Could immediate second-look endoscopy reduce post-endoscopic submucosal dissection bleeding?

BACKGROUND AND STUDY AIM: Gastric endoscopic submucosal dissection (ESD) is a curative treatment for gastric neoplasm. A scheduled second-look endoscopy could be performed to prevent delayed post-ESD bleeding. However, no studies on the efficacy of second-look endoscopy for the prevention of early delayed post-ESD bleeding have been conducted. So, the aim of this study was to be the first to investigate the efficacy of immediate second-look endoscopy for the prevention of post-ESD bleeding. PATIENTS AND METHODS: The 266 gastric ESD cases were included. Immediate second-look endoscopy was defined as repeated upper endoscopy soon after complete hemostasis of the ESD site and specimen fixation. Early and late delayed bleeding were classified as before or after 24 h after the ESD, respectively. RESULTS: The 262 ESD cases were enrolled and divided into three groups: the immediate second-look (n = 79), scheduled second-look (n = 86), and no second-look (n = 97). Post-ESD bleeding occurred in 19 cases (7.3%). Of these, 13 (68.4%) were early delayed post-ESD bleeding. The immediate second-look endoscopy had a lower incidence of early delayed post-ESD bleeding compared to the groups without immediate second-look endoscopy, (3.8% vs. 0.8%, p = 0.009). In a multivariate analysis, immediate second-look endoscopy significantly reduced early delayed post-ESD bleeding (OR 0.39, p = 0.022). The resected specimen area ≥ 1,000 mm2 was an independent risk factor for early delayed post-ESD bleeding (OR 8.98, p = 0.010). However, the frequency of delayed post-ESD bleeding did not differ between the three groups. CONCLUSION: Immediate second-look endoscopy after gastric ESD may prevent early delayed post-ESD bleeding under certain circumstances.

Artificial intelligence that determines the clinical significance of capsule endoscopy images can increase the efficiency of reading.

Artificial intelligence (AI), which has demonstrated outstanding achievements in image recognition, can be useful for the tedious capsule endoscopy (CE) reading. We aimed to develop a practical AI-based method that can identify various types of lesions and tried to evaluate the effectiveness of the method under clinical settings. A total of 203,244 CE images were collected from multiple centers selected considering the regional distribution. The AI based on the Inception-Resnet-V2 model was trained with images that were classified into two categories according to their clinical significance. The performance of AI was evaluated with a comparative test involving two groups of reviewers with different experiences. The AI summarized 67,008 (31.89%) images with a probability of more than 0.8 for containing lesions in 210,100 frames of 20 selected CE videos. Using the AI-assisted reading model, reviewers in both the groups exhibited increased lesion detection rates compared to those achieved using the conventional reading model (experts; 34.3%-73.0%; p = 0.029, trainees; 24.7%-53.1%; p = 0.029). The improved result for trainees was comparable to that for the experts (p = 0.057). Further, the AI-assisted reading model significantly shortened the reading time for trainees (1621.0-746.8 min; p = 0.029). Thus, we have developed an AI-assisted reading model that can detect various lesions and can successfully summarize CE images according to clinical significance. The assistance rendered by AI can increase the lesion detection rates of reviewers. Especially, trainees could improve their efficiency of reading as a result of reduced reading time using the AI-assisted model.

The etiology of potential small-bowel bleeding depending on patient's age and gender.

BACKGROUND: Whether the etiology of potential small-bowel bleeding depends on the age and gender of the patient is not yet fully understood. METHODS: A total of 1953 patients who underwent video capsule endoscopy (VCE) to evaluate potential small-bowel bleeding and were registered in the Capsule Endoscopy Nationwide Database Registry from 2003 to 2014 were eligible for this study. VCE findings and the etiology of small-bowel bleeding were analyzed by age and gender. RESULTS: The diagnostic yield of VCE was 48.4% (95% CI: 46.2%-50.6%) and the diagnosis rate of etiology of potential small-bowel bleeding was 61.4% (95% CI: 59.2%-63.6%). The etiology of potential small-bowel bleeding depends on the age and gender of the patient. Crohn's disease and small-bowel diverticular diseases were more prevalent etiology of potential small-bowel bleeding in the young adults group (< 40 years) whereas angiodysplasia was revealed to be a most common etiology in elderly group (≥ 60 years), reaching statistical significance (p<0.00152) by Bonferroni correction. CONCLUSIONS: The etiology of potential small-bowel bleeding depends on the age of the patient. Thus, an individualized lesion-specific diagnostic approach based on age might be needed for patients with potential small-bowel bleeding.