Efficacy and safety of three-dimensional magnetically assisted capsule endoscopy for upper gastrointestinal and small bowel examination.

BACKGROUND: Magnetically assisted capsule endoscopy (MACE) showed the feasibility for upper gastrointestinal examination. To further enhance the performance of conventional MACE, it is necessary to provide quality-improved and three-dimensional images. The aim of this clinical study was to determine the efficacy and safety of novel three-dimensional MACE (3D MACE) for upper gastrointestinal and small bowel examination at once. METHODS: This was a prospective, single-center, non-randomized, and sequential examination study (KCT0007114) at Dongguk University Ilsan Hospital. Adult patients who visited for upper endoscopy were included. The study protocol was conducted in two stages. First, upper gastrointestinal examination was performed using 3D MACE, and a continuous small bowel examination was performed by conventional method of capsule endoscopy. Two hours later, an upper endoscopy was performed for comparison with 3D MACE examination. The primary outcome was confirmation of major gastric structures (esophagogastric junction, cardia/fundus, body, angle, antrum, and pylorus). Secondary outcomes were confirmation of esophagus and duodenal bulb, accuracy for gastric lesions, completion of small bowel examination, 3D image reconstruction of gastric lesion, and safety. RESULTS: Fifty-five patients were finally enrolled. The examination time of 3D MACE was 14.84 ± 3.02 minutes and upper endoscopy was 5.22 ± 2.39 minutes. The confirmation rate of the six major gastric structures was 98.6% in 3D MACE and 100% in upper endoscopy. Gastric lesions were identified in 43 patients during 3D MACE, and 40 patients during upper endoscopy (Sensitivity 0.97). 3D reconstructed images were acquired for all lesions inspected by 3D MACE. The continuous small bowel examination by 3D MACE was completed in 94.5%. 3D MACE showed better overall satisfaction (3D MACE 9.55 ± 0.79 and upper endoscopy 7.75 ± 2.34, p<0.0001). There were no aspiration or significant adverse event or capsule retention in the 3D MACE examination. CONCLUSIONS: Novel 3D MACE system is more advanced diagnostic modality than the conventional MACE. And it is possible to perform serial upper gastrointestinal and small bowel examination as a non-invasive and one-step test. It would be also served as a bridge to pan-endoscopy.

Osteoporosis Is Associated with an Increased Risk of Colorectal Neoplasms Regardless of Sex: Nationwide Population-Based Cohort Study.

Vitamin D may have anticancer effects against colorectal cancer (CRC). Bone mineral density (BMD) reflects the long-term vitamin D status. This study investigated the association between osteoporosis and colorectal neoplasms (CRN). The data were obtained from the National Health Insurance Service sample cohort, which included 60,386 osteoporosis patients and 8224 controls who underwent BMD in 2002-2019. The logistic regression models included age, sex, income level, and comorbidity. Sensitivity tests were performed using the data from the National Health Screening Program. In total, 7706 (11.2%) patients were diagnosed with CRN, and the proportion was significantly higher in osteoporosis patients than in controls (11.7% vs. 8.1%). In the multivariate analysis, osteoporosis was associated with an increased risk of CRN (odds ratio (OR) = 1.91, 95% confidence interval = 1.75-2.09, p < 0.0001), which was significant for both colorectal adenomas and CRC (OR = 1.88 and 1.83, respectively). A subgroup analysis by sex revealed a significant association between osteoporosis and CRN in both women and men (OR = 2.06 and 1.66, respectively). The sensitivity tests revealed results similar to those of the original dataset. In conclusion, osteoporosis is significantly associated with CRN risk in both sexes. In high-risk patients with low BMD, appropriate screening for CRN and vitamin D supplementation are required, regardless of sex.

The combined use of anti-peptic agents is associated with an increased risk of osteoporotic fracture: a nationwide case-control study.

