Deep learning-based long-term risk evaluation of incident type 2 diabetes using electrocardiogram in a non-diabetic population: a retrospective, multicentre study.

Background: Diabetes is a major public health concern. We aimed to evaluate the long-term risk of incident type 2 diabetes in a non-diabetic population using a deep learning model (DLM) detecting prevalent type 2 diabetes using electrocardiogram (ECG). Methods: In this retrospective study, participants who underwent health checkups at two tertiary hospitals in Seoul, South Korea, between Jan 1, 2001 and Dec 31, 2022 were included. Type 2 diabetes was defined as glucose ≥126 mg/dL or glycated haemoglobin (HbA1c) ≥ 6.5%. For survival analysis on incident type 2 diabetes, we introduced an additional variable, diabetic ECG, which is determined by the DLM trained on ECG and corresponding prevalent diabetes. It was assumed that non-diabetic individuals with diabetic ECG had a higher risk of incident type 2 diabetes than those with non-diabetic ECG. The one-dimensional ResNet-based model was adopted for the DLM, and the Guided Grad-CAM was used to localise important regions of ECG. We divided the non-diabetic group into the diabetic ECG group (false positive) and the non-diabetic ECG (true negative) group according to the DLM decision, and performed a Cox proportional hazard model, considering the occurrence of type 2 diabetes more than six months after the visit. Findings: 190,581 individuals were included in the study with a median follow-up period of 11.84 years. The areas under the receiver operating characteristic curve for prevalent type 2 diabetes detection were 0.816 (0.807-0.825) and 0.762 (0.754-0.770) for the internal and external validations, respectively. The model primarily focused on the QRS duration and, occasionally, P or T waves. The diabetic ECG group exhibited an increased risk of incident type 2 diabetes compared with the non-diabetic ECG group, with hazard ratios of 2.15 (1.82-2.53) and 1.92 (1.74-2.11) for internal and external validation, respectively. Interpretation: In the non-diabetic group, those whose ECG was classified as diabetes by the DLM were at a higher risk of incident type 2 diabetes than those whose ECG was not. Additional clinical research on the relationship between the phenotype of ECG and diabetes to support the results and further investigation with tracked data and various ECG recording systems are suggested for future works. Funding: National Research Foundation of Korea.

Real-time machine learning model to predict in-hospital cardiac arrest using heart rate variability in ICU.

Predicting in-hospital cardiac arrest in patients admitted to an intensive care unit (ICU) allows prompt interventions to improve patient outcomes. We developed and validated a machine learning-based real-time model for in-hospital cardiac arrest predictions using electrocardiogram (ECG)-based heart rate variability (HRV) measures. The HRV measures, including time/frequency domains and nonlinear measures, were calculated from 5 min epochs of ECG signals from ICU patients. A light gradient boosting machine (LGBM) algorithm was used to develop the proposed model for predicting in-hospital cardiac arrest within 0.5-24 h. The LGBM model using 33 HRV measures achieved an area under the receiver operating characteristic curve of 0.881 (95% CI: 0.875-0.887) and an area under the precision-recall curve of 0.104 (95% CI: 0.093-0.116). The most important feature was the baseline width of the triangular interpolation of the RR interval histogram. As our model uses only ECG data, it can be easily applied in clinical practice.

Automatic segmentation of atrial fibrillation and flutter in single-lead electrocardiograms by self-supervised learning and Transformer architecture.

