• Journal of the Korean Data and Information Science Society
• /
• v.14 no.4
• /
• pp.817-824
• /
• 2003

We employed a hierarchical document classification method to classify a massive collection of electronic medical records(EMR) written in both Korean and English. Our experimental system has been learned from 5,000 records of EMR text data and predicted a newly given set of EMR text data over 68% correctly. We expect the accuracy rate can be improved greatly provided a dictionary of medical terms or a suitable medical thesaurus. The classification system might play a key role in some clinical decision support systems and various interpretation systems for clinical data.

• Journal of Biomedical Engineering Research
• /
• v.43 no.2
• /
• pp.109-115
• /
• 2022

Purpose: Medical records classification using vectorization techniques plays an important role in natural language processing. The purpose of this study was to investigate proper vectorization techniques for electronic medical records classification. Material and methods: 403 electronic medical documents were extracted retrospectively and classified using the cosine similarity calculated by Scikit-learn (Python module for machine learning) in Jupyter Notebook. Vectors for medical documents were produced by three different vectorization techniques (TF-IDF, latent sematic analysis and Word2Vec) and the classification precisions for three vectorization techniques were evaluated. The Kruskal-Wallis test was used to determine if there was a significant difference among three vectorization techniques. Results: 403 medical documents were relevant to 41 different diseases and the average number of documents per diagnosis was 9.83 (standard deviation=3.46). The classification precisions for three vectorization techniques were 0.78 (TF-IDF), 0.87 (LSA) and 0.79 (Word2Vec). There was a statistically significant difference among three vectorization techniques. Conclusions: The results suggest that removing irrelevant information (LSA) is more efficient vectorization technique than modifying weights of vectorization models (TF-IDF, Word2Vec) for medical documents classification.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.21 no.2
• /
• pp.198-204
• /
• 1999

The treatment of cleft lip and palate patients requires multidisciplinary coorperation, and the involved clinicians rely on the completeness and accuracy of the patient's medical records in developing comprehensive treatment plans. There are so many classifications in cleft lip and palate but each classification has advantages and disadvantages. Furthermore there are few classification or assessment in secondary cleft lip and palate deformities. A modification of Kenahan's Y classification in primary cleft lip and palate and new classification in secondary cleft lip and palate deformities are proposed as a simple and reproducible method. These reproducible classification may be used to facilitate not only storing and analyzing of medical informations in computer but also the planning of secondary repairs

• Quality Improvement in Health Care
• /
• v.12 no.2
• /
• pp.84-92
• /
• 2006

Background : To examine the difference between ICD-10 and The Korean standard classification of disease(oriental medicine), and to aim at improve the practical use as statistical data. It is one of the reason of disease classification. On that account we convert the many to many correspondence presenting classification of oriental medicine into many to one correspondence. Method : The study tracked out 155 patients discharged from the university hospital which is located in Gyeonggi Province and managing hospital and oriental medicine hospital from July to October this year. The period of this study was from August 1 to November 18. We compared correspondence between the two services' diagnosis(hospital services and oriental medicine hospital services) at the same time and attempted many to one correspondence classification. That is for production of statistical data. Result : We investigated the group which have had medical treatment experience of two kinds of services at the same time. The result of this investigation was that the same oriental medicine diagnosis used differently in western medicine diagnosis. 44.5% was accorded with western medicine diagnosis. Correspondence of the western medicine diagnose with the top of the Korean standard classification of disease(oriental medicine) list's western medicine diagnosis was 13.5%. For many to one correspondence classification for statistics, one western medicine diagnosis was selected for one oriental medicine diagnosis. In case of the main diagnosis(I sign) was not enough to explain oriental medicine diagnosis' characteristic, we chose multiple other diagnosis, so other diagnosis(II sign) about patient's cause of disease could be selected for supplement after we examined the patient's records. The statistics was possible with this many to one correspondence. Conclusion : The result of this study about correspondence between western medicine diagnoses and those of oriental medicine confirms that The Korean standard classification of disease(oriental medicine) is hard to be standardized with western medicine diagnosis. Therefore, according to this study, we use new many to one correspondence classification, multiple oriental medicine diagnoses with one ICD-10, which can be used by statistical data.

• Journal of Korean Society of Archives and Records Management
• /
• v.18 no.1
• /
• pp.155-175
• /
• 2018

The purpose of this study is to establish a classification system for the records of the Association for the Bereaved Families of the Hampyeong Massacre Victims. The content of the records is accordingly implemented through a functional source principle, and a classification table is presented in such a way that it reflects the characteristics by type and by production period so that the records can be used effectively. DIRKS, a methodology for the development of the functional classification system, is used to conduct a functional analysis of Hampyeong massacre victims' families to derive a task classification table that leads to task function-work activity-handling actions. The category is determined by taking into consideration the type and nature of the time of the production of the records of the Hampyeong massacre victims' families. The records are mapped according to the function classification system, which corresponds to the task classification table, and the multicategory system that drafts the type and period, which is used to classify the functions. The medical institution introduces a system for classifying records into task subjects, task activities, handling actions, types, and period.