BACKGROUND/AIMS: Long-term use of acid suppressants such as proton pump inhibitors (PPIs) and histamine 2 receptor antagonist (H2RA) has been associated with the risk of osteoporotic fracture. Acid suppressants and muco-protective agents (MPAs) are often used together as anti-ulcer agents. We evaluated the association between the risk of osteoporotic fracture and the combined use of these anti-peptic agents. METHODS: A population-based case-control study was conducted by analyzing the Korean National Health Insurance Data from 2014 to 2020. Patients who had been prescribed anti-peptic agents, such as PPI, H2RA, or MPA, were included. Considering the incidence of osteoporotic fractures, the case group (n = 14,704) and control group (n = 58,816) were classified by 1:4 matching based on age and sex. RESULTS: The use of all types of anti-peptic agents was associated with an increased risk of osteoporotic fractures (PPI: hazard osteoratio [HR], 1.31; H2RA: HR, 1.44; and MPA: HR, 1.33; all p < 0.001). Compared to PPI alone, the combined use of "PPI and H2RA" (HR, 1.58; p = 0.010) as well as "PPI, H2RA, and MPA" (HR, 1.71; p = 0.001) was associated with an increased risk of osteoporotic fracture. However, compared with PPI alone, "MPA and PPI or H2RA" was not associated with an increased risk of osteoporotic fracture. CONCLUSION: This study found that the combined use of "PPI and H2RA" was associated with a higher risk of osteoporotic fractures. In cases where deemed necessary, the physicians may initially consider prescribing the combination use of MPA.

Reading of small bowel capsule endoscopy after frame reduction using an artificial intelligence algorithm.

OBJECTIVES: Poorly visualized images that appear during small bowel capsule endoscopy (SBCE) can confuse the interpretation of small bowel lesions and increase the physician's workload. Using a validated artificial intelligence (AI) algorithm that can evaluate the mucosal visualization, we aimed to assess whether SBCE reading after the removal of poorly visualized images could affect the diagnosis of SBCE. METHODS: A study was conducted to analyze 90 SBCE cases in which a small bowel examination was completed. Two experienced endoscopists alternately performed two types of readings. They used the AI algorithm to remove poorly visualized images for the frame reduction reading (AI user group) and conducted whole frame reading without AI (AI non-user group) for the same patient. A poorly visualized image was defined as an image with < 50% mucosal visualization. The study outcomes were diagnostic concordance and reading time between the two groups. The SBCE diagnosis was classified as Crohn's disease, bleeding, polyp, angiodysplasia, and nonspecific finding. RESULTS: The final SBCE diagnoses between the two groups showed statistically significant diagnostic concordance (k = 0.954, p < 0.001). The mean number of lesion images was 3008.5 ± 9964.9 in the AI non-user group and 1401.7 ± 4811.3 in the AI user group. There were no cases in which lesions were completely removed. Compared with the AI non-user group (120.9 min), the reading time was reduced by 35.6% in the AI user group (77.9 min). CONCLUSIONS: SBCE reading after reducing poorly visualized frames using the AI algorithm did not have a negative effect on the final diagnosis. SBCE reading method integrated with frame reduction and mucosal visualization evaluation will help improve AI-assisted SBCE interpretation.

Reduced risk of gastrointestinal bleeding associated with eupatilin in aspirin plus acid suppressant users: nationwide population-based study.

BACKGROUND/AIMS: Mucoprotective agents, such as eupatilin, are often prescribed to prevent gastrointestinal (GI) bleeding in addition to an acid suppressant despite the absence of a large-scale study. We evaluated the additional effect of eupatilin on the prevention of GI bleeding in both the upper and lower GI tract in concomitant aspirin and acid suppressant users using the nationwide database of national claims data from the Korean National Health Insurance Service (NHIS). METHODS: An aspirin cohort was constructed using the NHIS claims data from 2013 to 2020. Patients who manifested with hematemesis, melena, or hematochezia were considered to have GI bleeding. A Cox proportional hazards regression model was used to determine the risk factors for GI bleeding associated with the concomitant use of GI drugs and other covariates among aspirin users. RESULTS: Overall, a total of 432,208 aspirin users were included. The concurrent use of an acid suppressant and eupatilin (hazard ratio [HR] = 0.85, p = 0.016, vs. acid suppressant only) was a statistically significant preventive factor for GI bleeding. Moreover, a more than 3-month duration (HR = 0.88, p = 0.030) of acid suppressant and eupatilin prescription (vs. acid suppressant only) was a statistically significant preventive factor for GI bleeding. CONCLUSION: Eupatilin administration for ≥ 3 months showed additional preventive effect on GI bleeding in concomitant aspirin and acid suppressant users. Thus, cotreatment with eupatilin with a duration of 3 months or longer is recommended for reducing GI bleeding among aspirin plus acid suppressant users.

The Advent of Domain Adaptation into Artificial Intelligence for Gastrointestinal Endoscopy and Medical Imaging.