OBJECTIVES: Automatic detection of atrial fibrillation and flutter (AF/AFL) is a significant concern in preventing stroke and mitigating hemodynamic instability. Herein, we developed a Transformer-based deep learning model for AF/AFL segmentation in single-lead electrocardiograms (ECGs) by self-supervised learning with masked signal modeling (MSM). MATERIALS AND METHODS: We retrieved data from 11 open-source databases on PhysioNet; 7 of these databases included labeled ECGs, while the other 4 were without labels. Each database contained ECG recordings with durations of ≥30 s. A total of 24 intradialytic ECGs with paroxysmal AF/AFL during 4 h of hemodialysis sessions at Seoul National University Hospital were used for external validation. The model was pretrained by predicting masked areas of ECG signals and fine-tuned by predicting AF/AFL areas. Cross-database validation was used for evaluation, and the intersection over union (IOU) was used as a main performance metric in external database validation. RESULTS: In the 7 labeled databases, the areas marked as AF/AFL constituted 41.1% of the total ECG signals, ranging from 0.19% to 51.31%. In the evaluation per ECG segment, the model achieved IOU values of 0.9254 and 0.9477 for AF/AFL segmentation and other segmentation tasks, respectively. When applied to intradialytic ECGs with paroxysmal AF/AFL, the IOUs for the segmentation of AF/AFL and non-AF/AFL were 0.9896 and 0.9650, respectively. Model performance by different training procedure indicated that pretraining with MSM and the application of an appropriate masking ratio both contributed to the model performance. It also showed higher IOUs of AF/AFL labels than in previous studies when training and test databases were matched. CONCLUSION: The present model with self-supervised learning by MSM performs robustly in segmenting AF/AFL.

Real-time dual prediction of intradialytic hypotension and hypertension using an explainable deep learning model.

Both intradialytic hypotension (IDH) and hypertension (IDHTN) are associated with poor outcomes in hemodialysis patients, but a model predicting dual outcomes in real-time has never been developed. Herein, we developed an explainable deep learning model with a sequence-to-sequence-based attention network to predict both of these events simultaneously. We retrieved 302,774 hemodialysis sessions from the electronic health records of 11,110 patients, and these sessions were split into training (70%), validation (10%), and test (20%) datasets through patient randomization. The outcomes were defined when nadir systolic blood pressure (BP) < 90 mmHg (termed IDH-1), a decrease in systolic BP ≥ 20 mmHg and/or a decrease in mean arterial pressure ≥ 10 mmHg (termed IDH-2), or an increase in systolic BP ≥ 10 mmHg (i.e., IDHTN) occurred within 1 h. We developed a temporal fusion transformer (TFT)-based model and compared its performance in the test dataset, including receiver operating characteristic curve (AUROC) and area under the precision-recall curves (AUPRC), with those of other machine learning models, such as recurrent neural network, light gradient boosting machine, random forest, and logistic regression. Among all models, the TFT-based model achieved the highest AUROCs of 0.953 (0.952-0.954), 0.892 (0.891-0.893), and 0.889 (0.888-0.890) in predicting IDH-1, IDH-2, and IDHTN, respectively. The AUPRCs in the TFT-based model for these outcomes were higher than the other models. The factors that contributed the most to the prediction were age and previous session, which were time-invariant variables, as well as systolic BP and elapsed time, which were time-varying variables. The present TFT-based model predicts both IDH and IDHTN in real time and offers explainable variable importance.

Machine learning-based prediction of intraoperative hypoxemia for pediatric patients.

BACKGROUND: Reducing the duration of intraoperative hypoxemia in pediatric patients by means of rapid detection and early intervention is considered crucial by clinicians. We aimed to develop and validate a machine learning model that can predict intraoperative hypoxemia events 1 min ahead in children undergoing general anesthesia. METHODS: This retrospective study used prospectively collected intraoperative vital signs and parameters from the anesthesia ventilator machine extracted every 2 s in pediatric patients undergoing surgery under general anesthesia between January 2019 and October 2020 in a tertiary academic hospital. Intraoperative hypoxemia was defined as oxygen saturation <95% at any point during surgery. Three common machine learning techniques were employed to develop models using the training dataset: gradient-boosting machine (GBM), long short-term memory (LSTM), and transformer. The performances of the models were compared using the area under the receiver operating characteristics curve using randomly assigned internal testing dataset. We also validated the developed models using temporal holdout dataset. Pediatric patient surgery cases between November 2020 and January 2021 were used. The performances of the models were compared using the area under the receiver operating characteristic curve (AUROC). RESULTS: In total, 1,540 (11.73%) patients with intraoperative hypoxemia out of 13,130 patients' records with 2,367 episodes were included for developing the model dataset. After model development, 200 (13.25%) of the 1,510 patients' records with 289 episodes were used for holdout validation. Among the models developed, the GBM had the highest AUROC of 0.904 (95% confidence interval [CI] 0.902 to 0.906), which was significantly higher than that of the LSTM (0.843, 95% CI 0.840 to 0.846 P < .001) and the transformer model (0.885, 95% CI, 0.882-0.887, P < .001). In holdout validation, GBM also demonstrated best performance with an AUROC of 0.939 (95% CI 0.936 to 0.941) which was better than LSTM (0.904, 95% CI 0.900 to 0.907, P < .001) and the transformer model (0.929, 95% CI 0.926 to 0.932, P < .001). CONCLUSIONS: Machine learning models can be used to predict upcoming intraoperative hypoxemia in real-time based on the biosignals acquired by patient monitors, which can be useful for clinicians for prediction and proactive treatment of hypoxemia in an intraoperative setting.

