Oral health plays an important role in people’s quality of life as it is related to eating, talking, and smiling. In recent years, many studies have utilized artificial intelligence for oral health care. Many studies have been published on tooth identification or recognition of dental diseases using X-ray images, but studies with RGB images are rarely found. In this paper, we propose a deep convolutional neural network (CNN) model that classifies teeth with periodontal diseases from optical color images captured in front of the mouth. A novel network module with one-dimensional convolutions in parallel was proposed and compared to the conventional models including ResNet152. In results, the proposed model achieved 11.45% higher than ResNet152 model, and it was proved that the proposed structure enhanced the training performances, especially when the amount of training data was insufficient. This paper shows the possibility of utilizing optical color images for the detection of periodontal diseases, which may lead to a mobile oral healthcare system in the future.

10–20% of COVID (Corona Virus Disease)-19 cases proceed to a severe stage, and age and the presence of comorbidity increased the risk of death from COVID-19. The identification of risk factors on progression to the severity stages is essential in providing more efficient and suitable management to COVID-19 patients. However, there is insufficient study on risk factors for severity stages of COVID-19 patients. In this study, 2959 confirmed COVID-19 patients were analyzed while using national data, COVID-19 patients Clinical Epidemiological Information provided from the Korea Disease Control and Prevention Agency. The epidemiological variable, hospital room, periods from confirmation to release, initial symptom and vital signs, underlying comorbidities, and initial blood variables were used to verify the relation with progression to severity stages of COVID-19 and severe COVID-19. The chi-square test, welch test, multiple regression and logistic regression analysis were performed. The ICU (Intensive Care Unit) admission rate of patients having characteristics, such as older age, male, abnormal BMI (Body Mass Index), high heart rate, high body temperature, fever, cough, sputum, sore throat, rhinorrhea, fatigue, dyspnea, change of consciousness, diabetes mellitus, hypertension, chronic artery disease, chronic kidney disease, cancer, dementia, abnormal hemoglobin, abnormal hematocrit, abnormal lymphocyte, abnormal platelets, and abnormal white blood cell were high. The risk factors for severe COVID-19 were older age, shorter hospitalization, abnormal lymphocyte, abnormal platelets, dyspnea, change of consciousness, and dementia. Whereas, significant predictors for progression to severity stages of COVID-19 were older age, longer period from confirmation to release, higher BMI, higher body temperature, abnormal lymphocyte, abnormal platelets, fever, no sore throat, dyspnea, no headache, COPD (Chronic Obstructive Pulmonary Disease), and dementia. Therefore, classifying patients with a high risk of severe stage of COVID-19 and managing patients by considering the risk factors could be helpful in the efficient management of COVID-19 patients.

OBJECTIVES:We investigated the risk of dementia in older adults with chronic periodontitis according to the severity of periodontitis.METHODS: Data on patients with chronic periodontitis were extracted from the National Health Insurance Service-Senior cohort database from 2002 to 2014. Among 52,728 subjects eligible for inclusion, 11,953 subjects had newly diagnosed mild chronic periodontitis (MCP), and 40,775 subjects had newly diagnosed severe chronic periodontitis (SCP). Two 1:1 propensity score matched cohorts were created with 8,624 patients each in the MCP and SCP groups. To analyze the risk of dementia, a Cox proportional-hazard model was used to calculate hazard ratios with 95% confidence intervals (CIs).RESULTS: In the Kaplan-Meier curve, the disease-free probability was significantly lower in the SCP group than in the MCP group (p for log-rank=0.001). In the multivariable-adjusted model, the HR for the occurrence of dementia in the SCP group compared to the MCP group was 1.15 (95% CI, 1.04 to 1.27; p=0.009). A subgroup analysis revealed a significant association between dementia and the severity of periodontitis, especially in subjects who were male, aged ≥70 years, and had comorbidities.CONCLUSIONS: Reducing the severity of chronic periodontitis can help to reduce the risk of dementia. Therefore, it is necessary to aggressively conduct early dementia-prevention programs for males under the age of 70 that include dental health to prevent the progression of periodontitis from mild to severe.

Proper moisture is an essential condition for maintaining the homeostasis of the body, enhancing immunity, and preventing constipation, and it is an indispensable substance for maintaining human life and health. As the bacteria that cause oral disease are affected by water intake, there is a strong relationship between water intake and oral disease. Therefore, the purpose of this study is to determine the effect of daily water intake on oral disease. The data analyzed were from a seven-year period (2010–2017) from the National Health and Nutrition Survey, conducted annually by the Korea Centers for Disease Control and Prevention. Out of a total of 48,422 people, 134 people in the ‘7 cups’ group were selected as subjects. Each time a person drank one less cup of water per day, the prevalence of periodontal disease increased by 1.018 times, the prevalence of dental caries increased by 1.032 times, and the experience of dental caries increased by 1.075 times. Even in Model 2, for which age and gender were adjusted, there was a significant effect. In addition, there was a significant impact in Model 3, which adjusted for oral health behavior, except for permanent caries prevalence. Based on the above results, oral health behavior and state were positive in those who consumed more water per day. Therefore, it is suggested that the government’s active promotion of water intake recommendations and policies should be prepared to include water intake as a component of improving oral health.

OBJECTIVES:The aim of this study was to determine whether the development of chronic periodontitis is more likely among patients who have been newly diagnosed with obstructive sleep apnea (OSA) through an analysis of representative data from the general population.METHODS: A nationwide, population-based, retrospective cohort study was conducted using patient records from the Korean National Health Insurance Service database. For the period 2004-2019, patient data were categorized into 2 groups: a diagnosis of OSA (747 subjects) and no diagnosis of OSA (1,494 subjects). Subsequently, 1:2 propensity score matching was performed to ensure the homogeneity of the 2 groups. To analyze the risk of incident chronic periodontitis, a Cox proportional-hazards model was used to calculate hazard ratios (HRs) with 95% confidence intervals (CIs).RESULTS: In the Kaplan-Meier curve, the disease-free probability was significantly lower in the OSA group than in the non-OSA group (p for log-rank test=0.001). The crude HR for the association between OSA and chronic periodontitis was 1.29 (95% CI, 1.16 to 1.43). The multivariable-adjusted HR was calculated at 1.28 (95% CI, 1.15 to 1.42).CONCLUSIONS: This study confirmed a relationship between OSA and chronic periodontitis. Therefore, OSA patients require oral care to prevent the progression of chronic periodontitis from mild to severe.

Automatic age estimation using panoramic dental radiographic images is an important procedure for forensics and personal oral healthcare. The accuracies of the age estimation have increased recently with the advances in deep neural networks (DNN), but DNN requires large sizes of the labeled dataset which is not always available. This study examined whether a deep neural network is able to estimate tooth ages when precise age information is not given. A deep neural network model was developed and applied to age estimation using an image augmentation technique. A total of 10,023 original images were classified according to age groups (in decades, from the 10s to the 70s). The proposed model was validated using a 10-fold cross-validation technique for precise evaluation, and the accuracies of the predicted tooth ages were calculated by varying the tolerance. The accuracies were 53.846% with a tolerance of ±5 years, 95.121% with ±15 years, and 99.581% with ±25 years, which means the probability for the estimation error to be larger than one age group is 0.419%. The results indicate that artificial intelligence has potential not only in the forensic aspect but also in the clinical aspect of oral care.