• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2359-2376
• /
• 2022

With the exponential growth of medical image big data represented by high-resolution CT images(CTI), the high-resolution CTI data is of great importance for clinical research and diagnosis. The paper takes lung CTI as an example to study. Retrieving answer CTIs similar to the input one from the large-scale lung CTI database can effectively assist physicians to diagnose. Compared with the conventional content-based image retrieval(CBIR) methods, the CBIR for lung CTIs demands higher retrieval accuracy in both the contour shape and the internal details of the organ. In traditional supervised deep learning networks, the learning of the network relies on the labeling of CTIs which is a very time-consuming task. To address this issue, the paper proposes a Weakly Supervised Similarity Evaluation Network (WSSENet) for efficiently support similarity analysis of lung CTIs. We conducted extensive experiments to verify the effectiveness of the WSSENet based on which the CBIR is performed.

• Journal of Convergence Society for SMB
• /
• v.6 no.1
• /
• pp.33-38
• /
• 2016

Disease of patient who visited the hospital can cause different symptoms of the disease, depending on the environment and lifestyle. Recent medical services offered in patients has changed in the environment that can be selected for treatment by analyzing the patient according to the disease symptoms. In this paper, we propose an efficient method to manage disease control because the treatment method may change at any patients suffering from the disease according to the patient conditions by grouping the different treatments to patients for disease information. The proposed scheme has a feature that can be ingested by the patient big disease information, as well as to improve the treatment efficiency of the medical treatment the increase patient satisfaction. The proposed sheme can handle big data by clustering of disease information for patients suffering from diseases such as patient consent small groups. In addition, the proposed scheme has the advantage that can be conveniently accessed via a particular keyword, the treatment method according to patient disease information. The experimental results, the proposed method has been improved by 23% in terms of efficiency compared to conventional techniques, disease management time is gained 11.3% improved results. Medical service user satisfaction seen from the survey is to obtain a high 31.5% results.

• Journal of Society of Preventive Korean Medicine
• /
• v.8 no.1
• /
• pp.89-107
• /
• 2004

This study was conducted to analyze community residents' behavior of Oriental medicine utilization and its related factors in order to provide basic data for formulation of policies on Oriental medicine. The subjects of this study was 500 residents who lived in big or medium sized cities and towns or villages Data were collected from March, 2002 to June, 2002. The results of this study can be summarized as follows. 1) According to socio-demographic characteristics of the respondents, female was 50.3%; 'over 50 years old' 29.9%, 'over college graduate' 39.7%, 'housewife' 23.0%, 'having spouse' 62.1%, 'Buddhist' 50.8%, 'living in big cities' 59.0%, 'middle economic class' 88.1%. 2) The highest proportion of frequency of Oriental medicine utilization was over 10 times(32.5%). The respondents visited Oriental medicine institutions for taking invigorant(51.1%), treatment of diseases in muscle or bone system(30.8%), treatment of diseases in digestive system(6.3%), etc. 3) According to the reasons of utilizing Oriental medicine, the proportion of good effect was highest(36.3%). 66.8% of the respondents replied that Oriental medical fee was expensive, while 0.8% of them replied that it was not expensive. 33.3% of them thought it was proper. 4) 35.5% of the respondents replied that treatment by Oriental medicine could cause side effect and 40.3% of them replied that the side effect could be caused by taking herb medicine. 5) 62.8% of the respondents replied that they would continuously receive opinions on Oriental medicine. The score of knowledge level of treatment by Oriental medicine $6.25{\pm}2.82$ points on the basis of 14 points. 6) The variables significantly influencing utilization of Oriental medicine includes taking diseases, living in big cities, male, upper (economic class, having religion, and effect of Oriental medicine. 7) The factors affecting effect of herb medicine were effect of treatment by Oriental medicine, marital status, knowledge level of Oriental medicine, having diseases, and frequency of receiving the treatment.

