• 한국경영과학회지
• /
• 제39권4호
• /
• pp.51-69
• /
• 2014

Times to multiple events (TMEs) are a major data type in large-scale business and medical data. Despite its importance, the analysis of TME data has not been well studied because of the analysis difficulty from censoring of observation. To address this difficulty, we have developed a Bayesian-based multivariate survival analysis method, which can successfully estimate the joint probability density of survival times. In this work, we extended this method for the analysis of precedence, dependency and causality among multiple events. We applied this method to the electronic health records of 2,111 patients in a children's hospital in the US and the proposed analysis successfully shows the relation between times to two types of hospital visits for different medical issues. The overall result implies the usefulness of the multivariate survival analysis method in large-scale big data in a variety of areas including marketing, human resources, and e-commerce. Lastly, we suggest our future research directions based multivariate survival analysis method.

• Advances in pediatric surgery
• /
• 제19권2호
• /
• pp.90-97
• /
• 2013

Laparoscopic surgery has become popular in the past few decades, owing to less postoperative pain, fast recovery, and better cosmetic outcomes. The laparoscopic approach has been employed in pediatric surgery for the same reasons. After the first attempts of single incision laparoscopic appendectomy in pediatrics in 1998, single incision laparoscopic surgery (SILS) has recently been proven to be safe and feasible for the pediatric population. However, limitations have been reported for SILS, such as the wide learning curve, compared to standard laparoscopic surgery, and the restricted number of hospitals with surgical training programs including SILS. In this study, we intend to present our initial experiences with SILS in children, and to describe the technique, instruments used, and outcomes. This is a retrospective study of 71 pediatric patients who underwent SILS, at a tertiary medical center, between September, 2012 and August, 2013. Electronic medical records were reviewed for demographics, type of procedure, operation time, use of additional ports, conversion to open surgery, complications and hospital stay. Additional ports were inserted in 4 cases, for the purpose of traction. Postoperative complications were noted in 13 cases, which were mostly related to wound inflammation or formation of granulation tissue. According to our analyses, patients with complications had significantly longer use and more frequent use of pain killers. Notwithstanding the small sample size, many of the procedures performed in pediatric patients seem to be possible with SILS.

• Journal of Hospice and Palliative Care
• /
• 제23권2호
• /
• pp.85-92
• /
• 2020

Purpose: In 2018, the Act on Decisions on Life-Sustaining Treatment for Patients in Hospice and Palliative Care or at the End of Life was implemented and the scope of official recognition for terminally ill patients was expanded. The purpose of this study was to investigate the decisions made by patients with end-stage liver disease about their life-sustaining treatment in a clinical setting. Methods: The subjects of this study were patients with end-stage liver disease hospitalized at a tertiary hospital in Seoul, Korea who wrote physician orders for life-sustaining treatment (POLST). Data collection was done using patients' electronic medical records, and a retrospective analysis of POLST was conducted. Results: Among 101 patients, 18.8% were female and 81.2% were male, and their mean age was 61.8 (±10.61) years. Sixty-three patients (62.4%) wrote their POLST by themselves. Three patients withdrew the POLST, of whom two did so for liver transplantation, and one did so for chemotherapy. Conclusion: This study shows that sufficient consideration of liver transplantation is needed for end-stage liver disease patients before making decisions on life-sustaining treatment. The self-determination of patients must be respected and effective guidelines are urgently needed.

• Preventive Nutrition and Food Science
• /
• 제18권2호
• /
• pp.117-123
• /
• 2013

This study investigated the prevalence of and risk factors for malnutrition in hospitalized patients in Busan, Republic of Korea. 944 patients (440 men and 504 women) were hospitalized in four Busan general hospitals from March through April, 2011. Nutritional status was assessed on admission by the Nutritional Risk Screening 2002. Data were collected from the electronic medical records system for the characteristics of the subjects, clinical outcomes, biochemical laboratory data, and nutrition support states. Clinical dietitians interviewed the patients using structured questionnaires involving data on weight loss and problems related to oral intakes. Malnourished patients were significantly older (P<0.001) than well-nourished patients, but the values for BMI, serum albumin, total cholesterol, TLC, hemoglobin, and hematocrit were significantly lower (P<0.001) for malnourished than for well-nourished patients. Logistic regression indicated that the main determinant factors for nutritional status were the age, length of stay, BMI, serum albumin, and total cholesterol. In order to increase therapeutic effects of hospitalized patients, clinical dietitians need to offer proper nutritional intervention based on the results of nutrition assessment and identification of malnutrition.

• Journal of Korean Biological Nursing Science
• /
• 제19권2호
• /
• pp.60-68
• /
• 2017

Purpose: The purpose of this study was to analyze the relationship between lower urinary tract symptoms and urodynamic parameters to investigate the characteristics of mixed urinary incontinence (MUI) and stress urinary incontinence (SUI). Methods: The subjects were 318 women with MUI and 128 women with SUI. Data were collected retrospectively from electronic medical records including Bristol Female Lower Urinary Tract Symptoms-Scored Form (BFLUTS-SF), Incontinence Quality of Life Instrument (I-QOL), voiding diaries, and urodynamic parameters. Results: Compared with the SUI group, the MUI group was older and showed lower I-QOL and more severe urinary tract symptoms. The MUI group had more urinary frequency, more nocturia, and a higher urgency score than the SUI group. In the correlation analysis, the greatest difference between the two groups was that urgency was associated with Qmax, maximal cystometric capacity, and detrusor overactivity only in the MUI group (r = -.175, p= .004; r = -.281, p< .001; r= .232, p< .001, respectively). Conclusion: As a result of this study, we propose that a customized management program that emphasizes the control of urgency for the MUI group, and one that effectively strengthens the weak pelvic floor for the SUI group.

