different polyp sizes, morphologies, locations, and other factors. A deeper understanding of these variables is crucial for optimising AI performance and facilitating its clinical integration.

Aims & Methods

This CESCAIL sub-analysis evaluates the per-polyp diagnostic accuracy of AI-assisted versus standard clinician assessment (readings) and identifies key factors influencing AI-assisted accuracy using AiSPEED^TM, the Computer-Aided Detection (CADe) system.
The CESCAIL study evaluated the diagnostic accuracy of AI-assisted CCE readings using AiSPEED™ compared to the standard readings. Standard readings were manually performed by clinicians, while AI-assisted readings incorporated an AI pre-review followed by clinician validation. A total of 1,803 polyps from 673 patients were analysed at the per-polyp level, focusing on sensitivity and positive predictive value. Factors influencing the improved accuracy of AI-assisted readings over standard clinician readings were also assessed, including polyp size, morphology, location, patient demographics (age and sex), bowel preparation quality, capsule excretion rates, comorbidities, medications, reading time, and video duration.

Results

AI-assisted reading demonstrated significantly higher sensitivity with clear superiority for smaller polyps (<10 mm) compared to larger ones (≥10 mm) (OR 2.27 vs 0.88, p<0.001) (see Table 1). While there was no observed difference in diagnostic accuracy between AI-assisted and standard clinician assessment for polyps ≥10 mm, non-inferiority was established. AI accuracy remained consistent between 6–9 mm and ≤5 mm polyps (p=0.64). The most notable improvement was observed with hyperplastic polyps (HPs) (OR 5.4, p<0.001). No significant differences were identified for pedunculated, sub-pedunculated, Lateral Spreading Tumours, or Sessile Serrated Lesions. Furthermore, AI-assisted readings were significantly more accurate for left-sided polyps than right-sided ones (OR 2.36 vs 1.66, p<0.0001), although AI-assisted reads outperformed standard reads in both locations.

Conclusion

This study highlights the performance and consistency of AI-assisted reading, particularly for detecting smaller adenomas and HPs, with notably improved accuracy in the left colon. Next-generation AI should focus on distinguishing significant from diminutive polyps and enhancing polyp characterisation, especially for right-sided lesions.

References

1. Spada C, Piccirelli S, Hassan C, Ferrari C, Toth E, Gonzalez-Suarez B, et al. AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study. Lancet Digit Health. 2024;6(5):e345-e53.

Disclosure

Hagen Wenzek serves as the CEO, Elizabeth White is the Project Manager, and Pablo Laiz is the AI software engineer at Corporate Health International, which owns the intellectual properties of AiSPEED^TM.

Introduction

The treatment of esophageal motor disorders (EMD) has historically been focused on decreasing pressure at the gastro-esophageal junction (GEJ) by disrupting muscular fibers at this level. The classic management through dilatation, botulinum toxin injection, and Heller's myotomy (HM) underwent a revolution with the advent of third-space endoscopy, offering safe access to the submucosal space and enabling peroral endoscopic myotomy (POEM).
In this prospective national multicenter study, the results of the implementation period of this technique in Spain from 2016 to the present are analyzed, examining its short, medium, and long-term outcomes. Furthermore, outcomes based on EMD, previous treatments, and other multiple variables are also investigated.

Aims & Methods

The primary aim of this study was to ascertain the clinical efficacy of POEM.
Secondary objectives included the identification of predictors of clinical success and the measurement of the incidence of post-POEM GERD and significant complications, as well as the determination of the risk factors for complications
This is a prospective multicenter study conducted across 13 hospitals in Spain. Symptomatic patients undergoing POEM for any EMD were recruited between June 2016 and February 2023. Baseline characteristics, procedural details and outcomes related to efficacy and safety during short and long-term follow-up were analyzed.

Results

A total of 441 patients were enrolled, with type II achalasia representing the most common diagnosis (62.1%). POEM was the primary treatment in 277 patients (62.8%). Clinical success data were available for 396 patients, with a success rate of 94.4% at the last available follow-up (2 years in 117 patients, 1 year in 140, <1 year in 139). A higher baseline Eckardt score was an independent risk factor for clinical failure in the long-term follow-up (p = 0.024). Symptomatic reflux occurred in 4.7% of the patients, with a significant esophagitis rate of 10.1%. Complication incidence was 9.3% (41/441), including 14 (3.2%) severe events. Older age (p = 0.025) and total procedure duration (p=0.036) were independent risk factors for complications, while mucosal injury was found to be a predictor of severe complications (p = 0.027).

Conclusion

These findings confirm the clinical efficacy and safety during the implementation phase of POEM for all EMD in Spain.

Introduction

Several Randomized Controlled Trials (RCTs) have evaluated the role of artificial intelligence (AI) Computer-Aided Detection (CADe) systems to enhance polyp detection. However, these studies have focused exclusively on locally deployed hardware-based AI systems, whereas cloud-based systems may improve the accessibility and upgrading of CADe technology. ‘CADDIE’ (Odin Vision, an Olympus company) is a cloud-based CADe system that receives the live endoscopy image stream via the hospital’s internet network, where the AI algorithm processes the images, and overlays real-time bounding boxes on the endoscopy screen to highlight suspected polyps.