Artificial intelligence (AI) is a subfield of computer science that aims to implement computer systems that perform tasks that generally require human learning, reasoning, and perceptual abilities. AI is widely used in the medical field. The interpretation of medical images requires considerable effort, time, and skill. AI-aided interpretations, such as automated abnormal lesion detection and image classification, are promising areas of AI. However, when images with different characteristics are extracted, depending on the manufacturer and imaging environment, a so-called domain shift problem occurs in which the developed AI has a poor versatility. Domain adaptation is used to address this problem. Domain adaptation is a tool that generates a newly converted image which is suitable for other domains. It has also shown promise in reducing the differences in appearance among the images collected from different devices. Domain adaptation is expected to improve the reading accuracy of AI for heterogeneous image distributions in gastrointestinal (GI) endoscopy and medical image analyses. In this paper, we review the history and basic characteristics of domain shift and domain adaptation. We also address their use in gastrointestinal endoscopy and the medical field more generally through published examples, perspectives, and future directions.

A practical approach for small bowel bleeding.

Gastrointestinal (GI) bleeding is one of the most common conditions among patients visiting emergency departments in Korea. GI bleeding is divided into upper and lower GI bleeding, according to the bleeding site. GI bleeding is also divided into overt and occult GI bleeding based on bleeding characteristics. In addition, obscure GI bleeding refers to recurrent or persistent GI bleeding from a source that cannot be identified after esophagogastroduodenoscopy or colonoscopy. The small intestine is the largest part of the alimentary tract. It extends from the pylorus to the cecum. The small intestine is difficult to access owing to its long length. Moreover, it is not fixed to the abdominal cavity. When hemorrhage occurs in the small intestine, the source cannot be found in many cases because of the characteristics of the small intestine. In practice, small-intestinal bleeding accounts for most of the obscure GI bleeding. Therefore, in this review, we introduce and describe systemic approaches and examination methods, including video capsule endoscopy and balloon enteroscopy, that can be performed in patients with suspected small bowel bleeding in clinical practice.

Association between eupatilin and reduction in small bowel bleeding in aspirin users and aspirin plus acid suppressant users.

BACKGROUND/AIMS: Capsule endoscopy (CE) has shown that low-dose aspirin occasionally causes small bowel (SB) bleeding. We herein evaluated the protective effects of mucoprotective agents (MPAs) on SB bleeding in aspirin users using the nationwide database of claims data from the National Health Insurance Service (NHIS). METHODS: As CE is an insured procedure, we constructed an aspirin-SB cohort using NHIS claims data, with a maximum follow- up period of 24 months. Patients with anemia, melena, or hematochezia that occurred within 4 weeks before and after performing CE were suspected to have SB bleeding. A Cox proportional hazards regression model was used to determine the risk factors for SB bleeding. Subgroup analyses were conducted among patients who used acid suppressants, such as proton pump inhibitors (PPIs) and histamine-2 receptor antagonists. RESULTS: A total of 15,542 aspirin users were included. Anticoagulant use (hazard ratio [HR], 3.22), high Charlson comorbidity index score (≥ 2) (HR, 3.54), and PPI use (HR, 2.85) were significantly associated with SB bleeding, whereas eupatilin use (HR, 0.35) was a preventive factor. SB bleeding occurred more frequently in concurrent users of acid suppressants than in nonusers (1.3% vs. 0.5%). Subgroup analysis revealed that eupatilin significantly reduced the risk of SB bleeding in aspirin users with concurrent use of acid suppressants (HR, 0.23 vs. 2.55). CONCLUSION: Eupatilin was associated with a reduced risk of SB bleeding in both aspirin users and those with concomitant use of acid suppressants. Eupatilin use should be considered for aspirin users, especially for those concomitantly taking acid suppressants.

Cancer risk in patients with Peutz-Jeghers syndrome in Korea: a retrospective multi-center study.

