• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.9
• /
• pp.317-322
• /
• 2022

The rapid development of information technology is also bringing about many changes in the medical environment. In particular, it is leading the rapid change of medical image information systems using big data and artificial intelligence (AI). The prescription delivery system (OCS), which consists of an electronic medical record (EMR) and a medical image storage and transmission system (PACS), has rapidly changed the medical environment from analog to digital. When combined with multiple solutions, PACS represents a new direction for advancement in security, interoperability, efficiency and automation. Among them, the combination with artificial intelligence (AI) using big data that can improve the quality of images is actively progressing. In particular, AI PACS, a system that can assist in reading medical images using deep learning technology, was developed in cooperation with universities and industries and is being used in hospitals. As such, in line with the rapid changes in the medical image information system in the medical environment, structural changes in the medical market and changes in medical policies to cope with them are also necessary. On the other hand, medical image information is based on a digital medical image transmission device (DICOM) format method, and is divided into a tomographic volume image, a volume image, and a cross-sectional image, a two-dimensional image, according to a generation method. In addition, recently, many medical institutions are rushing to introduce the next-generation integrated medical information system by promoting smart hospital services. The next-generation integrated medical information system is built as a solution that integrates EMR, electronic consent, big data, AI, precision medicine, and interworking with external institutions. It aims to realize research. Korea's medical image information system is at a world-class level thanks to advanced IT technology and government policies. In particular, the PACS solution is the only field exporting medical information technology to the world. In this study, along with the analysis of the medical image information system using big data, the current trend was grasped based on the historical background of the introduction of the medical image information system in Korea, and the future development direction was predicted. In the future, based on DICOM big data accumulated over 20 years, we plan to conduct research that can increase the image read rate by using AI and deep learning algorithms.

• Radiation Oncology Journal
• /
• v.22 no.1
• /
• pp.33-39
• /
• 2004

Purpose : A tumor registry system for the patients treated by radiotherapy at Samsung Medical Center since the opening of a hospital at 1994 was employed. In this study, the tumor registry system was introduced and the validity of the tumor registration was analyzed. Materials and Methods: The tumor registry system was composed of three parts: patient demographic, diagnostic, and treatment Information. All data were input in a screen using a mouse only. Among the 10,000 registered cases in the tumor registry system until Aug, 2002, 199 were randomly selected and their registration data were compared with the patients' medical records. Results : Total input errors were detected on 15 cases (7.5%). There were 8 error items In the part relating to diagnostic Information: tumor site 3, pathology 2, AJCC staging 2 and performance status 1. In the part relating to treatment information there were 9 mistaken items: combination treatment 4, the date of initial treatment 3 and radiation completeness 2. According to the assignment doctor, the error ratio was consequently variable. The doctors who 010 no double-checks showed higher errors than those that 010 (15.6%:3.7%). Conclusion: Our tumor registry had errors within 2% for each Item. Although the overall data qualify was high, further improvement might be achieved through promoting sincerity, continuing training, periodic validity tests and keeping double-checks. Also, some items associated with the hospital Information system will be input automatically In the next step.

• The Journal of Society for e-Business Studies
• /
• v.19 no.3
• /
• pp.91-105
• /
• 2014

This study purposed to benchmark the number of patients who visited an oriental medicine hospital from its surrounding regions using data envelopment analysis (DEA) model, and to analyze the relationships between regional characteristics and efficiency scores from DEA. Study data was collected from one oriental medicine hospital operated in a metropolitan city in Korea. Patient locations were identified at the smallest administrative district, Dong, and number of patients was calculated at the Dong level based on the address of patients in hospital information system. Socio-demographic variables of each Dong were identified from the Statistics of Korea web-sites. DEA was used to benchmark the number of patients between Dongs and to compute the efficiency scores. Tobit regression analysis model was applied to analyze the relationship between efficiency scores and regional variables. 6 Dongs were identified as efficient after DEA. In Tobit analysis, number of medical aid recipients and number of total population in each Dong was significant in explaining the differences of efficiency scores. The study model introduced the application of DEA model in benchmarking the patients between regions. It can be applied to identify the number of patients in each region which a hospital needs to improve their performances.

