OBJECTIVE: Enhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice. METHODS: Researches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized. RESULTS: Based on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics. CONCLUSION: Researchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.
Bays ; Forests ; Health Care Sector ; Internet ; Learning ; Machine Learning ; Mental Health ; Residence Characteristics ; Sample Size ; Support Vector Machine

PURPOSE: Despite the well-known anti-inflammatory effects of vitamin D in periodontal health, its mechanism has not been fully elucidated. In the present study, the effect of vitamin D on strengthening E-cadherin junctions (ECJs) was explored in human gingival keratinocytes (HGKs). ECJs are the major type of intercellular junction within the junctional epithelium, where loose intercellular junctions develop and microbial invasion primarily occurs. METHODS: HOK-16B cells, an immortalized normal human gingival cell line, were used for the study. To mimic the inflammatory environment, cells were treated with tumor necrosis factor-alpha (TNF-α). Matrix metalloproteinases (MMPs) in the culture medium were assessed by an MMP antibody microarray and gelatin zymography. The expression of various molecules was investigated using western blotting. The extent of ECJ development was evaluated by comparing the average relative extent of the ECJs around the periphery of each cell after immunocytochemical E-cadherin staining. Vitamin D receptor (VDR) expression was examined via immunohistochemical analysis. RESULTS: TNF-α downregulated the development of the ECJs of the HGKs. Dissociation of the ECJs by TNF-α was accompanied by the upregulation of MMP-9 production and suppressed by a specific MMP-9 inhibitor, Bay 11-7082. Exogenous MMP-9 decreased the development of ECJs. Vitamin D reduced the production of MMP-9 and attenuated the breakdown of ECJs in the HGKs treated with TNF-α. In addition, vitamin D downregulated TNF-α-induced nuclear factor kappa B (NF-κB) signaling in the HGKs. VDR was expressed in the gingival epithelium, including the junctional epithelium. CONCLUSIONS: These results suggest that vitamin D may avert TNF-α-induced downregulation of the development of ECJs in HGKs by decreasing the production of MMP-9, which was upregulated by TNF-α. Vitamin D may reinforce ECJs by downregulating NF-κB signaling, which is upregulated by TNF-α. Strengthening the epithelial barrier may be a way for vitamin D to protect the periodontium from bacterial invasion.
Bays ; Blotting, Western ; Cadherins ; Cell Line ; Down-Regulation ; Epithelial Attachment ; Epithelium ; Gelatin ; Humans ; Intercellular Junctions ; Keratinocytes ; Matrix Metalloproteinase 9 ; Matrix Metalloproteinases ; NF-kappa B ; Periodontium ; Receptors, Calcitriol ; Tumor Necrosis Factor-alpha ; Up-Regulation ; Vitamin D ; Vitamins

Inferior meatal antrostomy (IMA) is a widely performed surgical technique to treat postoperative maxillary mucocele. The method is safe and easy to perform, without major complications compared with other approaches. Facial pain after IMA is a rare clinical entity that can be challenging to diagnose and treat. The authors present an unusual case of acute facial neuralgia triggered by cold air that developed after IMA. The antrostomy was located at the anterior-most part of the inferior meatus, and the inlet size was relatively large compared with the size of the remaining sinus. Surgical narrowing of the antrostomy inlet using endoscopy dramatically reduced the symptoms, and symptom relief was maintained for up to one year after surgery.
Bays ; Cartilage ; Endoscopy ; Facial Neuralgia ; Facial Pain ; Methods ; Mucocele ; Transplants

Parkinson's disease (PD) is a widespread degenerative syndrome that affects the nervous system. Its early appearing symptoms include tremor, rigidity, and vocal impairment (dysphonia). Consequently, speech indicators are important in the identification of PD based on dysphonic signs. In this regard, computer-aided-diagnosis systems based on machine learning can be useful in assisting clinicians in identifying PD patients. In this work, we evaluate the performance of machine learning based techniques for PD diagnosis based on dysphonia symptoms. Several machine learning techniques were considered and trained with a set of twenty-two voice disorder measurements to classify healthy and PD patients. These machine learning methods included linear discriminant analysis (LDA), k nearest-neighbors (k-NN), naïve Bayes (NB), regression trees (RT), radial basis function neural networks (RBFNN), support vector machine (SVM), and Mahalanobis distance classifier. We evaluated the performance of these methods by means of a tenfold cross validation protocol. Experimental results show that the SVM classifier achieved higher average performance than all other classifiers in terms of overall accuracy, G-mean, and area under the curve of the receiver operating characteristic plot. The SVM classifier achieved higher performance measures than the majority of the other classifiers also in terms of sensitivity, specificity, and F-measure statistics. The LDA, k-NN and RT achieved the highest average precision. The RBFNN method yielded the highest F-measure.; however, it performed poorly in terms of other performance metrics. Finally, t tests were performed to evaluate statistical significance of the results, confirming that the SVM outperformed most of the other classifiers on the majority of performance measures. SVM is a promising method for identifying PD patients based on classification of dysphonia measurements.
Bays ; Classification ; Diagnosis ; Dysphonia ; Humans ; Machine Learning ; Methods ; Nervous System ; Parkinson Disease ; ROC Curve ; Sensitivity and Specificity ; Support Vector Machine ; Trees ; Tremor ; Voice Disorders

