Capsule endoscopy (CE) quality control requires an objective scoring system to evaluate the preparation of the small bowel (SB). We propose a deep learning algorithm to calculate SB cleansing scores ...and verify the algorithm’s performance. A 5-point scoring system based on clarity of mucosal visualization was used to develop the deep learning algorithm (400,000 frames; 280,000 for training and 120,000 for testing). External validation was performed using additional CE cases (n = 50), and average cleansing scores (1.0 to 5.0) calculated using the algorithm were compared to clinical grades (A to C) assigned by clinicians. Test results obtained using 120,000 frames exhibited 93% accuracy. The separate CE case exhibited substantial agreement between the deep learning algorithm scores and clinicians’ assessments (Cohen’s kappa: 0.672). In the external validation, the cleansing score decreased with worsening clinical grade (scores of 3.9, 3.2, and 2.5 for grades A, B, and C, respectively, p < 0.001). Receiver operating characteristic curve analysis revealed that a cleansing score cut-off of 2.95 indicated clinically adequate preparation. This algorithm provides an objective and automated cleansing score for evaluating SB preparation for CE. The results of this study will serve as clinical evidence supporting the practical use of deep learning algorithms for evaluating SB preparation quality.
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.
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.
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 mm
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.
Immediate second-look endoscopy after gastric ESD may prevent early delayed post-ESD bleeding under certain circumstances.
Many patients with ulcerative colitis (UC) in clinical remission frequently complain of bowel symptoms such as increased stool frequency (SF) and rectal bleeding (RB). However, studies on these ...patient-reported outcomes in patients with inactive UC are limited, especially in Korea. Therefore, we investigated the prevalence and risk factors of bowel symptoms in Korean patients with inactive UC.
We investigated the prevalence of bowel symptoms in patients with endoscopically quiescent UC between June 1989 and December 2016 using a well-characterized referral center-based cohort. The Mayo clinic score (MCS) was used to evaluate bowel symptoms at the most recent visit near the date of endoscopy. Clinical characteristics of the patients were compared based on the presence or absence of bowel symptoms.
Overall, 741 patients with endoscopically quiescent UC were identified, of whom 222 (30%) and 48 (6.5%) had an SF and RB subscore of ≥ 1, respectively. Patients with bowel symptoms (SF + RB ≥ 1; n = 244 32.9%) had higher rates of left-sided colitis (E2) or extensive colitis (E3) than patients without bowel symptoms (SF + RB = 0; n = 497 67.1%; P = 0.002). Multivariate analysis revealed that female sex (odds ratio OR: 1.568; 95% confidence interval CI: 1.023-2.402; P = 0.039) and E2 or E3 (OR 1.411; 95% CI 1.020-1.951; P = 0.038) were the significant risk factors for increased SF.
This study revealed that one-third of patients with endoscopically quiescent UC reported increased SF. Female sex and disease extent may be associated with bowel symptoms.
By automatically classifying the stomach, small bowel, and colon, the reading time of the wireless capsule endoscopy (WCE) can be reduced. In addition, it is an essential first preprocessing step to ...localize the small bowel in order to apply automated small bowel lesion detection algorithms based on deep learning. The purpose of the study was to develop an automated small bowel detection method from long untrimmed videos captured from WCE. Through this, the stomach and colon can also be distinguished. The proposed method is based on a convolutional neural network (CNN) with a temporal filtering on the predicted probabilities from the CNN. For CNN, we use a ResNet50 model to classify three organs including stomach, small bowel, and colon. The hybrid temporal filter consisting of a Savitzky–Golay filter and a median filter is applied to the temporal probabilities for the “small bowel” class. After filtering, the small bowel and the other two organs are differentiated with thresholding. The study was conducted on dataset of 200 patients (100 normal and 100 abnormal WCE cases), which was divided into a training set of 140 cases, a validation set of 20 cases, and a test set of 40 cases. For the test set of 40 patients (20 normal and 20 abnormal WCE cases), the proposed method showed accuracy of 99.8% in binary classification for the small bowel. Transition time errors for gastrointestinal tracts were only 38.8 ± 25.8 seconds for the transition between stomach and small bowel and 32.0 ± 19.1 seconds for the transition between small bowel and colon, compared to the ground truth organ transition points marked by two experienced gastroenterologists.
The aim of this study was to evaluate the risk of asthma in rheumatoid arthritis patients using matched control group for socioeconomic factors and past medical history. Adults >20 years old were ...collected from the Korean Health Insurance Review and Assessment Service - National Sample Cohort (HIRA-NSC) from 2002 through 2013. A total of 6,695 individuals with rheumatoid arthritis were matched for age, sex, income, region of residence, hypertension, diabetes, and dyslipidemia with 26,780 individuals included in a control group. In both the rheumatoid arthritis and control groups, subjects' history of asthma was evaluated. Asthma (J45 and J46) and rheumatoid arthritis (M05 and M06) were included based on the International Classification of Disease-10 (ICD-10) codes and medication history. The crude and adjusted (depression and Charlson Comorbidity Index) hazard ratios (HRs) and 95% confidence intervals (CI) of asthma for rheumatoid arthritis patients were analyzed using a stratified Cox proportional hazard model. Subgroup analyses were conducted according to age and sex, number of treatment histories, and medication histories. Approximately 16.4% (1,095/6,695) of rheumatoid arthritis group and 13.0% (3,469/26,780) of the control group had asthma (P < 0.001). The rheumatoid arthritis group demonstrated a higher adjusted HR for asthma than the control group (adjusted HR = 1.23, 95% CI = 1.15-1.32, P < 0.001). This result was consistent in all subgroups. Rheumatoid arthritis was related to an increase risk of asthma.