• Korea Journal of Hospital Management
• /
• v.13 no.1
• /
• pp.42-64
• /
• 2008

This study was conducted to evaluate the quality in medical records by analyzing its completeness through setting up the level of record on the patient's past history and through examining the actual medial records. Targeting the information on the patient's past history in interns' records, residents' records and nurses' records toward 403 inpatients who were admitted first in 2004 at an university hospital due to stomach cancer. We analyzed whether the charts were recorded or not, recording level, the satisfaction with the expectant level of the records in the hospital targeted for a research and the level of agreement. The results were as follows; first, as for the rate of recording those each items, they were high in the chief complaint & present illness and the past illness history. Depending on the group of recorders, the recording rate showed big difference by items. Second, as a result of measuring the level after dividing the recording level of items for the patient's past history from Level 1 to Level 4 by each item, the admission history, the past illness history, and the family history were about Level 3, and the smoking history, the medication history, the chief complaint & present illness, the drinking history and allergy were about Level 2. In the admission department, it was excellent in the interns' records for the medical department. Third, as a result of its satisfactory level by comparing the expect level of a record and the actual record by item in information on the patient's past history, which was expected by the medical-record committee members of the hospital targeted for a study. And forth, we analyzed the level of agreement with Kappa score in the level of 'Yes' or 'None' related to the corresponding matter in Level 1, in terms of information on the past history in the intern's record, the resident's record, and the nurse's record. The level of agreement in the resident's record & the nurse's record, and in the intern's record & the resident's record was from "excellent" to "a little good". There were differences in the level of completeness and in reliability for the information on the past history by the recorder group or by the admission department. The encounter process that was performed by the admission department or the recorder group, indicated the result that was directly reflected on the quality of medical records, thus it was required further study about the medical record documentation process and quality of care. The items that showed the high recording rate quantitatively were rather low, consequently we'd should develop the tool for the qualitative inspection and evaluate the medical records further. And the items were needed to be detailed in the record level were rather low, and hence there needed to be a documentation guideline and education by the clinical departments.

• Neonatal Medicine
• /
• v.18 no.2
• /
• pp.359-364
• /
• 2011

Purpose: Aplasia cutis congenita (ACC) is a rare condition characterized by a localized absence of skin, and it can be associated with other congenital anomalies. This study was done to evaluate clinical course and outcome of ACC in neonates. Methods: Based on the medical records, we retrospectively reviewed 8 neonates diagnosed with ACC at Cheil General Hospital and Women's Health Care Center, Kwandong university College of Medicine from January 2004 to December 2010. We classified ACC by Frieden's classification and analyzed the patient's demographic data, clinical course and outcome. Results: Among 8 patients with ACC, 5 patients were classified to group 1; scalp ACC without anomalies and 3 patients to group 7; ACC localized to extremities without blistering. Defect size was from 0.3 cm to 1.5 cm, limited in the superficial skin or subcutaneous tissue without associated anomalies. Defects were healed under conservative treatment with mild scar formation within four months. Conclusion: ACC could be diagnosed easily through physical examination in neonates. All cases showed good clinical outcome without surgical treatment. However because of small numbers and small sized defects of cases, further study including lesions of large size is needed.

• Pediatric Infection and Vaccine
• /
• v.19 no.3
• /
• pp.141-148
• /
• 2012

Purpose : Ventriculoperitoneal (VP) shunt insertion is an important treatment modality in children with hydrocephalus. VP shunt infection is a major complication and an important factor that determines the surgery outcome. This 15-year study was performed to evaluate the epidemiology of VP shunt infections in pediatric patients treated at our center. Methods : A retrospective review of medical records was performed in patients 18 years old or younger who underwent VP shunt insertion surgery from April 1995 to June 2010. Results : Three hundred twenty-seven VP shunt surgeries were performed in a total of 190 pediatric patients (83 females, 107 males). The median age of the patients was 2.4 years (range, 0.02-17.9 years). Having a malignant brain tumor was the most frequent cause for VP shunt insertion. The shunt infection rate was 6.7% (22/327) per 100 operations and 9.5% (18/190) per 100 patients, and the incidence rate was 0.45 infection cases per 100 shunt operations-year. The most common pathogen was coagulase-negative staphylococcus (n=7) followed by methicillin resistant Staphylococcus aureus (n=1). Ten cases were treated with vancomycin and beta-lactam antibiotic (cephalosporin or carbapenem) combination therapy and 7 cases were treated with vancomycin monotherapy. The median duration of antibiotic treatment was 26 days (range, 7 to 58 days). Surgical intervention was performed in 18 cases (18/22, 81.8%). Conclusion : Epidemiologic information regarding VP shunt infections in pediatric patients is valuable that will help guide proper antibiotic management. Additional studies on the risk factors for developing VP shunt infections are also warranted.