The prevalence of metabolic syndrome (MS) in the nonobese population is not low. However, the identification and risk mitigation of MS are not easy in this population. We aimed to develop an MS prediction model using genetic and clinical factors of nonobese Koreans through machine learning methods. A prediction model for MS was designed for a nonobese population using clinical and genetic polymorphism information with five machine learning algorithms, including naïve Bayes classification (NB). The analysis was performed in two stages (training and test sets). Model A was designed with only clinical information (age, sex, body mass index, smoking status, alcohol consumption status, and exercise status), and for model B, genetic information (for 10 polymorphisms) was added to model A. Of the 7,502 nonobese participants, 647 (8.6%) had MS. In the test set analysis, for the maximum sensitivity criterion, NB showed the highest sensitivity: 0.38 for model A and 0.42 for model B. The specificity of NB was 0.79 for model A and 0.80 for model B. In a comparison of the performances of models A and B by NB, model B (area under the receiver operating characteristic curve [AUC] = 0.69, clinical and genetic information input) showed better performance than model A (AUC = 0.65, clinical information only input). We designed a prediction model for MS in a nonobese population using clinical and genetic information. With this model, we might convince nonobese MS individuals to undergo health checks and adopt behaviors associated with a preventive lifestyle.
Alcohol Drinking ; Bays ; Body Mass Index ; Classification ; Life Style ; Machine Learning ; Polymorphism, Genetic ; Prevalence ; ROC Curve ; Sensitivity and Specificity ; Smoke ; Smoking

In Korea, small octopus (Octopus minor) and webfoot octopus (Octopus ocellatus) are food items and fatal laryngeal choking due to ingestion of live octopus is not uncommon. We recently encountered two autopsy cases of accidental choking on small octopus and webfoot octopus. Case 1 involved a 58-year-old fisherman who ingested two live webfoot octopuses in his fishing boat and collapsed. He was immediately taken to the hospital but died. During autopsy, one of the webfoot octopuses was found between his pharynx and esophagus; it was obstructing the epiglottis and upper esophagus. His blood alcohol concentration was 0.140%. Case 2 involved a 55-year-old man who ingested an intact body part of a small octopus and was found dead in his house. He had a history of cerebral infarction and angina pectoris. During autopsy, an intact body part of the small octopus was found to be lodged in the laryngeal inlet.
Airway Obstruction ; Angina Pectoris ; Autopsy ; Bays ; Blood Alcohol Content ; Cerebral Infarction ; Eating ; Epiglottis ; Esophagus ; Humans ; Korea ; Larynx ; Middle Aged ; Octopodiformes ; Pharynx ; Ships

OBJECTIVES: The objective of this study was to compare the performance of two popularly used early sepsis diagnostic criteria, systemic inflammatory response syndrome (SIRS) and quick Sepsis-related Organ Failure Assessment (qSOFA), using statistical and machine learning approaches. METHODS: This retrospective study examined patient visits in Emergency Department (ED) with sepsis related diagnosis. The outcome was 28-day in-hospital mortality. Using odds ratio (OR) and modeling methods (decision tree [DT], multivariate logistic regression [LR], and naïve Bayes [NB]), the relationships between diagnostic criteria and mortality were examined. RESULTS: Of 132,704 eligible patient visits, 14% died within 28 days of ED admission. The association of qSOFA ≥2 with mortality (OR = 3.06; 95% confidence interval [CI], 2.96–3.17) greater than the association of SIRS ≥2 with mortality (OR = 1.22; 95% CI, 1.18–1.26). The area under the ROC curve for qSOFA (AUROC = 0.70) was significantly greater than for SIRS (AUROC = 0.63). For qSOFA, the sensitivity and specificity were DT = 0.39, LR = 0.64, NB = 0.62 and DT = 0.89, LR = 0.63, NB = 0.66, respectively. For SIRS, the sensitivity and specificity were DT = 0.46, LR = 0.62, NB = 0.62 and DT = 0.70, LR = 0.59, NB = 0.58, respectively. CONCLUSIONS: The evidences suggest that qSOFA is a better diagnostic criteria than SIRS. The low sensitivity of qSOFA can be improved by carefully selecting the threshold to translate the predicted probabilities into labels. These findings can guide healthcare providers in selecting risk-stratification measures for patients presenting to an ED with sepsis.
Artificial Intelligence ; Bays ; Diagnosis ; Emergency Service, Hospital ; Health Personnel ; Hospital Mortality ; Humans ; Logistic Models ; Machine Learning* ; Medical Informatics ; Methods* ; Mortality ; Odds Ratio ; Retrospective Studies ; ROC Curve ; Sensitivity and Specificity ; Sepsis ; Severity of Illness Index ; Systemic Inflammatory Response Syndrome ; Trees

