Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Background/Aims: Fexuprazan, a novel potassium-competitive acid blocker, was developed for treating acid-related disorders. Pharmacokinetic and pharmacodynamic properties of fexuprazan, unlike those of proton pump inhibitors, are independent of food effect. This study aims to evaluate differences in efficacy and safety of fexuprazan in patients with erosive esophagitis (EE) according to the timing of dosing. Methods: In this multicenter, open-label noninferiority study, patients who had typical reflux symptoms with endoscopically confirmed EE were randomized 1:1 to receive fexuprazan 40 mg daily 30 minutes before or after meal. Treatment was completed after 2 weeks or 4 weeks when healing was endoscopically confirmed. The primary endpoint was the proportion of patients with healed EE confirmed by endoscopy up to week 4. Safety endpoints included treatment-emergent adverse events (TEAEs). Results: In the prior-to-meal group (n = 89) and after-meal group (n = 86), 4-week EE healing rates were 98.77% and 100.00% (difference, 0.01%; 95% CI, –0.01% to 0.04%) and 2-week EE healing rates were 95.77% and 97.14% (difference, 0.01%; 95% CI, –0.05% to 0.07%), respectively. TEAEs were 9.78% and 8.70% in the prior-to-meal group and the after-meal group, respectively. Conclusions Non-inferiority analysis revealed that taking fexuprazan after meal was non-inferior to taking fexuprazan before meals in patients with EE. The frequency of adverse events was similar between the 2 study groups. The drug is safe and effective for healing EE regardless of the timing of dosing.

Background: Although the presence of both obesity and reduced muscle mass presents a dual metabolic burden and additively has a negative effect on a variety of cardiometabolic parameters, data regarding the associations between their combined effects and left ventricular diastolic function are limited. This study investigated the association between the ratio of skeletal muscle mass to visceral fat area (SVR) and left ventricular diastolic dysfunction (LVDD) in patients with preserved ejection fraction using random forest machine learning. Methods: In total, 1,070 participants with preserved left ventricular ejection fraction who underwent comprehensive health examinations, including transthoracic echocardiography and bioimpedance body composition analysis, were enrolled. SVR was calculated as an index of sarcopenic obesity by dividing the appendicular skeletal muscle mass by the visceral fat area. Results: In the random forest model, age and SVR were the most powerful predictors of LVDD. Multivariate logistic regression analysis demonstrated that older age (adjusted odds ratio [OR], 1.11; 95% confidence interval [CI], 1.07 to 1.15) and lower SVR (adjusted OR, 0.08; 95% CI, 0.01 to 0.57) were independent risk factors for LVDD.SVR showed a significant improvement in predictive performance and fair predictability for LVDD, with the highest area under the curve noted in both men and women, with statistical significance. In non-obese and metabolically healthy individuals, the lowest SVR tertile was associated with a greater risk of LVDD compared to the highest SVR tertile. Conclusion Decreased muscle mass and increased visceral fat were significantly associated with LVDD compared to obesity, body fat composition, and body muscle composition indices.

Objective: Adult attachment style is linked to how an individual responds to threats or stress and is known to be related to the onset of psychiatric symptoms such as depression. However, as the current assessment of attachment type mainly relies on self-report questionnaires and can be prone to bias, there is a need to incorporate physiological factors along with psychological symptoms and history in this process. We aimed to predict the measurement of two important types of adult attachment with heart rate variability (HRV), early life stress experience, and subjective psychiatric symptoms. Methods: Five hundred eighty-two subjects with depressive disorder were recruited retrospectively from January 2015 to June 2021. The experience of early life stress and psychiatric symptoms were collected, and HRV measures were obtained as input for an ensembled Voting Regressor model of machine learning-based regression models, including linear regression, ElasticNet, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost). Results: Model performances evaluated with R-squared score averaged across 30 seeds were 0.377 and 0.188 for anxious- and avoidant-attachment, respectively. Mean absolute error averaged to 13.251 and 12.083, respectively. Shapley value importance analysis indicated that for both attachment types, the most important feature was the trait-anxiety, followed by emotional abuse, state-anxiety or self-reported depressive symptoms, and fear or helplessness felt in the moment of an early life stressor. Conclusion Our results provide the evidence base that may be utilized in clinical settings to predict the degree of attachment type using bio-psychological factors.