Efficacy and Safety of ClearCut™ Knife H-type in Endoscopic Submucosal Dissection for Gastric Neoplasms: A Multicenter, Randomized Trial

Purpose@#Endoscopic submucosal dissection (ESD) is an effective treatment for early gastrointestinal neoplasms. However, this is a time-consuming procedure requiring various devices. This study aimed to evaluate the efficacy and safety of the ClearCut™ Knife H-type, which is an integrated needle-tipped and insulated-tipped (IT) knife. @*Materials and Methods@#Between July 2020 and September 2021, 99 patients with gastric epithelial neoplasms scheduled for ESD at three tertiary care hospitals were randomly assigned to H-knife (ClearCut™ Knife H-type) or IT-knife (conventional IT knife) groups.Procedure times, therapeutic outcomes, and adverse events were analyzed. @*Results@#A total of 98 patients (50 in the H-knife group and 48 in the IT-knife group) were analyzed. The median total procedure time was 11.9 minutes (range, 4.4–47.2 minutes) in the H-knife group and 12.7 minutes (range, 5.2–137.7 minutes) in the IT-knife group (P=0.209).Unlike the IT-knife group, which required additional devices in all cases, no additional devices were used in the H-knife group (P<0.001). En-bloc resection was performed for all lesions in both groups. The incidence of adverse events was not significantly different between groups (4.0% in the H-knife group vs. 8.3% in the IT-knife group; P=0.431). @*Conclusions@#The newly developed hybrid device, the ClearCut™ Knife H-type, had comparable efficacy to the conventional IT knife for gastric ESD.

2023 Clinical Practice Guidelines for Diabetes Mellitus of the Korean Diabetes Association

In May 2023, the Committee of Clinical Practice Guidelines of the Korean Diabetes Association published the revised clinical practice guidelines for Korean adults with diabetes and prediabetes. We incorporated the latest clinical research findings through a comprehensive systematic literature review and applied them in a manner suitable for the Korean population. These guidelines are designed for all healthcare providers nationwide, including physicians, diabetes experts, and certified diabetes educators who manage patients with diabetes or individuals at risk of developing diabetes. Based on recent changes in international guidelines and the results of a Korean epidemiological study, the recommended age for diabetes screening has been lowered. In collaboration with the relevant Korean medical societies, recently revised guidelines for managing hypertension and dyslipidemia in patients with diabetes have been incorporated into this guideline. An abridgment containing practical information on patient education and systematic management in the clinic was published separately.

Clinical practice guidelines for percutaneous endoscopic gastrostomy

With an aging population, the number of patients with difficulty in swallowing due to medical conditions is gradually increasing. In such cases, enteral nutrition is administered through a temporary nasogastric tube. However, the long-term use of a nasogastric tube leads to various complications and a decreased quality of life. Percutaneous endoscopic gastrostomy (PEG) is the percutaneous placement of a tube into the stomach that is aided endoscopically and may be an alternative to a nasogastric tube when enteral nutritional is required for four weeks or more. This paper is the first Korean clinical guideline for PEG developed jointly by the Korean College of Helicobacter and Upper Gastrointestinal Research and led by the Korean Society of Gastrointestinal Endoscopy. These guidelines aimed to provide physicians, including endoscopists, with the indications, use of prophylactic antibiotics, timing of enteric nutrition, tube placement methods, complications, replacement, and tube removal for PEG based on the currently available clinical evidence.