BACKGROUND/AIMS: There have been little research on the cancer risks of patients with Peutz-Jeghers syndrome (PJS) in Korea. We aimed to investigate the clinical features of PJS patients and their cancer incidence rate. METHODS: Patients with PJS from nine medical centers were enrolled. In those patients diagnosed with cancer, data obtained included the date of cancer diagnosis, the tumor location, and the cancer stage. The cumulative risks of gastrointestinal cancers and extra-gastrointestinal cancers were calculated using the Kaplan-Meier method. RESULTS: A total of 96 PJS patients were included. The median age at diagnosis of PJS was 23.4 years. Cancer developed in 21 of the 96 patients (21.9%). The age of PJS diagnosis was widely distributed (0.9 to 72.4 years). The most common cancers were gastrointestinal cancer (n = 12) followed by breast cancer (n = 6). The cumulative lifetime cancer risk was calculated to be 62.1% at age 60. The cumulative lifetime gastrointestinal cancer risk was 47.1% at age 70. The cumulative lifetime extra- gastrointestinal cancer risk was 40.3% at age 60. CONCLUSION: PJS onset may occur at any age and the risks of gastrointestinal and extra-gastrointestinal cancer are high. Thorough surveillance of PJS patients for malignancies is vital.

Taking Oral Sulfate Tablets with Simethicone for Bowel Preparation Leads to Higher Adenoma Detection Rate than Polyethylene Glycol: A Propensity Score Analysis.

BACKGROUND: Efficient bowel preparation is essential for preventing colorectal cancer by improving endoscopic adenoma detection. Tablet for bowel preparation containing sulfate salts, OSTs (oral sulfate tablets), has been developed and it is gaining more popularity. However, its efficacy compared to standard preparation agent, PEG-AA (polyethylene glycol), has not been well discovered. We assessed the efficacy of PEG and OSTs using a real-time clinical data warehouse (CDW) model. METHODS: We performed a propensity score-matched (PSM) analysis of consecutive adult patients undergoing colonoscopy who received PEG-AA or OSTs prior to colonoscopy at a tertiary academic hospital. The endoscopic records of 992 adult patients were retrospectively analyzed. The clinical data warehouse collected data including bowel preparation, insertion time, observation time, and the detection of polyps and adenomas. Multivariate regression analysis was performed to reveal the factors associated with endoscopic outcomes. RESULTS: Among 992 patients included in the study, 770 and 222 patients received PEG-AA and OSTs, respectively. Among the propensity score-matched population (n = 1897), OSTs resulted in better bowel cleansing quality (8.16 vs 7.84, p = 0.014) and a higher adenoma detection rate (38.6% vs 27.1%, p = 0.003). Using PEG-AA, older age, inadequate bowel preparation (BBPS score < 6) and endoscopy by fellows were found to be factors associated with poor adenoma detection. In the elderly over 65 years of age, a significant difference in cleansing quality between the two groups (7.21 vs 8.19, p < 0.001) was found, but its impact on ADR was not prominent (49.5% vs 45.4%, p = 0.653). CONCLUSIONS: OSTs with simethicone achieved better endoscopic cleanliness, improving adenoma detection rate compared to the conventional PEG-AA protocol. The synergistic effect of both the convenience of taking tablets and the reduction of intraluminal bubble by adjunctive simethicone improves the clinical efficacy of colonoscopy.

Small bowel cleanliness in capsule endoscopy: a case-control study using validated artificial intelligence algorithm.

Small bowel capsule endoscopy (SBCE) may need to be performed immediately after colonoscopy without additional bowel preparation if active small bowel diseases are suspected. However, it is unclear whether the small bowel cleanliness is adequately maintained even after SBCE is performed immediately after colonoscopy. We compared the small bowel cleanliness scores of the study group (SBCE immediately after colonoscopy) and control group (SBCE alone) using a validated artificial intelligence (AI) algorithm (cut-off score > 3.25 for adequate). Cases of SBCE in which polyethylene glycol was used were included retrospectively. Among 85 enrolled cases, 50 cases (58.8%) were the study group. The mean time from the last dose of purgative administration to SBCE was 6.86 ± 0.94 h in the study group and 3.00 ± 0.18 h in the control group. Seventy-five cases (88.2%) were adequate small bowel cleanliness, which was not different between the two groups. The mean small bowel cleanliness score for the study group was 3.970 ± 0.603, and for the control group was 3.937 ± 0.428. In the study group, better colon preparation resulted in a higher small bowel cleanliness score (p = 0.015). Small bowel cleanliness was also adequately maintained in SBCE immediately after colonoscopy. There was no difference between the time and volume of purgative administration and small bowel cleanliness.

Osteoporosis Is Associated with an Increased Risk of Colorectal Adenoma and High-Risk Adenoma: A Retrospective, Multicenter, Cross-Sectional, Case-Control Study.

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.

