Search

The majority of suicide decedents die on their initial attempt. To bring attention to suicide decedents without a suicide attempt history, the current study explored their demographic, clinical, and suicide-related characteristics. The data were derived from the Korea National Investigation of Suicide Victims Study, which assessed all suicide cases from 2013 to 2017 recorded in police investigation reports. We compared suicide decedents with and without a history of nonfatal attempts using the Korea Psychological Autopsy Checklist for Police Records (K-PAC). Out of 5228 cases included in our study, 3147 (60.2%) died on their first suicide attempt. Demographically, those who were male, older than 65, employed, and married/widowed were more likely to die on their initial attempt. Clinically, those who died on their initial attempt were more likely to have never been diagnosed with psychiatric disorders, whereas those who died on a repeated attempt were more likely to have been diagnosed with mood disorders. In terms of suicide-related factors, experiencing relationship problems and complaining about physical discomfort were associated with dying on an initial attempt. Depressed affect, self-harming behaviors, and talking about suicide or death were associated with repeated attempts.

It seems as though progressively more people are in the race to upload content, data, and information online; and hospitals haven’t neglected this trend either. Hospitals are now at the forefront for multi-site medical data sharing to provide groundbreaking advancements in the way health records are shared and patients are diagnosed. Sharing of medical data is essential in modern medical research. Yet, as with all data sharing technology, the challenge is to balance improved treatment with protecting patient’s personal information. This paper provides a novel split learning algorithm coined the term, “multi-site split learning”, which enables a secure transfer of medical data between multiple hospitals without fear of exposing personal data contained in patient records. It also explores the effects of varying the number of end-systems and the ratio of data-imbalance on the deep learning performance. A guideline for the most optimal configuration of split learning that ensures privacy of patient data whilst achieving performance is empirically given. We argue the benefits of our multi-site split learning algorithm, especially regarding the privacy preserving factor, using CT scans of COVID-19 patients, X-ray bone scans, and cholesterol level medical data.

It seems as though progressively more people are in the race to upload content, data, and information online; and hospitals haven’t neglected this trend either. Hospitals are now at the forefront for multi-site medical data sharing to provide ground-breaking advancements in the way health records are shared and patients are diagnosed. Sharing of medical data is essential in modern medical research. Yet, as with all data sharing technology, the challenge is to balance improved treatment with protecting patient’s personal information. This paper provides a novel split learning algorithm coined the term, “multi-site split learning”, which enables a secure transfer of medical data between multiple hospitals without fear of exposing personal data contained in patient records. It also explores the effects of varying the number of end-systems and the ratio of data-imbalance on the deep learning performance. A guideline for the most optimal configuration of split learning that ensures privacy of patient data whilst achieving performance is empirically given. We argue the benefits of our multi-site split learning algorithm, especially regarding the privacy preserving factor, using CT scans of COVID-19 patients, X-ray bone scans, and cholesterol level medical data.

Objective The suicide rate in South Korea was the second highest among the Organization for Economic Cooperation and Development countries in 2017. The purpose of this study is to understand the characteristics of people who died by suicide in Korea from 2013-2017 and to better prevent suicide. Methods This study was performed by the Korea Psychological Autopsy Center (KPAC), an affiliate of the Korea Ministry of Health and Welfare. According to the Korea National Statistical Office, the number of suicide victims nationwide was estimated to reach about 70,000 from 2013 to 2017. Comprehensive suicide records from all 254 police stations in South Korea were evaluated by 32 investigators who completed a 14-day didactic training program. Then, we evaluated the characteristics of suicide victims in association with disease data from the National Health Insurance Database (NHID), which is anonymously linked to personal information of suicide victims. Results Thirty-one of 254 police stations in the Seoul metropolitan area were analyzed by August 10, 2018. Findings showed that the characteristics of suicide victims differed according to the nature of the region. Conclusion Our results suggest that different strategies and methods are needed to prevent suicide by regional groups.

Experience sharing among multiple users in virtual reality (VR) is one of the key applications in next generation wireless systems. In this VR application, one object can be reproduced as a virtual object based on recorded/captured multiple real-time images from multiple observation points. At this time, VR applications require a lot of bandwidth to provide seamless services to users in wireless links, and thus, a certain level of data rates should be maintained. As the number of users increases, the server allocates more data rates to users on top of the limited bandwidth in wireless networks. At this time, users who utilize the VR streaming services will suffer from a lower quality, due to the limited bandwidth. This paper reports the measurement study and also analyzes the fluctuations in terms of the data rates as the number of users increases while sharing point cloud information in real-time authorized reality environments over IEEE 802.11ac wireless networks. Moreover, it measures and analyzes fluctuations in terms of frames-per-second and Jitters, which are practical quality reduction indicators.

This demo abstract presents the visualization of deep reinforcement learning (DRL)-based autonomous aerial mobility simulations. In order to implement the software, Unity-RL is used and additional buildings are introduced for urban environment. On top of the implementation, DRL algorithms are used and we confirm it works well in terms of trajectory and 3D visualization.

Objective Early recognition of a high-risk group impending suicide is important. We aimed to compare warning signs depending on the nature of the psychiatric disorder and whether it was a documented diagnosis. Methods Data of suicide decedents were collected from police records from 2013 to 2017. We evaluate psychiatric symptoms and warning signs in three aspects (language, behavior, and affect) using the Korea-Psychological Autopsy Checklist for Police Records (K-PAC-PR). Results A total of 13,265 suicide decedents were recruited for this study. Of them, 66.9% of females and 46.7% of males diagnosed psychiatric disorders, with depressive disorder being the most common one. Warning signs were observed in 93.0% of suicide decedents. They were observed more in those who were diagnosed with psychiatric disorders, especially in those with a depressive disorder. "Talking about dying or suicide" was the most common warning sign in all groups, and "apathetic behavior" was the most related warning sign for depressive disorder. Especially for "talking about dying or suicide," the proportion of observed "within a week" was high, making it valuable as a warning sign. Conclusion Warning signs were commonly found in suicide decedents regardless of gender. They were more common among the decedents diagnosed with psychiatric disorders, especially among those with a depressive disorder.

Background Suicide survivors are defined as victims who experienced suicide of siblings or parents, spouses, or lineal relatives within the fourth degree who had lived with them. We compared the effects of major depressive disorder (MDD), symptoms of posttraumatic stress disorder (PTSD), and impulsivity on lifetime suicide attempts among suicide survivors. Methods Participants included 272 suicide survivors. We compared them to 5,200 members from the general population who were matched by age, sex, and years of education. We evaluated participants using the Patient Health Questionnaire-9 (PHQ-9), the EuroQuality of Life (EuroQol) scale, the Impact of Events Scale-Revised (IES-R), the Barratt Impulsiveness Scale-11 (BIS-11), and the Composite International Diagnostic Interview (K-CIDI). Results Among the 272 suicide survivors, MDD was nine times higher (47.1% vs. 5.3%), and suicidal attempts were six times higher (20.5% vs. 3.3%) than reported among the general population. The suicide survivors showed more severe depression, greater impulsivity, and poorer quality of life than did the general population. In multivariate logistic regression analyses performed to evaluate each IES-R item, “trouble staying asleep” was the only PTSD symptom item that was significantly associated with suicide attempts among suicide survivors. Suicide survivors who had both MDD with insomnia and high impulsivity were at four times higher risk for suicide attempts than the general population with no MDD (AOR = 4.04, 95% CI: 1.25-13.09). Conclusions Surviving suicide by family members is an important risk factor for suicide attempts. In particular, MDD with insomnia and impulsivity are associated with suicide attempts among suicide survivors.