Eradication of Helicobacter pylori Infection Using 7-day PCR-based Tailored Therapy

Background/Aims@#Standard triple therapy (STT; proton pump inhibitor [PPI]+clarithromycin+amoxicillin) used for Helicobacter pylori (H. pylori) eradication has shown low treatment success rates in recent years, which is most likely attributable to increased clarithromycin resistance. In this study, we compared treatment success rates of tailored therapy (TT) using real-time polymerase chain reaction (RT-PCR) and empirical STT. @*Methods@#This retrospective study included 650 patients with H. pylori infection, who visited Eunpyeong St. Mary’s Hospital in Korea; 343 patients received TT based on RT-PCR assays, and 307 patients received STT. Eradication success was defined as a negative 13C-urea breath test result 4~8 weeks after treatment completion. Patients who failed first-line therapy and those with clarithromycin resistance received bismuth-containing quadruple therapy (BQT; PPI+bismuth+metronidazole+tetracycline). @*Results@#Intention-to-treat analysis showed that H. pylori eradication rates were higher in patients who received RT-PCR–based TT than in those who were treated using empirical STT (80.5% [190/236] vs. 70.4% [216/307], P=0.069). Per-protocol (PP) analysis showed similar results (84.4% [190/225] vs. 74.7% [216/289], P=0.007). PP analysis showed that 7-day TT treatment was associated with a higher eradication rate than that observed with 10- to 14-day STT (85.2% [178/209] vs. 73.8% [59/80], P=0.029). The clarithromycin resistance rate was 27.9% (87/312). The eradication success rate was 89.2% (74/83) in patients with clarithromycin resistance, who received BQT as first-line therapy. @*Conclusions@#The treatment success rate was higher in patients who received 7-day RT-PCR–based TT than in those who were administered 10- to 14-day empirical treatment.

Clinical Practice Guideline for Percutaneous Endoscopic Gastrostomy / 대한소화기학회지

With an aging population, the number of patients with difficulty in swallowing due to medical conditions is gradually increasing. In such cases, enteral nutrition is administered through a temporary nasogastric tube. However, the long-term use of a nasogastric tube leads to various complications and a decreased quality of life. Percutaneous endoscopic gastrostomy (PEG) is the percutaneous place­ment of a tube into the stomach that is aided endoscopically and may be an alternative to a nasogastric tube when enteral nutritional is required for four weeks or more. This paper is the first Korean clinical guideline for PEG developed jointly by the Korean College of Helicobacter and Upper Gastrointestinal Research and led by the Korean Society of Gastrointestinal Endoscopy. These guidelines aimed to provide physicians, including endoscopists, with the indications, use of prophylactic antibiotics, timing of enteric nutrition, tube placement methods, complications, replacement, and tubes removal for PEG based on the currently available clinical evidence.

A Study of the Molecular Characteristics of the Serologic D-- Blood Type in Korean Blood Donors / 대한수혈학회지

Background@#The Korean Red Cross has conducted serologic tests for C, c, E, e antigens and found 18 D-- donors.In this study, we performed RHCE genotyping to identify the molecular characteristics of the serologic D-- blood type in Korean blood donors. @*Methods@#We performed RHCE-specific PCR-based electrophoresis to check the amplification pattern of each exon.Sanger sequencing was conducted to find the variants in the nucleotide sequence. We determined the RHCE genotype based on the electrophoresis and Sanger sequencing results. @*Results@#Total eight out of 18 D-- donors were participated in this research. In the PCR-based electrophoresis tests, RHCE exons 3, 4, and 6 were not amplified in samples #4, #6, and #8. Also, sample #2 showed an abnormal band pattern of RHCE exon 9. The Sanger sequencing results showed that the nucleotide sequences of the RHCE exons 5, 7, and 8 in samples #4, #6 and #8 corresponded to the nucleotide sequences of RHD exons 5, 7, and 8, respectively, suggesting the possibility of a RHCE-RHD(3-8)-RHCE hybrid allele. The nucleotide sequences of RHCE exons 7 and 8 in sample #2 were the same as the nucleotide sequences of RHD exons 7 and 8, respectively.In samples #1, #3, #5, and #7, no specific variants known to cause D-- phenotype were found. @*Conclusion@#RHCE genes partially replaced by the RHD genes were found in four out of eight participants and three of them were identified as ?RHCE*02N.07, which is known as the RHCE null allele. A further study with complete RHCE sequencing could be helpful for an understanding of the molecular mechanisms of samples in which no significant variants were identified.