• 대한간호학회지
• /
• 제47권6호
• /
• pp.817-827
• /
• 2017

Purpose: This study aimed to identify latent classes based on major modifiable risk factors for coronary artery disease. Methods: This was a secondary analysis using data from the electronic medical records of 2,022 patients, who were newly diagnosed with coronary artery disease at a university medical center, from January 2010 to December 2015. Data were analyzed using SPSS version 20.0 for descriptive analysis and Mplus version 7.4 for latent class analysis. Results: Four latent classes of risk factors for coronary artery disease were identified in the final model: 'smoking-drinking', 'high-risk for dyslipidemia', 'high-risk for metabolic syndrome', and 'high-risk for diabetes and malnutrition'. The likelihood of these latent classes varied significantly based on socio-demographic characteristics, including age, gender, educational level, and occupation. Conclusion: The results showed significant heterogeneity in the pattern of risk factors for coronary artery disease. These findings provide helpful data to develop intervention strategies for the effective prevention of coronary artery disease. Specific characteristics depending on the subpopulation should be considered during the development of interventions.

• 동서간호학연구지
• /
• 제24권2호
• /
• pp.146-153
• /
• 2018

Purpose: This study aimed to identify characteristics and severity assessed by Korean Triage and Acuity Scale (KTAS) among 2,496 older adults aged 65 and over who visited an emergency department (ED) located in Chuncheon city. Methods: Data were collected via electronic medical records from two hospitals from January to December of 2016. Chi square test and logistic regression were applied using SPSS 22.0. Results: 53.5% of the participants were women and 17.6% of visits were done by aged 85 and older. ED visits by ambulance were 33.9%. More than two-third of older adults' ED visits were emergent status. Severity of the ED visits of older adults were rated by KTAS. Commonly reported chief complaints of the ED visits were dizziness, dyspnea, chest pain, abdominal pain, and hypoalbuminemia. Among them, dizziness, chest pain, dyspnea, and hypoalbuminemia were related factors for being-emergent condition. Conclusion: Strategies for older adults' chief complaints are needed in order to reduce unexpected ED visits.

• International journal of advanced smart convergence
• /
• 제10권2호
• /
• pp.21-30
• /
• 2021

With the rapid development of artificial intelligence and big data, a lot of medical data is effectively used, and the diagnosis and analysis of diseases has entered the era of intelligence. With the increasing public health awareness, ordinary citizens have also put forward new demands for panic disorder health services. Specifically, people hope to predict the risk of panic disorder as soon as possible and grasp their own condition without leaving home. Against this backdrop, the smart health industry comes into being. In the Internet age, a lot of panic disorder health data has been accumulated, such as diagnostic records, medical record information and electronic files. At the same time, various health monitoring devices emerge one after another, enabling the collection and storage of personal daily health information at any time. How to use the above data to provide people with convenient panic disorder self-assessment services and reduce the incidence of panic disorder in China has become an urgent problem to be solved. In order to solve this problem, this research applies the context awareness to the automatic diagnosis of human diseases. While helping patients find diseases early and get treatment timely, it can effectively assist doctors in making correct diagnosis of diseases and reduce the probability of misdiagnosis and missed diagnosis.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1238-1249
• /
• 2020

Throughout the world, aging populations and doctor shortages have helped drive the increasing demand for smart healthcare systems. Recently, these systems have benefited from the evolution of the Internet of Things (IoT), big data, and machine learning. However, these advances result in the generation of large amounts of data, making healthcare data analysis a major issue. These data have a number of complex properties such as high-dimensionality, irregularity, and sparsity, which makes efficient processing difficult to implement. These challenges are met by big data analytics. In this paper, we propose an innovative analytic framework for big healthcare data that are collected either from IoT wearable devices or from archived patient medical images. The proposed method would efficiently address the data heterogeneity problem using middleware between heterogeneous data sources and MapReduce Hadoop clusters. Furthermore, the proposed framework enables the use of both fog computing and cloud platforms to handle the problems faced through online and offline data processing, data storage, and data classification. Additionally, it guarantees robust and secure knowledge of patient medical data.

• Journal of Korean Biological Nursing Science
• /
• 제24권3호
• /
• pp.161-170
• /
• 2022

Purpose: The purpose of this study was to investigate polypharmacy and potentially inappropriate medication (PIM) use in elderly patients admitted to hospitals after falls. Methods: The study surveyed 283 patients 65 or older admitted January 1-December 31, 2016. Data were collected from electronic medical records, and medications administered immediately prior to admission were examined. PIM use for patients was investigated using the Beers criteria, and data were analyzed by Chi-square test and independent ttest. Results: The average age of participants was 79.42± 8.16, and the study included 226 women (79.9%) and 57 men (20.1%). The average number of self-administered medications daily was 4.94± 3.68, and 55.1% took five or more medications. PIM use was found in 107 patients (37.8%). There was a significant difference in polypharmacy according to age, and the proportion of medical aid beneficiaries and prevalence of cardiocerebrovascular, endocrine, and other chronic diseases were higher in the polypharmacy and PIM use patients than in the non-polypharmacy and non-PIM use patients. The number of chronic diseases and medications taken were significantly high among polypharmacy and PIM use patients. Conclusion: It is necessary to minimize polypharmacy and PIM use, and establish a system for systematically evaluating and managing medication use to prevent falls in the elderly.