• Health Policy and Management
• /
• v.27 no.2
• /
• pp.167-176
• /
• 2017

Background: This study aimed to analyze the impact of community health care resources on the place of death of older adults with dementia compared to those with cancer in South Korea, using public administrative big data. Methods: Based on a literature review, we selected person- and community-level variables that can affect older people's decisions about where to die. Data on place-of-death and person-level attributes were obtained from the 2013 death certification micro data from Statistics Korea. Data on the population and economic and health care resources in the community where the older deceased resided were obtained from various open public administrative big data including databases on the local tax and resident population statistics, health care resources and infrastructure statistics, and long-term care (LTC) insurance statistics. Community-level data were linked to the death certificate micro data through the town (si-gun-gu) code of the residence of the deceased. Multi-level logistic regression models were used to simultaneously estimate the impacts of community as well as individual-level factors on the place of death. Results: In both the dementia (76.1%) and cancer (87.1%) decedent groups, most older people died in the hospital. Among the older deceased with dementia, hospital death was less likely to occur when the older person resided in a community with a higher supply of LTC facility beds, but hospital death was more likely to occur in communities with a higher supply of LTC hospital beds. Similarly, among the cancer group, the likelihood of a hospital death was significantly lower in communities with a higher supply of LTC facility beds, but was higher in communities with a higher supply of acute care hospital beds. As for individual-level factors, being female and having no spouse were associated with the likelihood of hospital death among older people with dementia. Conclusion: More than three in four older people with dementia die in the hospital, while home is reported to be the place of death preferred by Koreans. To decrease this gap, an increase in the supply of end-of-life (EOL) care at home and in community-based service settings is necessary. EOL care should also be incorporated as an essential part of LTC. Changes in the perception of EOL care by older people and their families are also critical in their decisions about the place of death, and should be supported by public education and other related non-medical, social approaches.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.195-205
• /
• 2019

Linked Open Data (LOD) is rated as the best of any kind of data disclosure, and allows you to search related data by linking them in a standard format across the Internet. There is an increasing number of cases in which relevant data are constructed in the LOD form in the global environment, but in the domestic healthcare sector, the disclosure of data in the form of LOD is still at the beginning stage. In this paper, we introduce a case of LOD platform construction that provides services by linking domestic and international related data by LOD method, based on the data of Korean medical research paper data and health care big data linkage platform. Linking all data from each DB into an LOD requires a lot of time and effort, and is basically an infrastructure task that government or public institutions should be in charge of rather than the private sector. In this study, ten domestic and foreign LOD sites were linked with only a portion of each DB, enabling users to link data from various domestic and foreign organizations in a convenient manner.

• Korean Circulation Journal
• /
• v.52 no.11
• /
• pp.808-813
• /
• 2022

Studies showing that coronavirus disease 2019 (COVID-19) is associated with an increased risk of cardiovascular disease continue to be published. However, studies on how long the overall cardiovascular risk increases after COVID-19 and the magnitude of its long-term effects have only been confirmed recently. This is partly because the distinction between cardiovascular risk as an acute complication of COVID-19 or post-acute cardiovascular manifestations is ambiguous. Long-COVID has arisen as an important topic in the second half of the pandemic. This term indicates that symptoms persist for more than two 2 months; following three months of SARS-CoV-2 infection and cannot be explained by other medical conditions. Despite the agreement of these international organizations and experts, it is difficult to define whether there is sufficient medical evidence to prove the existence of long-COVID. However, the Korean government and Korea Disease Control and Prevention Agency (KDCA) are preparing a new platform to assess the long-term impact of COVID-19. Using this data, a prospective cohort of 10,000 confirmed COVID-19 cases will be established. This cohort will be linked with claims data from the National Health Insurance Services (NHIS) and it is expected that increased real-world evidence of long-COVID will be accumulated.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.11a
• /
• pp.181-186
• /
• 2005

Many data sets obtained from surveys or medical trials often include missing observations. When these data sets are analyzed, it is general to use only complete cases. However, it is possible to have big biases or involve inefficiency. In this paper, we consider a method for estimating parameters in logistic linear models involving non-ignorable missing data mechanism. A binomial response and normal exploratory model for the missing data are used. We fit the model using the EM algorithm. The E-step is derived by Metropolis-hastings algorithm to generate a sample for missing data and Monte-carlo technique, and the M-step is by Newton-Raphson to maximize likelihood function. Asymptotic variances of the MLE's are derived and the standard error and estimates of parameters are compared.