Propofol Alone versus Propofol in Combination with Midazolam for Sedative Endoscopy in Patients with Paradoxical Reactions to Midazolam.

BACKGROUND/AIMS: The efficacy of propofol in gastrointestinal endoscopy for patients with midazolam-induced paradoxical reactions remains unclarified. This study aimed to compare the efficacy and safety of propofol-based sedation in patients who previously experienced paradoxical reactions. METHODS: This was a prospective, single-blinded, randomized controlled pilot study. Participants with a history of paradoxical reactions to midazolam during a previous esophagogastroduodenoscopy were recruited and randomly assigned to group I (propofol monosedation) or group II (combination of propofol and midazolam). The primary endpoint was the occurrence of a paradoxical reaction. RESULTS: A total of 30 participants (mean age, 54.7±12.6 years; male, 19/30) were randomly assigned to group I (n=16) or group II (n=14). There were no paradoxical reactions in group I, but there were two in group II, without a significant difference (p=0.209). The mean dose of propofol was higher in group I than in group II (p=0.002). Meanwhile, the procedure and recovery times did not differ between groups. CONCLUSION: Propofol-based sedation was safe and effective for patients who experienced paradoxical reactions to midazolam. However, caution is needed because few cases of paradoxical reaction again can happen in group II in which midazolam was readministered.

The effect of menopausal hormone therapy on gastrointestinal cancer risk and mortality in South Korea: a population-based cohort study.

BACKGROUND: The effect of menopausal hormone therapy (MHT) on gastrointestinal (GI) cancers is controversial, and no research has been conducted in the East. This study investigates the association between MHT and GI cancer risks in South Korea. METHODS: A prescription-based cohort study was conducted using the NHIS Sample Cohort (2002-2013) of Korea. We used 1:5 propensity score matching, and 22,577 MHT users and 111,113 non-users were selected. Kaplan-Meier survival curves with log-rank tests were used. Cox proportional hazard models were used to estimate hazard ratios (HR) with 95% confidence intervals (CI). Landmark analysis was used to determine dose-response relationship. RESULTS: The median follow-up was 79.6 of months. Kaplan-Meier survival curve showed less frequent GI cancer diagnoses in MHT users compared to non-users (0.13 vs. 0.16 per 100,000 person-years). Menopausal hormone therapy was associated with decreased incidence of GI cancer (HR = 0.809, 95%CI = 0.691-0.946) and colorectal cancer (CRC) (HR = 0.757, 95%CI = 0.577-0.995). Gastric cancer (GC) incidence showed marginal significance (HR = 0.787, 95%CI = 0.605-1.023). The mortality from GI cancer was lower in MHT users than in non-users (HR = 0.737, 95%CI = 0.547-0.993). The relationship between MHT and GI cancer was stronger with increasing MHT dose in terms of both incidence (Ptrend = 0.0002) and mortality (Ptrend = 0.0064). CONCLUSIONS: The association between MHT use and reduced risks of GI cancers was attributed to CRC and GC and showed a dose-response relationship in a population-based cohort study.

Gastric examination using a novel three-dimensional magnetically assisted capsule endoscope and a hand-held magnetic controller: A porcine model study.

Magnetically assisted capsule endoscopy (MACE) is a noninvasive procedure and can overcome passive capsule movement that limits gastric examination. MACE has been studied in many trials as an alternative to upper endoscopy. However, to increase diagnostic accuracy of various gastric lesions, MACE should be able to provide stereoscopic, clear images and to measure the size of a lesion. So, we conducted the animal experiment using a novel three-dimensional (3D) MACE and a new hand-held magnetic controller for gastric examination. The purpose of this study is to assess the performance and safety of 3D MACE and hand-held magnetic controller through the animal experiment. Subsequently, via the dedicated viewer, we evaluate whether 3D reconstruction images and clear images can be obtained and accurate lesion size can be measured. During real-time gastric examination, the maneuverability and visualization of 3D MACE were adequate. A polypoid mass lesion was incidentally observed at the lesser curvature side of the prepyloric antrum. The mass lesion was estimated to be 10.9 x 11.5 mm in the dedicated viewer, nearly the same size and shape as confirmed by upper endoscopy and postmortem examination. Also, 3D and clear images of the lesion were successfully reconstructed. This animal experiment demonstrates the accuracy and safety of 3D MACE. Further clinical studies are warranted to confirm the feasibility of 3D MACE for human gastric examination.