Background/Aims: The Korean guidelines for Helicobacter pylori treatment were revised in 2020, however, the extent of adherence to these guidelines in clinical practice remains unclear. Herein, we initiated a prospective, nationwide, multicenter registry study in 2021 to evaluate the current management of H.pylori infection in Korea. Methods: This interim report describes the adherence to the revised guidelines and their impact on firstline eradication rates. Data on patient demographics, diagnoses, treatments, and eradication outcomes were collected using a web-based electronic case report form. Results: A total of 7,261 patients from 66 hospitals who received first-line treatment were analyzed.The modified intention-to-treat eradication rate for first-line treatment was 81.0%, with 80.4% of the prescriptions adhering to the revised guidelines. The most commonly prescribed regimen was the 14-day clarithromycin-based triple therapy (CTT; 42.0%), followed by tailored therapy (TT; 21.2%), 7-day CTT (14.1%), and 10-day concomitant therapy (CT; 10.1%). Time-trend analysis demonstrated significant increases in guideline adherence and the use of 10-day CT and TT, along with a decrease in the use of 7-day CTT (all p<0.001). Multivariate logistic regression analysis revealed that guideline adherence was significantly associated with first-line eradication success (odds ratio, 2.03; 95% confidence interval, 1.61 to 2.56; p<0.001). Conclusions The revised guidelines for the treatment of H. pylori infection have been increasingly adopted in routine clinical practice in Korea, which may have contributed to improved first-line eradication rates. Notably, the 14-day CTT, 10-day CT, and TT regimens are emerging as the preferred first-line treatment options among Korean physicians.

While scaphoid injuries are the most common carpal bone injuries, injuries to other carpal bones also occur frequently, accounting for about 40% of all carpal bone injuries. These non-scaphoid injuries are often complex, typically resulting from high-energy trauma and involving damage to two or more carpal bones or surrounding soft tissues. The carpus is a complex joint with eight carpal bones, making an accurate initial diagnosis challenging in many cases. A missed diagnosis or delayed treatment can lead to complications such as malunion, nonunion, avascular necrosis, and carpal instability. These complications can result in arthritis, neurovascular compression, and tendon rupture, causing chronic pain and functional impairment of the wrist joint. Therefore, careful attention to diagnosis and treatment is essential at the time of injury.

Objective: Adult attachment style is linked to how an individual responds to threats or stress and is known to be related to the onset of psychiatric symptoms such as depression. However, as the current assessment of attachment type mainly relies on self-report questionnaires and can be prone to bias, there is a need to incorporate physiological factors along with psychological symptoms and history in this process. We aimed to predict the measurement of two important types of adult attachment with heart rate variability (HRV), early life stress experience, and subjective psychiatric symptoms. Methods: Five hundred eighty-two subjects with depressive disorder were recruited retrospectively from January 2015 to June 2021. The experience of early life stress and psychiatric symptoms were collected, and HRV measures were obtained as input for an ensembled Voting Regressor model of machine learning-based regression models, including linear regression, ElasticNet, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost). Results: Model performances evaluated with R-squared score averaged across 30 seeds were 0.377 and 0.188 for anxious- and avoidant-attachment, respectively. Mean absolute error averaged to 13.251 and 12.083, respectively. Shapley value importance analysis indicated that for both attachment types, the most important feature was the trait-anxiety, followed by emotional abuse, state-anxiety or self-reported depressive symptoms, and fear or helplessness felt in the moment of an early life stressor. Conclusion Our results provide the evidence base that may be utilized in clinical settings to predict the degree of attachment type using bio-psychological factors.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Objective: Adult attachment style is linked to how an individual responds to threats or stress and is known to be related to the onset of psychiatric symptoms such as depression. However, as the current assessment of attachment type mainly relies on self-report questionnaires and can be prone to bias, there is a need to incorporate physiological factors along with psychological symptoms and history in this process. We aimed to predict the measurement of two important types of adult attachment with heart rate variability (HRV), early life stress experience, and subjective psychiatric symptoms. Methods: Five hundred eighty-two subjects with depressive disorder were recruited retrospectively from January 2015 to June 2021. The experience of early life stress and psychiatric symptoms were collected, and HRV measures were obtained as input for an ensembled Voting Regressor model of machine learning-based regression models, including linear regression, ElasticNet, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost). Results: Model performances evaluated with R-squared score averaged across 30 seeds were 0.377 and 0.188 for anxious- and avoidant-attachment, respectively. Mean absolute error averaged to 13.251 and 12.083, respectively. Shapley value importance analysis indicated that for both attachment types, the most important feature was the trait-anxiety, followed by emotional abuse, state-anxiety or self-reported depressive symptoms, and fear or helplessness felt in the moment of an early life stressor. Conclusion Our results provide the evidence base that may be utilized in clinical settings to predict the degree of attachment type using bio-psychological factors.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.