Ultrasonography of intrascrotal torsed appendages: size and interval between symptom onset and the ultrasonographic examination according to echogenicity

Purpose@#This study investigated the size of torsed appendages and the interval between symptom onset and the ultrasonographic examination according to the echogenicity of the torsed appendages. @*Methods@#This was a retrospective analysis of 54 cases in 46 patients with torsion of the testicular appendages between December 2008 and July 2021. Eight patients received follow-up ultrasonography 7-48 days after initial ultrasonography. The echogenicity of torsed appendages was classified into three groups: hypoechoic, hyperechoic, or isoechoic. @*Results@#The 54 torsed appendages were hypoechoic (n=40), hyperechoic (n=9), or isoechoic (n=5). The size of the torsed appendages ranged from 4 to 14 mm (8.0±3.1 mm) in hypoechoic torsed appendages and from 2.6 to 5.0 mm (3.7±0.9 mm) in hyperechoic torsed appendages. The interval between symptom onset and the ultrasonographic examination ranged from 0 to 17 days (4.2±4.4 days) in hypoechoic torsed appendages and from 8 to 48 days (29.8±16.0 days) in hyperechoic torsed appendages. The hyperechoic torsed appendages were smaller and had longer intervals between symptom onset and the ultrasonographic examination than the hypoechoic torsed appendages (P<0.05). Three hypoechoic torsed appendages and a single isoechoic torsed appendage on initial ultrasonography became hyperechoic on follow-up ultrasonography. @*Conclusion@#The size of the torsed appendages and the interval between symptom onset and the ultrasonographic examination varied according to the echogenicity of the torsed appendages. The hyperechoic torsed appendages were smaller and had longer intervals until the examination than the hypoechoic torsed appendages.

Korean Practice Guidelines for Gastric Cancer 2022: An Evidence-based, Multidisciplinary Approach

Gastric cancer is one of the most common cancers in Korea and the world. Since 2004, this is the 4th gastric cancer guideline published in Korea which is the revised version of previous evidence-based approach in 2018. Current guideline is a collaborative work of the interdisciplinary working group including experts in the field of gastric surgery, gastroenterology, endoscopy, medical oncology, abdominal radiology, pathology, nuclear medicine, radiation oncology and guideline development methodology. Total of 33 key questions were updated or proposed after a collaborative review by the working group and 40 statements were developed according to the systematic review using the MEDLINE, Embase, Cochrane Library and KoreaMed database. The level of evidence and the grading of recommendations were categorized according to the Grading of Recommendations, Assessment, Development and Evaluation proposition. Evidence level, benefit, harm, and clinical applicability was considered as the significant factors for recommendation. The working group reviewed recommendations and discussed for consensus. In the earlier part, general consideration discusses screening, diagnosis and staging of endoscopy, pathology, radiology, and nuclear medicine. Flowchart is depicted with statements which is supported by meta-analysis and references. Since clinical trial and systematic review was not suitable for postoperative oncologic and nutritional follow-up, working group agreed to conduct a nationwide survey investigating the clinical practice of all tertiary or general hospitals in Korea. The purpose of this survey was to provide baseline information on follow up. Herein we present a multidisciplinary-evidence based gastric cancer guideline.

Production of polyhydroxyalkanoates containing monomers conferring amorphous and elastomeric properties from renewable resources: Current status and future perspectives.