Aims & Methods

This prospective RCT aimed to evaluate the efficacy and safety of the novel cloud-based CADe-system in improving polyp detection.

This international, multi-centre, parallel-group RCT was conducted across eight centres in four European countries. Participating endoscopists had a baseline of >1000 colonoscopy procedures and an adenoma detection rate (ADR) of ≥25%. Patients aged ≥40 years and at average risk for colorectal cancer undergoing screening or surveillance indications for colonoscopy were recruited. Patients were randomised in a 1:1 ratio to standard colonoscopy (SoC) or CADDIE-assisted (CADe-arm) colonoscopy. The co-primary endpoints were superiority in adenomas per colonoscopy (APC) as the efficacy endpoint, and non-inferiority for the Positive Percent Agreement (PPA), defined as the percentage of resections that are histologically confirmed adenomas, SSLs and large (>10mm) hyperplastic polyps of the proximal colon, as the safety endpoint.

Results

Overall, 22 endoscopists and 841 participants were included in the analysis. The CADe-arm significantly increased APC by 33% (0.62 vs 0.82, Ratio 1.33 [95%CI 1.06-1.67], p=0.01) and ADR (35.9% vs 43.2%, difference of 7.3% [95%CI 0.7%-13.9%], p=0.03) compared to the SoC-arm. The mean detection of sessile serrated lesions (SSLs) (0.03 vs 0.08, Ratio 3.30 [95%CI 1.41-7.57], p<0.01), large adenomas (0.04 vs 0.09; Ratio 1.93 [95%CI 1.03-3.62], p=0.04), and large polyps (0.05 vs 0.12; Ratio 2.36 [95%CI 1.33-4.17], p<0.01) also significantly improved. A higher proportion of large polyps (27.3% vs. 37.0%) and large adenomas (15.8% vs 24.2%) were non-polypoid ‘flat’ morphology in the CADe-arm compared to the SoC-arm. Other detection metrics, including neoplastic polyps per colonoscopy (0.66 vs 0.91; Ratio 1.39 [95%CI 1.12-1.73], p<0.01) and polyps per colonoscopy (1.06 vs 1.41 (Ratio 1.35 [95%CI 1.13-1.61], p<0.01), also significantly increased.

Non-inferiority in PPA was achieved (53.4% vs 53.9%; 0.5% (-5.0%,∞)), with no increase in unnecessary resections.

Conclusion

This trial demonstrates the safety and efficacy of a cloud-based CADe-system to increase endoscopists' polyp detection across multiple metrics, notably for large adenomas, large polyps, and SSLs.

Disclosure

AR, CS, LBL, RK have received medical consultancy fees from Odin Medical Ltd

Introduction

Acetaminophen (APAP) overdose is a primary cause of drug-induced liver injury (DILI). Although the inflammatory microenvironment plays a critical role in APAP-induced liver injury (AILI), its cellular interaction network and molecular regulatory mechanisms remain incompletely elucidated. Krüppel-like factor 4 (KLF4), a zinc finger transcription factor, is known to regulate monocyte differentiation, but its functional role in the AILI inflammatory microenvironment remains unclear. This study aims to investigate the regulatory effects of myeloid KLF4 deletion on the AILI microenvironment.

Aims & Methods

By integrating multidimensional omics analysis and a myeloid-specific Klf4 knockout mouse model, we dynamically dissected microenvironmental remodeling during AILI progression. Liver samples were collected for RNA sequencing, combined with single-cell transcriptomics, flow cytometry, and molecular interaction validation to clarify the KLF4-dependent cellular subpopulation interaction network. In vivo liver imaging, histology, biochemical assays, and molecular experiments were performed to validate KLF4-dependent intercellular interactions. Primary hepatocytes and hepatocyte cell lines were used for in vitro verification.

Results

Myeloid-specific KLF4 deletion led to an increase in CXCL2⁺CXCL3⁺CD24⁺ monocytes, which activated the NF-κB signaling pathway to secrete CXCL2/CXCL3 chemokines. These chemokines bound to the CXCR2 receptor on neutrophils, driving neutrophil infiltration and neutrophil extracellular traps (NETs) formation, while amplifying the TNF-α signaling pathway. Concurrently, myeloid KLF4 knockout induced enrichment of CXCL1⁺IL17RA⁺ endothelial cells. Neutrophil-derived NETs promoted endothelial phenotypic switching toward pro-inflammatory polarization, while endothelial-derived CXCL1 further recruited neutrophils, establishing a "monocyte-neutrophil-endothelial" cellular subpopulation interaction that perpetuated microenvironmental inflammation.

Conclusion

This study reveals the molecular mechanism by which KLF4 drives inflammatory cascades in the AILI microenvironment through regulation of the myeloid-endothelial interaction network. We propose therapeutic strategies targeting NETs formation or the CXCL2/CXCL3-CXCR2 axis, providing novel targets for precise intervention in AILI.