• Journal of Gastric Cancer
• /
• v.5 no.2
• /
• pp.113-119
• /
• 2005

Purpose: Some controversies exist over the prognostic values of lymphatic, venous, and neural invasion in patients with gastric cancer. This study was conducted to confirm the prognostic values of these histopathologic factors in gastric cancer patients who received a gastrectomy. Materials and Methods: Data for clinicopathologic factors and clinical outcomes were collected retrospectively from the medical records of 1,018 gastric cancer patients who received a gastrectomy at Yeungnam University Medical Center between January 1995 and December 1999. A statistical analysis was done using the SPSS program for Windows (Version 10.0, SPSS Inc., USA). The Kaplan-Meier method was used for the survival analysis. Prognostic factors were analyzed by using a multivariate analysis with Cox proportional hazard regression model. Results: Ages ranged from 21 to 79 (median age, 56). A univariate analysis revealed that age, tumor size, location, gross type, depth of invasion, extent of gastrectomy or lymph node dissection, lymph node metastasis, distant metastasis, lymphatic invasion, venous invasion, neural invasion, pathologic stage, histologic type, and curability of surgery had statistical significance. Among these factors, lymph node metastasis, curability of surgery, neural invasion, lymphatic invasion, and depth of invasion were found to be independent prognostic factors by using a multivariate analysis. Venous invasion showed no prognostic value in the multivariate analysis. Conclusion: Neural invasion and lymphatic invasion are useful parameters in determining a prognosis for gastric cancer patients.

• Pediatric Infection and Vaccine
• /
• v.22 no.1
• /
• pp.23-28
• /
• 2015

Purpose: The aim of this study was to investigate the clinical manifestations and laboratory characteristics of eosinophilic meningitis in Severance Children's Hospital. Methods: We examined 6,335 children under the age of 18 years old who had visited the tertiary hospital in Seoul, Korea, and had received cerebrospinal study results between January 2007 and July 2012. The medical records of the patients identified as eosinophilic meningitis were retrospectively reviewed. Results: Eosinophilic meningitis was diagnosed in 39 patients (0.6%). The mean age was 6 years (range 0-18 years) and the sex ratio was 1.3:1 (22 males and 17 females). The underlying diseases and past history were neurologic disease (n=36, 92%). Eosinophilic meningitis was diagnosed in thirty-five patients who had undergone postoperation neurosurgery (90%). The most common symptoms were fever (50%), headache (20%), vomiting (15%), seizure (10%), and dizziness (5%). The average duration for recovery was five days, and intravenous antibiotics or steroids were used. Conclusions: Manifestations of eosinophilic meningitis are similar to other types of meningitis. The most common cause of eosinophilic meningitis in children was neurosurgery. Eosinophilic meningitis should be considered for patients showing fever and headache after neurosurgery. Through careful investigation, use of improper antibiotics could be avoided.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.4
• /
• pp.311-317
• /
• 2004

Purpose: The purpose of this study was to determine the utility of tumor marker CA 15-3 in the following: the diagnosis of breast cancer relapse after curative mastectomy, and the differentiation or the value of tumor marker by site of metastases. Materials and Methods: Two hundred two patients (median age 48 years) with breast cancer included in the follow-up after curative mastectomy. The tumor marker CA 15-3 was determined by IRMA (CIS BIO INTERNATIONAL, France). Test values > 30 U/ml were considered elevated (positive). Results: Among 202 patients, recurrent diseases were found in 16 patients. CA 15-3 was elevated in 5 of 16 patients with recurrences. There was no false-positive patient who had elevated CA 15-3. Sensitivity and specificity of CA 15-3 for detection of breast cancer recurrence were 31%, and 100%. CA 15-3 was elevated in all of the 4 patients with liver metastases. CA 15-3 was elevated in none of the patients who relapsed with metastasis to bone-only or contralateral breast-only. Conclusion: The tumor marker CA 15-3 in the detection of breast cancer relapse after curative mastectomy is specific, but not sensitive. However, it is useful to rule out liver metastases of breast cancer, which indicates bad prognosis.

• Journal of Hospice and Palliative Care
• /
• v.18 no.4
• /
• pp.322-328
• /
• 2015

Purpose: The aging of society has rapidly progressed, especially in Korea. Therefore, the necessity of research on end-of-life (EOL) care in elderly patients has increased. However, there are few studies on EOL care intensity for non-cancer patients. This study was designed to compare the EOL care intensity between cancer and non-cancer patients. Methods: We retrospectively analyzed the EOL care intensity based on medical records of decedents of Kyung Hee University Medical Center, a tertiary referral hospital from December 2014 through March 2015. And we compared EOL care intensity between cancer patients and non-cancer patients using statistical analysis of the frequency of invasive procedures and logistic regression analysis for factors that affect the EOL care intensity. Results: Statistical analysis showed invasive procedures, such as intensive care unit admission, endotracheal intubation followed by mechanical ventilation and emergency dialysis, were performed more frequently in non-cancer patients than cancer patients (29.3% vs. 72.4%, P<0.001). And age (P=0.038) and morbidity of cancer (P<0.001) influenced the invasive procedural decision when analyzed by logistic regression analysis. Conclusion: The EOL care was more intensive in non-cancer patients, and age and morbidity of cancer were major factors for the treatment intensity.