Petrochemical-based plastics cause environmental pollution and threaten humans and ecosystems. Polyhydroxyalkanoate (PHA) is considered a promising alternative to nondegradable plastics since it is eco-friendly and biodegradable polymer having similar properties to conventional plastics. PHA's material properties are generally determined by composition and type of monomers in PHA. PHA can be designed in tailor-made manner for their suitable application areas. Among many monomers in PHAs, ω-hydroxalkanoates such as 3-hydroxypropionate (3HP), 4-hydroxybutyrate (4HB), 5-hydroxyvalerate (5HV), and 6-hydroxyhexanoate (6HHx) and medium-chain-length 3-hydroxyalkanoate such as 3-hydroxyhexanoate (3HHx) and 4-hydroxyvalerate (4HV), have been examined as potential monomers able to confer amorphous and elastomer properties when these are incorporated as comonomer in poly(3-hydroxybutyrate) copolymer that has 3HB as main monomer along with comonomers in different monomer fraction. Herein, recent advances in production of PHAs designed to have amorphous and elastomeric properties from renewable sources such as lignocellulose, levulinic acid, crude glycerol, and waste oil are discussed.

Artificial intelligence in perioperative medicine: a narrative review.

Recent advancements in artificial intelligence (AI) techniques have enabled the development of accurate prediction models using clinical big data. AI models for perioperative risk stratification, intraoperative event prediction, biosignal analyses, and intensive care medicine have been developed in the field of perioperative medicine. Some of these models have been validated using external datasets and randomized controlled trials. Once these models are implemented in electronic health record systems or software medical devices, they could help anesthesiologists improve clinical outcomes by accurately predicting complications and suggesting optimal treatment strategies in real-time. This review provides an overview of the AI techniques used in perioperative medicine and a summary of the studies that have been published using these techniques. Understanding these techniques will aid in their appropriate application in clinical practice.

2021 Korean Heart Rhythm Society Guidelines for Catheter or Surgical Ablation of Atrial Fibrillation / 대한내과학회지

Rhythm control therapy is used in atrial fibrillation (AF) management to improve AF-related symptoms along with rate control. AF catheter ablation is effective in maintaining sinus rhythm and has an acceptable complication rate. Compared with antiarrhythmic drugs, AF catheter ablation is superior with respect to arrhythmia-free survival and improvement in the quality of life. Therefore, AF ablation is recommended for rhythm control after the failure of antiarrhythmic drugs and is sometimes considered a first-line therapy for AF patients. Radiofrequency and cryoballoon ablation show similar efficacy, with slightly different complication profiles. Surgery for AF is also an effective rhythm control therapy and should be considered in patients undergoing cardiac surgery or in those with failed catheter ablation. For patients undergoing AF catheter ablation, performing ablation under uninterrupted warfarin or non-vitamin K oral anticoagulant treatment is recommended for periprocedural stroke risk management. Here, we review existing data and discuss the general principles of AF catheter and surgical ablation in patients with AF.

Association between the Persistence of Obesity and the Risk of Gastric Cancer: A Nationwide Population-Based Study / Journal of the Korean Cancer Association, 대한암학회지

Purpose@#There remains controversy about relationship between obesity and gastric cancer. We aimed to examine the association using obesity-persistence. @*Materials and Methods@#We analyzed a nationwide population-based cohort which underwent health check-up between 2009 and 2012. Among them, those who had annual examinations during the last 5 years were selected. Gastric cancer risk was compared between those without obesity during the 5 years (never-obesity group) and those with obesity diagnosis during the 5 years (non-persistent obesity group; persistent obesity group). @*Results@#Among 2,757,017 individuals, 13,441 developed gastric cancer after median 6.78 years of follow-up. Gastric cancer risk was the highest in persistent obesity group (incidence rate [IR], 0.89/1,000 person-years; hazard ratio [HR], 1.197; 95% confidence interval [CI], 1.117 to 1.284), followed by non-persistent obesity group (IR, 0.83/1,000 person-years; HR, 1.113; 95% CI, 1.056 to 1.172) compared with never-obesity group. In subgroup analysis, this positive relationship was true among those < 65 years old and male. Among heavy-drinkers, the impact of obesity-persistence on the gastric cancer risk far increased (non-persistent obesity: HR, 1.297; 95% CI, 1.094 to 1.538; persistent obesity: HR, 1.351; 95% CI, 1.076 to 1.698). @*Conclusion@#Obesity-persistence is associated with increased risk of gastric cancer in a dose-response manner, especially among male < 65 years old. The risk raising effect was much stronger among heavy-drinkers.

