Joint representation and visualization of derailed cell states with Decipher.

Biological insights often depend on comparing conditions such as disease and health. Yet, we lack effective computational tools for integrating single-cell genomics data across conditions or characterizing transitions from normal to deviant cell states. Here, we present Decipher, a deep generative model that characterizes derailed cell-state trajectories.

Novel Risk Score for 30-Day Adverse Events Following Colonoscopy in Older Adults.

Background/aims: Physicians are challenged with balancing benefits and risks of performing colonoscopies in older adults. We identified adverse event risk factors in this population and developed a predictive risk score for colonoscopy-related adverse events.

Methods: From August 2017 to August 2022, 8,154 patients aged ≥60 years who underwent screening or diagnostic colonoscopies were enrolled at Gangnam Severance Hospital.

Early Progression Prediction in Korean Crohn's Disease Using a Korean-Specific PrediXcan Model.

Crohn's disease (CD) is a chronic inflammatory disorder with potential progression to stricturing (B2) or penetrating (B3) phenotypes, leading to significant complications. Early identification of patients at risk for these complications is critical for personalized management. This study aimed to develop a predictive model using clinical data and a Korean-specific transcriptome-wide association study (TWAS) to forecast early progression in CD patients.

Real-World Colonoscopy Video Integration to Improve Artificial Intelligence Polyp Detection Performance and Reduce Manual Annotation Labor.

: Artificial intelligence (AI) integration in colon polyp detection often exhibits high sensitivity but notably low specificity in real-world settings, primarily due to reliance on publicly available datasets alone. To address this limitation, we proposed a semi-automatic annotation method using real colonoscopy videos to enhance AI model performance and reduce manual labeling labor. : An integrated AI model was trained and validated on 86,258 training images and 17,616 validation images.

Tumor Budding as an Additional Factor in Determining the Need for Surgery after Endoscopic Resection in Mucosal Invasive Gastric Cancer: A Retrospective Study from a Korean Tertiary Hospital.

Background/aims: The presence of individual cancer cells at the invasive tumor front is referred to as tumor budding (TB). The purpose of this study was to assess the clinicopathological significance of TB in patients with early gastric cancer (EGC).

Methods: A total of 939 patients who received radical surgery for EGC were included in this retrospective study.

Helicobacter pylori Eradication Is Associated With a Reduced Risk of Metachronous Gastric Neoplasia by Restoring Immune Function in the Gastric Mucosa.

Background: Helicobacter pylori infection is a significant contributing factor of gastric cancer. Metachronous neoplasms also pose a risk. The mechanism underlying the impact of H.

Association of Immune-Mediated Inflammatory Diseases and Fracture Risk in Patients with Type 2 Diabetes: A Nationwide Population-Based Study.

: Immune-mediated inflammatory diseases (IMIDs) are associated with chronic inflammation that may increase fracture risk; however, their impact within specific populations, such as those with type 2 diabetes mellitus (T2DM), remains unclear. This study aimed to evaluate the association between IMIDs and fracture risk, leveraging a large, high-quality population-based cohort of patients with T2DM. : A total of 2,120,900 patients with T2DM without a previous history of fractures were enrolled from the nationwide health check-up database provided by the Korean National Health Insurance Service.

Survey of the Actual Practices Used for Endoscopic Removal of Colon Polyps in Korea: A Comparison with the Current Guidelines.

Background/aims: We investigated the clinical practice patterns of Korean endoscopists for the endoscopic resection of colorectal polyps.

Methods: From September to November 2021, an online survey was conducted regarding the preferred resection methods for colorectal polyps, and responses were compared with the international guidelines.

Results: Among 246 respondents, those with <4 years, 4-9 years, and ≥10 years of experience in colonoscopy practices accounted for 25.

Efficacy of Oral Sulfate Tablet and 2 L-Polyethylene Glycol With Ascorbic Acid for Bowel Preparation: A Prospective Randomized KASID Multicenter Trial.

Background: Oral sulfate tablets (OSTs) are bowel preparation agents that combine oral sulfate solution and simethicone. This study compared the efficacy, tolerability, and safety of OST compared to 2 L-polyethylene glycol plus ascorbic acid (2 L-PEG/ASC).

Methods: This prospective, randomized, controlled, single-blinded, multicenter, noninferiority trial enrolled 211 healthy adults who underwent colonoscopy between May 2020 and September 2022 at 13 university hospitals.

Effectiveness and Tolerability of Methotrexate Combined with Biologics in Patients with Crohn's Disease: A Multicenter Observational Study.

Background: Methotrexate (MTX) combination therapy with biological agents has gained increasing interest. Here, we assessed the efficacy and tolerability of the MTX combination therapy in patients with Crohn's disease (CD).

Methods: We performed a multicenter observational study with 185 patients with CD with MTX and biologics combination therapy; the patients were recruited from three IBD Clinics in Korea.

Creeping fat exhibits distinct Inflammation-specific adipogenic preadipocytes in Crohn's disease.

Creeping fat (CrF) is an extraintestinal manifestation observed in patients with Crohn's disease (CD). It is characterized by the accumulation of mesenteric adipose tissue (MAT) that wraps around the intestinal wall. Although the role of CrF in CD is still debated, multiple studies have highlighted a correlation between CrF and inflammation, as well as fibrostenosais of the intestine, which contributes to the worsening of CD symptoms.

Endoscopic mucosal resection using anchored snare Tip-in versus precut technique for small rectal neuroendocrine tumors.