• Health Policy and Management
• /
• v.30 no.1
• /
• pp.82-91
• /
• 2020

Background: This study investigates the influence factors of medical service variations using medical charge and the length of stay (LOS) for urinary incontinence surgery and uterine polypectomy. Methods: The National Health Insurance claims data and Medical Resource Report by the Health Insurance Review & Assessment Service in 2016 were used. Frequency analysis, one-way analysis of variance, and Bonferroni post-hoc tests were executed for each surgery. A multilevel analysis was executed to assess the factors to the medical charge and LOS for each surgery in patient, doctor, and hospital level. Results: Fifty-two point eight percent of urinary incontinence surgery and 87.1% of uterine polypectomy were distributed in general and tertiary hospitals. Among three levels, the patient level variation was 61.5% or 77.2% in medical charge and 93.9% or 96.3% in LOS, respectively. The doctor level variation was 29.6% or 22.6% in medical charge and 0.6% or 0.0% in LOS, respectively. The institution level variation was 8.9% or 0.2% in medical charge and 5.5% or 3.7% in LOS, respectively. Number of other disease and organizational type were main factors that affected the charge and LOS for urinary incontinence surgery and uterine polypectomy. Conclusion: Medical service variations of the urinary incontinence surgery and uterine polypectomy were the largest for the patient level, followed by doctor level for the medical charge, and the institution level for the LOS.

• Journal of the Korean Society of Radiology
• /
• v.16 no.4
• /
• pp.453-462
• /
• 2022

In this paper, the artificial intelligence (AI) technology used in the medical image analysis field was analyzed through a literature review. Literature searches were conducted on PubMed, ResearchGate, Google and Cochrane Review using the key word. Through literature search, 114 abstracts were searched, and 98 abstracts were reviewed, excluding 16 duplicates. In the reviewed literature, AI is applied in classification, localization, disease detection, disease segmentation, and fit degree of registration images. In machine learning (ML), prior feature extraction and inputting the extracted feature values into the neural network have disappeared. Instead, it appears that the neural network is changing to a deep learning (DL) method with multiple hidden layers. The reason is thought to be that feature extraction is processed in the DL process due to the increase in the amount of memory of the computer, the improvement of the calculation speed, and the construction of big data. In order to apply the analysis of medical images using AI to medical care, the role of physicians is important. Physicians must be able to interpret and analyze the predictions of AI algorithms. Additional medical education and professional development for existing physicians is needed to understand AI. Also, it seems that a revised curriculum for learners in medical school is needed.

• Journal of Chest Surgery
• /
• v.49 no.sup1
• /
• pp.1-13
• /
• 2016

Background: The purpose of this study was to investigate longitudinal changes of the utilization of operational and surgical medical care inside and outside a metropolitan area over 10 years, analyzing the residential areas of patients and the locations of medical facilities for major cardiovascular surgery. Methods: Data analysis was conducted by classifying the addresses of patients and the locations of medical care facilities of metropolitan cities and provinces, using data from the National Health Insurance Corporation from January 2003 to December 2013. Results: There is serious concentration of major heart surgery to medical facilities in Seoul; this problem has not improved over time. There were differences in percentages of surgical procedures performed in the metropolitan areas according to major diseases. In the case of Busan and Daegu provinces, at least 50% of the patients underwent surgery in medical facilities in the city, but there are other regions where the percentage is less than 50%. In the case of provinces, the percentage of surgical procedures performed in medical facilities in Seoul or nearby metropolitan cities is very high. Conclusion: Policies to strengthen the regional capabilities of heart surgery and to secure human resources are required to mitigate the concentration of patients in the capital area. Many regional multi-centers must be designated to minimize unnecessary competition among regional university hospitals and activate a win-win partnership model for medical services.