OBJECTIVES: Clusterin (CLU) is known as apolipoprotein J, and has three isoforms with different biological functions. CLU is associated with various diseases such as Alzheimer disease, atherosclerosis, and some malignancies. Recent studies report an association of CLU with inflammation and immune response in inflammatory airway diseases. However, the effect of CLU on mucin secretion of airway epithelial cells has not yet been understood. Therefore, the effect and brief signaling pathway of CLU on MUC5AC (as a major secreted mucin) expression were investigated in human airway epithelial cells. METHODS: In the tissues of nasal polyp and normal inferior turbinate, the presence of MUC5AC and CLU was investigated using immunohistochemical stain and Western blot analysis. In mucin-producing human NCI-H292 airway epithelial cells and primary cultures of normal nasal epithelial cells, the effect and nuclear factor kappa-light-chain-enhancer of activated B cells (NF-κB) signaling pathway of CLU on MUC5AC expression were investigated using immunohistochemical stain, reverse transcription-polymerase chain reaction, real-time polymerase chain reaction, enzyme immunoassay, and Western blot analysis. RESULTS: In the nasal polyps, MUC5AC and CLU were abundantly present in the epithelium on immunohistochemical stain, and nuclear CLU (nCLU) was strongly detected on Western blot analysis. In human NCI-H292 airway epithelial cells or the primary cultures of normal nasal epithelial cells, recombinant nCLU increased MUC5AC expression, and significantly activated phosphorylation of NF-κB. And BAY 11-7085 (a specific NF-κB inhibitor) and knockdown of NF-κB by NF-κB siRNA (small interfering RNA) significantly attenuated recombinant nCLU-induced MUC5AC expression. CONCLUSION: These results suggest that nCLU induces MUC5AC expression via the activation of NF-κB signaling pathway in human airway epithelial cells.
Alzheimer Disease ; Atherosclerosis ; B-Lymphocytes ; Bays ; Blotting, Western ; Clusterin* ; Epithelial Cells* ; Epithelium ; Humans* ; Immunoenzyme Techniques ; Inflammation ; Mucins ; Nasal Polyps ; NF-kappa B ; Phosphorylation ; Protein Isoforms ; Real-Time Polymerase Chain Reaction ; RNA, Small Interfering ; Turbinates

BACKGROUND: The alar rim is a complex structure that ensures the competence of the external valves and the patency of inlets to the nasal airways. Retraction of the alar rim is caused by congenital malpositioning, hypoplasia, or surgical weakening of the lateral crura, with the potential for both functional and aesthetic ramifications. Most previously introduced procedures involved a relatively long operation time and relatively high risks of surgical complications. The purpose of this study is to introduce a novel surgical technique for alar rim connection and to present its results. METHODS: After marking the extent of the correction, the recipient alar bed was created by making an incision through the vestibular skin 2-mm cephalad to the rim. Then, the composite graft was harvested from the cymba concha by removing the cartilage with its adherent anterior skin. According to the degree of retraction, the harvested composite graft was divided into 2 pieces considering the symmetry of both alar rims. The composite grafts were inserted into the defects and primary closure was done at the donor site. RESULTS: Our surgical technique was used to correct 12 retracted alar rims in 6 patients. Caudal advancement of the alar rims was observed and the contour of the ala was corrected in all 6 patients. The mean length of follow-up was 1-year, and there were no postoperative complications, such as graft loss or disruption. CONCLUSIONS: The alar rim composite graft is a safe and simple technique for correction of short nostril and caudal transposition of the retracted alar rim.
Bays ; Cartilage ; Esthetics ; Follow-Up Studies ; Humans ; Mental Competency ; Nasal Cartilages ; Nose ; Postoperative Complications ; Skin ; Tissue Donors ; Transplants*

BACKGROUND/AIMS: MicroRNAs (miRNAs) regulate gene expression. We assess miRNA regulation by Helicobacter pylori infection and elucidate their role in H. pylori-infected gastric epithelial cells. METHODS: The relationship between miRNA expression and DNA methylation was examined. Cells were treated with the nuclear factor-kappaB (NF-κB) inhibitor Bay 11-7082 to determine the relationship between miRNA expression and NF-κB signal transduction. RESULTS: In the negative control cells infected with H. pylori 26695, the expression of six miRNAs was increased, whereas the expression of five miRNAs was decreased. The expression of upregulated miRNAs was increased when the host cells were treated with H. pylori and an NF-κB inhibitor. miR-127-5p, -155, and -181 were associated with increased interleukin 6 (IL-6) secretion in H. pylori infected cells treated with anti-miRNA. The expression of miR-155, -127-5p, -195, -216, -206, and -488 increased by approximately 3-fold following treatment with the methylation inhibitor Aza. CONCLUSIONS: We found novel miR-NAs in H. pylori-infected negative control cells using miRNA microarrays. Upregulated miRNA expression was inversely related to the transcription of NF-κB. miR-195 and miR-488 appear to play a pivotal role in controlling IL-6 activity in H. pylori infection. miRNA expression in H. pylori infection was affected by methylation.
Bays ; Cytokines ; DNA Methylation ; Epithelial Cells ; Gene Expression ; Helicobacter pylori* ; Helicobacter* ; Interleukin-6 ; Methylation ; MicroRNAs* ; NF-kappa B ; Signal Transduction