Dupilumab therapy in a 12-year-old boy with Kimura disease, allergic rhinitis, and IgG3 deficiency

Kimura disease is characterized by painless subcutaneous masses, usually in the head and neck area as well as serum/tissue eosinophilia and elevated serum IgE levels. Various treatment methods, such as surgical excision, corticosteroids, and radiotherapy, have been suggested, but none of these are considered standard therapy due to high recurrence rates. Dupilumab is a human monoclonal antibody that binds to the alpha subunit of IL-4 receptor for IL-4 and IL-13 and inhibits T helper 2 (Th2) response, which plays an important role in the pathogenesis of allergic diseases, such as atopic dermatitis, asthma, and nasal polyps. Kimura disease has also been shown to increase CD4+Th2 cells and Th2 cytokines. We report a case of a 12-year-old boy who had subcutaneous neck and orbital masses of Kimura disease concurrent with allergic rhinitis, decreased lung function, and IgG subclass deficiency. The masses did not improve with omalizumab or immunomodulatory agents, but resolved with dupilumab. Considering potential side effects of steroids or immunosuppressant agents, dupilumab may be an option for initial treatment with Kimura diseases in children.

Artificial intelligence in perioperative medicine: a narrative review / 대한마취과학회지

Recent advancements in artificial intelligence (AI) techniques have enabled the development of accurate prediction models using clinical big data. AI models for perioperative risk stratification, intraoperative event prediction, biosignal analyses, and intensive care medicine have been developed in the field of perioperative medicine. Some of these models have been validated using external datasets and randomized controlled trials. Once these models are implemented in electronic health record systems or software medical devices, they could help anesthesiologists improve clinical outcomes by accurately predicting complications and suggesting optimal treatment strategies in real-time. This review provides an overview of the AI techniques used in perioperative medicine and a summary of the studies that have been published using these techniques. Understanding these techniques will aid in their appropriate application in clinical practice.

Esophageal Microbiota and Nutritional Intakes in Patients With Achalasia Before and After Peroral Endoscopic Myotomy

Background/Aims@#The composition of the microbiota in the esophagus is only partially understood, especially in patients with achalasia. We aim to investigate the esophageal microbial community and nutritional intakes in patients with achalasia before and after peroral endoscopicmyotomies (POEM). @*Methods@#Twenty-nine patients were prospectively enrolled from 4 referral institutions across Korea. We collected esophageal samples (mucosal biopsies and retention fluid) and conducted dietary surveys for nutritional intake before and 8 weeks after POEM. The esophageal microbiota was analyzed by 16S rRNA gene sequencing targeting the V3-V4 region. @*Results@#Out of the 105 samples from 29 patients, 99 samples were subjected to microbial bioinformatic analysis after quality control, which excluded samples with no amplification or low-quality sequence data. The overall esophageal microbial compositions of patientswith achalasia showed that Firmicutes, Bacteroidetes, Proteobacteria, Actinobacteria, and Fusobacteria were the dominant phyla, representing over 95% of the total phyla in all groups. At the genus level, Streptococcus was the most abundant in all groups. The observed operational taxonomic unit number was significantly higher in the retention fluid than in the tissue biopsies. However, the esophageal microbial composition showed no significant changes 8 weeks post POEM. The dietary survey analysis showed that nutritional intake significantly improved post POEM. @*Conclusion@#This study determined the unique esophageal microbial composition of patients with achalasia, and also found that the microbial composition did not significantly change after POEM in the short-term, despite a significant improvement in the nutritional intake.