Search

Kyung Soo Woo, Su Hyun Bong, Tae Young Choi, Jun Won Kim Department of Psychiatry, Daegu Catholic University School of Medicine, Daegu, Republic of KoreaCorrespondence: Jun Won KimDepartment of Psychiatry, Daegu Catholic University School of Medicine, 33 Duryugongwon-ro 17-gil, Nam-gu, Daegu, 42472, Republic of KoreaTel +82-53-650-4332Fax +82-53-623-1694Email f_affection@naver.comPurpose: The excessive use of smartphones for social interaction is associated with mental health. However, few studies have considered the purpose of smartphone usage and screen time together. Therefore, we investigated the impact of smartphone purpose and screen time on mental health using data from the 2017 Korea Youth Risk Behavior Web-based Survey (KYRBS).Participants and Methods: A total of 54,243 adolescents answered items on purpose and screen time of smartphone use, stress perception, sleep dissatisfaction, depressive symptoms, and suicide-related indicators. The purpose of smartphone usage was categorized as social interaction and non-social interaction, and the daily smartphone screen time was classified into three categories: < 2 hours, ≥ 2 hours but < 4 hours, ≥ 4 hours per day.Results: We determined that, on weekdays, stress perception, sleep satisfaction, depressive symptoms, and suicide-related indicators worsened in both groups that used smartphones for ≥ 4 hours per day. When using smartphone for ≥ 2 hours but < 4 hours per day on weekdays, depending on the smartphone use purpose, mental health outcomes differed between the two groups. On weekends, using smartphones for ≥ 2 hours but < 4 hours per day worsened sleep satisfaction but decreased suicide-related indicators in both groups. Mental health outcomes improved when participants used smartphones for ≥ 2 hours but < 4 hours per day but worsened when smartphones were used for ≥ 4 hours per day on weekends.Conclusion: Recommended screen time of smartphone is different depending on the purpose

Background: COVID-19, which is accompanied by acute respiratory distress, multiple organ failure, and death, has spread worldwide much faster than previously thought. However, at present, it has limited treatments. Objective: To overcome this issue, we developed an artificial intelligence (AI) model of COVID-19, named EDRnet (ensemble learning model based on deep neural network and random forest models), to predict in-hospital mortality using a routine blood sample at the time of hospital admission. Methods: We selected 28 blood biomarkers and used the age and gender information of patients as model inputs. To improve the mortality prediction, we adopted an ensemble approach combining deep neural network and random forest models. We trained our model with a database of blood samples from 361 COVID-19 patients in Wuhan, China, and applied it to 106 COVID-19 patients in three Korean medical institutions. Results: In the testing data sets, EDRnet provided high sensitivity (100%), specificity (91%), and accuracy (92%). To extend the number of patient data points, we developed a web application (BeatCOVID19) where anyone can access the model to predict mortality and can register his or her own blood laboratory results. Conclusions: Our new AI model, EDRnet, accurately predicts the mortality rate for COVID-19. It is publicly available and aims to help health care providers fight COVID-19 and improve patients’ outcomes.

Keon Hui Lee,1,* Su Hyun Bong,1,* Dae Hun Kang,2 Tae Young Choi,1 Jun Won Kim1 1Department of Psychiatry, Catholic University of Daegu School of Medicine, Daegu, Republic of Korea; 2Department of Psychiatry, The Armed Forces Daejeon Hospital, Daejeon, Republic of Korea*These authors contributed equally to this workCorrespondence: Jun Won KimCatholic University of Daegu School of Medicine, 17-Gil 33 Duryugongwon-Ro, Nam-Gu Daegu 42472, South KoreaTel +82-53-650-4780Fax +82-53-623-1694Email f_affection@hotmail.comBackground: Obesity in adolescents is associated with their mental as well as physical health. Adolescents tend to have negative or distorted perceptions about their body weight; however, the effects of such weight misperception on mental health remain unclear. This study investigated the association between weight misperception and mental health in Korean adolescents.Methods: The analysis was based on the Korea Youth Risk Behavior web-based survey 2017 dataset, which included data from 62,276 middle and high school students at 800 schools throughout Korea. The students were divided into three groups according to whether they overestimated their body weight, underestimated it, or had no misperception. The mental health characteristics of the overestimation and no misperception groups were compared through multiple logistic regression analysis.Results: Based on their body mass index, male adolescents were more likely to be overweight than female adolescents (p < 0.001) and less likely to have weight misperception. The female adolescents were more likely to overestimate their body weight and less likely to underestimate it (p < 0.001). The male adolescents and female adolescents who overestimated their body weight had significantly lower levels of subjective happiness than their peers had and were more likely to experience subjective stress, sadness/despair, suicidal ideation, and suicide planning. Compared with their peers who have no mispercepti

Geun Hui Won, Tae Young Choi, Jun Won Kim Department of Psychiatry, Catholic University of Daegu School of Medicine, Daegu, Republic of KoreaCorrespondence: Jun Won KimDepartment of Psychiatry, Catholic University of Daegu School of Medicine, 3056-6 Daemyeong-4 Dong, Nam-gu, Daegu 705-718, Republic of KoreaTel +82 53 650 4332Fax +82 53 623 1694Email f_affection@naver.comPurpose: We aimed to compare the Korean version of the ADHD Rating Scale (K-ARS) and Integrated Visual and Auditory Plus (IVA+Plus), a continuous performance test, by analyzing their abilities to distinguish different groups (attention-deficit/hyperactivity disorder [ADHD], ADHD-not otherwise specified [NOS], and normal control [NC]).Patients and Methods: Individuals of 7– 12 years of age who visited our child and adolescent psychiatric clinic were recruited. Seventy-four participants (58 males, 16 females) were classified into three groups according to results from the Korean Version of Diagnostic Interview Schedule for Children Version IV. The K-ARS and IVA+Plus were administered. An analysis of covariance (ANCOVA) was conducted. The tools’ accuracy in discriminating patients with ADHD or NOS from NCs was evaluated using a receiver operating characteristic (ROC) curve analysis.Results: ANCOVA revealed significant differences in the K-ARS results of the three groups (ADHD [n=29], NOS [n=33], NC [n=12]), whereas a difference in IVA+Plus results was observed only between the ADHD and NC groups. In the ROC curve analysis of the K-ARS, the areas under the curve (AUCs) for each group were 0.960 (ADHD vs NC), 0.885 (NOS vs NC), 0.920 (ADHD+NOS vs NC), and 0.779 (ADHD vs NOS+NC). In the ROC curve analysis for the IVA+Plus hyperactivity-impulsiveness scale, the AUCs for each group were 0.740 (ADHD vs NC), 0.643 (NOS vs NC), 0.688 (ADHD+NOS vs NC), and 0.626 (ADHD vs NOS+NC); those for the inattention scale were 0.731 (ADHD vs NC), 0.658 (NOS vs NC), 0.692 (ADHD+NOS vs NC), and 0.625 (ADH