Efficacy of a comprehensive binary classification model using a deep convolutional neural network for wireless capsule endoscopy.

The manual reading of capsule endoscopy (CE) videos in small bowel disease diagnosis is time-intensive. Algorithms introduced to automate this process are premature for real clinical applications, and multi-diagnosis using these methods has not been sufficiently validated. Therefore, we developed a practical binary classification model, which selectively identifies clinically meaningful images including inflamed mucosa, atypical vascularity or bleeding, and tested it with unseen cases. Four hundred thousand CE images were randomly selected from 84 cases in which 240,000 images were used to train the algorithm to categorize images binarily. The remaining images were utilized for validation and internal testing. The algorithm was externally tested with 256,591 unseen images. The diagnostic accuracy of the trained model applied to the validation set was 98.067%. In contrast, the accuracy of the model when applied to a dataset provided by an independent hospital that did not participate during training was 85.470%. The area under the curve (AUC) was 0.922. Our model showed excellent internal test results, and the misreadings were slightly increased when the model was tested in unseen external cases while the classified 'insignificant' images contain ambiguous substances. Once this limitation is solved, the proposed CNN-based binary classification will be a promising candidate for developing clinically-ready computer-aided reading methods.

Examination of Entire Gastrointestinal Tract: A Perspective of Mouth to Anus (M2A) Capsule Endoscopy.

Capsule endoscopy (CE) is the only non-invasive diagnostic tool that enables the direct visualization of the gastrointestinal (GI) tract. Even though CE was initially developed for small-bowel investigation, its clinical application is expanding, and technological advances continue. The final iteration of CE will be a mouth to anus (M2A) capsule that investigates the entire GI tract by the ingestion of a single capsule. This narrative review describes the current developmental status of CE and discusses the possibility of realizing an M2A capsule and what needs to be overcome in the future.

Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality.

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.

Complications of common bile duct stones: A risk factors analysis.

BACKGROUND: The latest guidelines recommended that common bile duct stones (CBDSs) should be removed, preferably endoscopically, regardless of the presence of symptoms or complications. However, the removal of CBDSs may not be feasible in very old patients or those with co-morbidities. In these cases, it is important to understand the risk factors for the development of CBDSs-related complications to decide whether or not to treat high-risk patients. Herein, we aimed to identify the risk factors for the development of complications after the diagnosis of CBDSs. METHODS: The medical records of patients with CBDSs between October 2005 and September 2019 were retrospectively analyzed. All patients with radiologically-diagnosed CBDSs, including those who received treatment and those who did not, were analyzed. RESULTS: A total of 634 patients were included and 95 (15.0%) patients had CBDS-related complications during the mean follow-up period of 32.6 months. Forty-four (6.9%) high-risk patients remained asymptomatic and did not receive treatment during the follow-up period. In multivariate analyses, size of CBDSs ≥ 5 mm and no treatment within 30 days were independent risk factors for the development of complications. The spontaneous passage of CBDSs was proved radiologically in 9 out of 81 (11.1%) patients within 30 days. CONCLUSIONS: It is recommended treating CBDSs within 30 days from the diagnosis, even in high-risk patients, especially if the size is larger than 5 mm.

Development of a deep learning-based software for calculating cleansing score in small bowel capsule endoscopy.

A standardized small bowel (SB) cleansing scale is currently not available. The aim of this study was to develop an automated calculation software for SB cleansing score using deep learning. Consecutively performed capsule endoscopy cases were enrolled from three hospitals. A 5-step scoring system based on mucosal visibility was trained for deep learning in the training set. Performance of the trained software was evaluated in the validation set. Average cleansing score (1.0 to 5.0) by deep learning was compared to clinical grading (A to C) reviewed by clinicians. Cleansing scores decreased as clinical grading worsened (scores of 4.1, 3.5, and 2.9 for grades A, B, and C, respectively, P < 0.001). Adequate preparation was achieved for 91.7% of validation cases. The average cleansing score was significantly different between adequate and inadequate group (4.0 vs. 2.9, P < 0.001). ROC curve analysis revealed that a cut-off value of cleansing score at 3.25 had an AUC of 0.977. Diagnostic yields for small, hard-to-find lesions were associated with high cleansing scores (4.3 vs. 3.8, P < 0.001). We developed a novel scoring software which calculates objective, automated cleansing scores for SB preparation. The cut-off value we suggested provides a standard criterion for adequate bowel preparation as a quality indicator.