Background/Aims: The protective effects of vitamin D and calcium on colorectal neoplasms are known. Bone mineral density (BMD) may be a reliable biomarker that reflects the long-term anticancer ...effect of vitamin D and calcium. This study aimed to evaluate the association between BMD and colorectal adenomas including high-risk adenoma.
Methods: A multicenter, cross-sectional, case-control study was conducted among participants with average risk of colorectal cancer who underwent BMD and screening colonoscopy between 2015 and 2019. The main outcome was the detection of colorectal neoplasms. The variable under consideration was low BMD (osteopenia/osteoporosis). The logistic regression model included baseline demographics, components of metabolic syndrome, fatty liver disease status, and aspirin and multivitamin use.
Results: A total of 2,109 subjects were enrolled. The mean age was 52.1±10.8 years and 42.6% were male. The adenoma detection rate was 43%. Colorectal adenoma and high-risk adenoma were both more prevalent in subjects with low BMD than those with normal BMD (48.2% vs 38.8% and 12.1% vs 9.1%). In the univariate analysis, old age, male sex, smoking, metabolic components, fatty liver, and osteoporosis were significantly associated with the risk of adenoma and high-risk adenoma. In the multivariate analysis, osteoporosis was independently associated with risk of colorectal adenoma (odds ratio OR, 1.65; 95% confidence interval CI, 1.11 to 2.46; p=0.014) and high-risk adenoma (OR, 1.94; 95% CI, 1.14 to 3.29; p=0.014).
Conclusions: Osteoporosis is an independent risk factor of colorectal adenoma and high-risk adenoma. (Gut Liver 2022;16:269-276)
Thymic epithelial tumors (TETs) are rare, and information regarding their surgical outcomes and prognostic factors has rapidly changed in the past few decades. We analyzed surgical treatment ...practices for TETs and outcomes in terms of overall survival (OS) and freedom from recurrence (FFR) during a 13-year period in Korea.
In total, 1,298 patients with surgically resected TETs between 2000 and 2013 were enrolled retrospectively. OS and FFR were calculated using the Kaplan-Meier method and evaluated with the log-rank test. Prognostic factors for OS and FFR were analyzed with multivariable Cox regression.
A total of 1,098 patients were diagnosed with thymoma, and 200 patients were diagnosed with thymic carcinoma. Over the study period, the total number of patients with surgically treated TETs and the proportion of patients who underwent minimally invasive thymic surgery (MITS) increased annually. The 5-year and 10-year survival rates of surgically treated TETs were 91.0% and 82.1%, respectively. The 5-year and 10-year recurrence rates were 86.3% and 80.0%, respectively. The outcomes of surgically treated TETs improved over time. Multivariable Cox hazards analysis for OS, age, tumor size, and Masaoka-Koga stage were independent predictors of prognosis. The World Health Organization classification and tumor-node-metastasis (TNM) staging were also related to the prognosis of TETs.
Surgical treatment of TETs achieved a good prognosis with a recent increase in MITS. The M-K stage was the most important prognostic factor for OS and FFR. The new TNM stage could also be an effective predictor of the outcomes of TETs.
This study aimed to investigate the occurrence of tonsillectomy in asthmatic children using a control group with a comparable frequency of a preoperative history of asthma. Asthmatic children ≤15 ...years old were collected from the Korean Health Insurance Review and Assessment Service - National Sample Cohort (HIRA-NSC) from 2002 through 2013. In study I, asthmatic children who had undergone a tonsillectomy (n = 2,326) and control I participants (n = 9,304) were selected and matched 1:4 for age, sex, income, and region of residence but not a preoperative history of asthma. In study II, a preoperative history of asthma was additionally matched for between the tonsillectomy (n = 2,280) and the new control II participants (n = 9,120). The margin of equivalence of difference (control-tonsillectomy) for asthma was set at -0.05 to 0.05 per year. In addition, repeated measures ANOVA was performed for tonsillectomy according to yearly changes in asthma, status asthmaticus, and admission. In study I, the preoperative frequencies of asthma, status asthmaticus, and admission were higher in the tonsillectomy group than in the control group (P ≤ 0.001). The frequencies of postoperative asthma, status asthmaticus, and admission were lower in the tonsillectomy group than in the control I group for 3 years. In study II, the frequencies of postoperative 1-, 2-, and 3-year asthma and admission were not lower in the tonsillectomy group than in the control II group. Tonsillectomy did not further reduce the frequency of asthma in patients who underwent this procedure compared to the control group when a preoperative history of asthma history was equally matched between the two groups.