Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Purpose: Accurate prediction of blood glucose variability is crucial for effective diabetes management, as both hypoglycemia and hyperglycemia are associated with increased morbidity and mortality. However, conventional predictive models rely primarily on patient-specific biometric data, often neglecting the influence of patient–provider interactions, which can significantly impact outcomes. This study introduces Cyclic Dual Latent Discovery (CDLD), a deep learning framework that explicitly models patient–provider interactions to improve prediction of blood glucose levels. By leveraging a real-world intensive care unit (ICU) dataset, the model captures latent attributes of both patients and providers, thus improving forecasting accuracy. Methods: ICU patient records were obtained from the MIMIC-IV v3.0 critical care database, including approximately 5,014 instances of patient–provider interaction. The CDLD model uses a cyclic training mechanism that alternately updates patient and provider latent representations to optimize predictive performance. During preprocessing, all numeric features were normalized, and extreme glucose values were capped at 500 mg/dL to mitigate the effect of outliers. Results: CDLD outperformed conventional models, achieving a root mean square error of 0.0852 on the validation set and 0.0899 on the test set, which indicates improved generalization. The model effectively captured latent patient–provider interaction patterns, yielding more accurate glucose variability predictions than baseline approaches. Conclusion Integrating patient–provider interaction modeling into predictive frameworks can increase blood glucose prediction accuracy. The CDLD model offers a novel approach to diabetes management, potentially paving the way for artificial intelligence-driven personalized treatment strategies.

Since the era of evidence-based medicine, it has become a matter of course to use statistics to create objective evidence in clinical research. As an extension of this, it has become essential in clinical research to calculate the correct sample size to demonstrate a clinically significant difference before starting the study.Also, because sample size calculation methods vary from study design to study design, there is no formula for sample size calculation that applies to all designs. It is very important for us to understand this. In this review, each sample size calculation method suitable for various study designs was introduced using the R program (R Foundation for Statistical Computing). In order for clinical researchers to directly utilize it according to future research, we presented practice codes, output results, and interpretation of results for each situation.

PURPOSE: Laparoscopic gastrectomy in early gastric cancer patients is accepted as standard, but it is sometimes challenging for patients who refuse blood transfusions such as Jehovah's Witness (JW) patients, because of the risk of bleeding related to radical lymph node dissection. This study aimed to confirm the adequacy and safety of laparoscopic gastrectomy with D1+ lymphadenectomy in JW patients. METHODS: From January 2009 to December 2015, 265 gastric cancer patients underwent laparoscopic gastrectomy in our institute. Among them, there were 25 JW, and they were statistically matched with 75 patients from the control groups depending on age, sex, and body mass index (BMI). In a retrospective review, patient laboratory values and their pathology results were analysed. RESULTS: There was no significant difference when comparing the clinical characteristics of JW and control groups. There was no statistically significant difference in blood loss or operation time between the two groups. Mean blood loss was 202.4±172.6 ml in the JW group and 179.7±163.8 ml in the control group (p=0.556). The number of retrieved lymph nodes was 27.8±13.9 in the JW group and 29.3±12.1 in the control group (p=0.607). Haemoglobin and haematocrit were measured after surgery and there was no statistically significant difference between the two groups. CONCLUSION: Laparoscopic D1+ gastrectomy in a JW may be performed with an equivalent risk to the control group. Laparoscopic gastrectomy can be applied to Jehovah's Witnesses if the specialied cancer center has sufficient experience in stomach cancer surgery, even if there is not enough experience in bloodless surgery.
Blood Transfusion ; Bloodless Medical and Surgical Procedures ; Body Mass Index ; Case-Control Studies* ; Gastrectomy ; Hemorrhage ; Humans ; Jehovah's Witnesses ; Lymph Node Excision* ; Lymph Nodes* ; Pathology ; Retrospective Studies ; Stomach Neoplasms*

Objectives: This study investigated the relationship between suicidal behavior and the use of methylphenidate (MPH) or atomoxetine (ATX) in patients with attention deficit hyperactivity disorder (ADHD). Methods: The Preferred Reporting Items for Systematic Review and Meta-Analysis guidelines were used to conduct a meta-analysis. The Physiotherapy Evidence Database scale was used to score the quality of the studies. Results: Nine studies were included in this quantitative analysis. The analysis included 602864 patients with ADHD (521125 and 81739 patients were taking methylphenidate [MPH group] and atomoxetine [ATX group], respectively) and 19230 healthy controls.The overall estimates were in the order of the control, MPH, and ATX groups; however, no statistically significant between-group difference was observed in the incidence of events (p=0.553 for control vs. MPH; p=1.000 for control vs. ATX; p=1.000 for MPH vs. ATX). Conclusion The rate of suicidal behavior was higher in the ADHD groups treated with MPH and ATX than in the control group. However, no statistically significant difference was observed between the ADHD groups treated with MPH and ATX, and the control group. Therefore, MPH and ATX did not increase suicidal behavior.

PURPOSE: The purpose of this study was to identify the influences of recognition on low fertility and views of marriage on childbirth will in university students. METHODS: Participants were 190 university students in Chungchungnamdo province, Korea. The data were collected from May to October 2018 and examined using descriptive statistics, t-test, analysis of variance, Pearson correlation and multiple regression with IBM SPSS Statistics ver. 24.0. RESULTS: Childbirth will was significantly correlated with recognition on low fertility (r=0.20, p=0.002) and views on marriage (r=0.53, p<0.001). Factors associated with childbirth will were views on marriage (β=0.24, p<0.001). CONCLUSION Theses results suggests that views on marriage have important influences on childbirth will in university students. To improve childbirth will, the positive views on marriage need to be formulated in university students.

Background: The present study employed National Health Insurance Data to explore complex regional pain syndrome (CRPS) updated epidemiology in a Korean context. Methods: A CRPS cohort for the period 2009-2016 was created based on Korean Standard Classification of Diseases codes alongside the national registry. The general CRPS incidence rate and the yearly incidence rate trend for every CRPS type were respectively the primary and secondary outcomes. Among the analyzed risk factors were age, sex, region, and hospital level for the yearly trend of the incidence rate for every CRPS. Statistical analysis was performed via the chi-square test and the linear and logistic linear regression tests. Results: Over the research period, the number of registered patients was 122,210.The general CRPS incidence rate was 15.83 per 100,000, with 19.5 for type 1 and 12.1 for type 2. The condition exhibited a declining trend according to its overall occurrence, particularly in the case of type 2 (P < 0.001). On the other hand, registration was more pervasive among type 1 compared to type 2 patients (61.7% vs.38.3%), while both types affected female individuals to a greater extent. Regarding age, individuals older than 60 years of age were associated with the highest prevalence in both types, regardless of sex (P< 0.001). Conclusions CRPS displayed an overall incidence of 15.83 per 100,000 in Korea and a declining trend for every age group which showed a negative association with the aging shift phenomenon.