Objectives. Prognosticating idiopathic sudden sensorineural hearing loss (ISSNHL) is an important challenge. In our study, a dataset was split into training and test sets and cross-validation was implemented on the training set, thereby determining the hyperparameters for machine learning models with high test accuracy and low bias. The effectiveness of the following five machine learning models for predicting the hearing prognosis in patients with ISSNHL after 1 month of treatment was assessed: adaptive boosting, K-nearest neighbor, multilayer perceptron, random forest (RF), and support vector machine (SVM).Methods. The medical records of 523 patients with ISSNHL admitted to Korea University Ansan Hospital between January 2010 and October 2017 were retrospectively reviewed. In this study, we analyzed data from 227 patients (recovery, 106; no recovery, 121) after excluding those with missing data. To determine risk factors, statistical hypothesis tests (e.g., the two-sample t-test for continuous variables and the chi-square test for categorical variables) were conducted to compare patients who did or did not recover. Variables were selected using an RF model depending on two criteria (mean decreases in the Gini index and accuracy).Results. The SVM model using selected predictors achieved both the highest accuracy (75.36%) and the highest F-score (0.74) on the test set. The RF model with selected variables demonstrated the second-highest accuracy (73.91%) and F-score (0.74). The RF model with the original variables showed the same accuracy (73.91%) as that of the RF model with selected variables, but a lower F-score (0.73). All the tested models, except RF, demonstrated better performance after variable selection based on RF.Conclusion. The SVM model with selected predictors was the best-performing of the tested prediction models. The RF model with selected predictors was the second-best model. Therefore, machine learning models can be used to predict hearing recovery in patients with ISSNHL.

Background: Pregnant women are at high risk of influenza-related morbidity and mortality. In addition, maternal influenza infection may lead to adverse birth outcomes. However, there is insufficient data on long-term impact of maternal influenza infection. Methods: This study was conducted to assess the impact of maternal influenza infection on birth outcomes and long-term influence on infants by merging the Korea National Health Insurance (KNHI) claims database and National Health Screening Program for Infants and Children (NHSP-IC). Mother-offspring pairs were categorized by maternal influenza infection based on the ICD-10 code. Results: Multivariate analysis revealed that maternal influenza infection significantly increased the risk of preterm birth (OR 1.408) and low birth weight (OR 1.198) irrespective of gestational age. The proportion of low birth weight neonates was significantly higher in influenza-infected women compared to those without influenza. However, since the fourth health screening (30–80 months after birth), the fraction of underweight was no longer different between children from influenza-infected and non-infected mothers, whereas the rates of overweight increased paradoxically in those born to mothers with influenza infection. Conclusions: Maternal influenza infection might have long-term effects on the health of children and adolescents even after infancy.

Recently, a number of data analysists have suffered from an insufficiency of historical observations in many real situations. To address the insufficiency of historical observations, self-starting forecasting process can be used. A self-starting forecasting process continuously updates the base models as new observations are newly recorded, and it helps to cope with inaccurate prediction caused by the insufficiency of historical observations. This study compared the properties of several exponentially weighted moving average methods as base models for the self-starting forecasting process. Exponentially weighted moving average methods are the most widely used forecasting techniques because of their superior performance as well as computational efficiency. In this study, we compared the performance of a self-starting forecasting process using different existing exponentially weighted moving average methods under various simulation scenarios and real case datasets. Through this study, we can provide the guideline for determining which exponentially weighted moving average method works best for the self-starting forecasting process.

Despite the importance of corporate foresight for innovation management, scholars have yet to identify the organisational processes through which corporate foresight influences a company’s innovativeness. Drawing on the resource-based view and dynamic capabilities theory, we developed a model and posited that the effect of corporate foresight on innovativeness is mediated by organisational learning, while the relationship between corporate foresight and organisational learning is moderated by integrative capabilities. We conducted an empirical study in the manufacturing industry and found support for the study model, in which the indirect effect of corporate foresight on innovativeness through organisational learning was conditional on the level of integrative capabilities. This study has theoretical and practical implications for a more nuanced understanding of corporate foresight and its effect on innovation management.

Wound healing mechanisms is believed to have effects similar to wound healing disorders in diabetic patients, including abnormal inflammatory cells, angiogenesis disorders, and reduced collagen synthesis. Therefore, reestablishment of structural and promoted angiogenesis could be beneficial to promote wound healing process. Therefore, we investigated whether the polydeoxyribonucleotide (PDRN) that was self-production in Korea, could be useful as an intradermal injection for promoting wound healing. Also, we validate for wound healing effect of PDRN using healing-impaired (db/db) mice. In this study, we confirmed the effects of PDRN by creating wound models in in vitro and in vivo model. Using an in vitro wound healing assay, we observed that PDRN stimulated closure of wounded monolayers of human fibroblast cells. PDRN (8.25 mg/ml) or phosphate-buffered saline (0.9% NaCl) was injected once daily into the dermis adjacent to the wound for 12 days after skin injury. Time course observations revealed that mice treated with PDRN showed accelerated wound closure and epidermal and dermal regeneration, enhanced angiogenesis. The wound area and depth decreased at 3, 6, 9, and 12 days after skin injury. Histological evaluation showed an increase of vascular endothelial growth factor, CD31, and collagen fibers in the PDRN group compared with the control group, indicating that PDRN was effective in the treatment of delayed wound healing caused by diabetes. This study suggests that our PDRN has a wound healing effect in transgenic animal models with cells and diabetes through angiogenesis.

Background and aim: Recent practice guidelines suggest healthy normal alanine aminotransferase (ALT) levels should be less than 30 U/L for males and 19 U/L for females. We tried to validate the prediction power of the “low cut off” for liver related outcomes in the general population. Methods: A total of 426,013 subjects were followed up for 10 years using the National Health Screening Cohort database. Prediction ability of long term mortality and liver related outcomes between conventional (<40 U/L in men and women) and low (<30 U/L in men and <19 U/L in women) ALT cut-off values were compared. Results: Both conventional and low ALT cut-offs predicted liver related unfavorable outcomes in Kaplan-Meier analysis. Following adjustment for age, body mass index, smoking, exercise, alcohol consumption, fasting blood glucose, and cholesterol via multivariate Cox regression, abnormal ALT using new ‘low ALT cut off’ was a significant independent predictor for liver-related mortality, HCC, and decompensated liver events. When the low cut-off criteria were added to the prediction model, the ability to predetect liver-related hard outcomes significantly increased in both men and women (p-values < 0.0001). The C-index values for predicting liver-related adverse events were the same in both ALT cut-offs, after adjusting confounding factors (C index value: 0.73~0.88). Conclusions: New low ALT cut-off showed good prediction power for liver related unfavorable outcomes.