Background/aims: Small rectal neuroendocrine tumors (NETs) can be treated with modified endoscopic mucosal resection (EMR). However, an optimal EMR method remains to be established. We aimed to assess the non-inferiority of Tip-in EMR versus precut EMR (EMR-P) for treating rectal NETs.

Joint representation and visualization of derailed cell states with Decipher.

Biological insights often depend on comparing conditions such as disease and health, yet we lack effective computational tools for integrating single-cell genomics data across conditions or characterizing transitions from normal to deviant cell states. Here, we present Decipher, a deep generative model that characterizes derailed cell-state trajectories. Decipher jointly models and visualizes gene expression and cell state from normal and perturbed single-cell RNA-seq data, revealing shared and disrupted dynamics.

Enrichment of Activated Fibroblasts as a Potential Biomarker for a Non-Durable Response to Anti-Tumor Necrosis Factor Therapy in Patients with Crohn's Disease.

We investigated whether the response to anti-tumor necrosis factor (anti-TNF) treatment varied according to inflammatory tissue characteristics in Crohn's disease (CD). Bulk RNA sequencing (RNA-seq) data were obtained from inflamed and non-inflamed tissues from 170 patients with CD. The samples were clustered based on gene expression profiles using principal coordinate analysis (PCA).

Effectiveness and tolerability of methotrexate monotherapy in Crohn's disease patients: a multicenter observational study.

Background: Methotrexate monotherapy is recommended as a maintenance therapy for Crohn's disease (CD). However, long-term follow-up data are scarce.

Objectives: We aimed to examine the effectiveness and tolerability of methotrexate monotherapy in 94 CD patients from three inflammatory bowel disease Clinics in Korea.

Risk of all-cause and cause-specific mortality associated with immune-mediated inflammatory diseases in Korea.

Objective: Immune-mediated inflammatory disease (IMID) is associated with an increased risk of mortality. It is unclear whether the higher mortality is attributable to the IMIDs themselves or to the higher prevalence of comorbidities in IMIDs. We aimed to investigate whether IMIDs confer a higher risk of mortality.

Association of immune-mediated inflammatory diseases with depression and anxiety in patients with type 2 diabetes: A nationwide population-based study.

Objective: Patients with type 2 diabetes (T2DM) are at a high risk of developing depression and anxiety. To better stratify the risk, we aimed to assess whether the presence of immune-mediated inflammatory diseases (IMIDs) confers a higher risk of depression and anxiety in these patients.

Methods: Patients with T2DM without prior depression or anxiety who underwent national health examination between 2009 and 2012 ( = 1,612,705) were enrolled from the nationwide health check-up data from Korean National Health Insurance Service.

Nomogram for pre-procedural prediction of non-curative endoscopic resection in patients with early gastric cancer.

Background: Non-curative resection (non-CR) after endoscopic submucosal dissection (ESD) requires additional surgery due to the possibility of lymph node metastasis (LNM). Therefore, it is important to accurately predict the risk of non-CR to avoid unnecessary preoperative procedures. Thus, we aimed to develop and verify a nomogram to predict the risk of non-CR prior to ESD.

Korean Guidelines for Postpolypectomy Colonoscopic Surveillance: 2022 revised edition.

Colonoscopic polypectomy is effective in decreasing the incidence and mortality of colorectal cancer (CRC). Premalignant polyps discovered during colonoscopy are associated with the risk of metachronous advanced neoplasia. Postpolypectomy surveillance is the most important method for managing advanced metachronous neoplasia.

Relieving Anxiety Through Virtual Reality Prior to Endoscopic Procedures.

Purpose: Endoscopic procedures can cause anxiety, which can lead to more uncomfortable, difficult, and incomplete procedures, in addition to greater use of sedative medication. Here, we investigate whether exposing patients to virtual reality (VR) prior to endoscopic procedures can reduce their anxiety levels.

Materials And Methods: Forty patients at Gangnam Severance Hospital were enrolled and divided into the VR group and the control group.

Development and validation of a convolutional neural network model for diagnosing Helicobacter pylori infections with endoscopic images: a multicenter study.

Background And Aims: Insufficient validation limits the generalizability of deep learning in diagnosing Helicobacter pylori infection with endoscopic images. The aim of this study was to develop a deep learning model for the diagnosis of H pylori infection using endoscopic images and validate the model with internal and external datasets.

Methods: A convolutional neural network (CNN) model was developed based on a training dataset comprising 13,403 endoscopic images from 952 patients who underwent endoscopy at Seoul National University Hospital Gangnam Center.

Association of Waist Circumference with the Risk of Inflammatory Bowel Disease: a Nationwide Cohort Study of 10 Million Individuals in Korea.

Background And Aims: Metabolic syndrome may share the pathophysiology of adipose tissue dysregulation and inadequate immune response with inflammatory bowel disease [IBD]. We determined the association of abdominal obesity [AO] with the risk of developing IBD.

Methods: We conducted a nationwide population-based cohort study using the Korean National Health Insurance Services database.

An Optimal Artificial Intelligence System for Real-Time Endoscopic Prediction of Invasion Depth in Early Gastric Cancer.

We previously constructed a VGG-16 based artificial intelligence (AI) model (image classifier [IC]) to predict the invasion depth in early gastric cancer (EGC) using endoscopic static images. However, images cannot capture the spatio-temporal information available during real-time endoscopy-the AI trained on static images could not estimate invasion depth accurately and reliably. Thus, we constructed a video classifier [VC] using videos for real-time depth prediction in EGC.