• The Journal of Korean Medical History
• /
• v.32 no.2
• /
• pp.71-78
• /
• 2019

Jeon Suk-hee worked as permanent licensed Uisaeng (medical cadet) in Dalseong the Japanese occupation. The his newly discovered medical records were analyzed for the actual medical aspects of local Uisaeng. This article examined the medical view and treatment method of Jeon Suk-hee through the analysis of medical records, reveals facts which include : 1) The medical treatment was based on korean medical classification and treatment. This, along with the case of Cheongkang Kim Young-hoon, is an example of the preservation of traditional Korean medicine during the Japanese colonial period. 2) There is little effect of Shanghanlun (Treatise on Cold Damage). One side of Joseon medicine, which had a weak tradition of Shanghan, is revealed. 3) It did not simply follow the existing prescription of korean medicine's book. Examples include use of Cheongsin-san and Jeongjin-tang, which cannot be found in existing prescriptions.

• The Korean Journal of Emergency Medical Services
• /
• v.25 no.3
• /
• pp.71-80
• /
• 2021

Purpose: The purpose of this study is to investigate the characteristics and appropriateness of the Korean-type severity classification by ambulance based on the medical records of 43,561 emergency patients who were brought to the emergency medical center via ambulance between January 1, 2015 and December 31, 2017. Methods: This study analyzed the classification characteristics of the Korean severity classification tool by applying them to emergency patients who visited the emergency medical center. Results: As a result of the study first, among the categories of home hospitals according to the results of visits, "other," "low consciousness," and "dyspnea" in the order of 129 ambulances were statistically significantly higher. In the order of "low consciousness" and "trauma," the "trauma" category was 5.3% higher than that of 129 ambulances. Conclusion: Among the classification items, "others," "low consciousness," and "dyspnea" were significantly higher in the group of patients who boarded 129 ambulances, and "others," "low consciousness," and "traumatic" were significantly higher in the 119 ambulances.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.21 no.2
• /
• pp.151-161
• /
• 2014

Purpose: The purpose of this study was to identify the risk factors that influence surgical site infections after surgery. Methods: This study was a retrospective research utilizing Electronic Medical Records. Data collection targeted 4,510 adult patients who had 8 different kinds of surgery (gastric surgery, colon surgery, laparoscopic cholecystectomy, hip & knee replacement, hysterectomy, cesarean section, cardiac surgery) in 4 medical care departments, at one general hospital between January 2006 and December 2011. Multivariate logistic regression analyses were used to identify the risk factors affecting surgical site infections after surgery. Results: Risk factors for increased surgical site infection following surgery were confirmed to be age (OR=1.59, p<.001), BMI (Body Mass Index)(OR=1.25, p=.034), year of operation (OR=2.45, p<.001), length of operation (OR=3.06, p<.001), ASA (American Society of Anesthesiology) score (OR=1.36, p=.025), classification of antibiotic used (OR=2.77, p<.001), duration of the prophylactic antibiotics use (OR=1.85, p<.001), and interaction between classification of antibiotic used and duration of the prophylactic antibiotics use (OR=1.90, p=.016). Conclusions: Results suggest that risk factors affecting surgical site infections should be monitored before surgery. The results of this study should contribute to establishing effective infection management measures and implementing surveillance systems for patients who have actual risk factors.

• Journal of the Korean Society for information Management
• /
• v.29 no.3
• /
• pp.257-285
• /
• 2012

As the electronic medical records systems (EMRs) are introduced into the hospitals in Korea and the needs of chief stakehoders of medical records are changed, the environments related to creating and managing medical records has been changed dynamically. At this moment it might be meaningful to examine medical records based on records management principles rather than information management principles. The purpose of this paper is to apply the KS X ISO 1549 standards, which covers the principles of records management, to hospital medical records management and assess the current quality of medical records management, and define a few tasks of improvement for hospitals. To achieve this goal, this study has performed following activities: Firstly, principles that could be applied to medical records management were prepared for each record management steps described in the standards, such as capture, registration, classification, storage, access, trace and disposition, and 22 principles were selected from those 7 steps of the record management. Secondly, the Y hospital, which is affiliated with a medical school in Seoul, was chosen to evaluate the current situation regarding medical records management. The department head of the medical records management team in Y hospital was interviewed and the present status was evaluated according to each principle. Thirdly, tasks for improvement were suggested, in such stages as access, trace and disposition. With this study as a cornerstone, useful implications are expected to be gathered from future studies that apply standards for metadata of records, management systems for records, and record management systems to medical record management in hospitals.

• Industrial Engineering and Management Systems
• /
• v.4 no.1
• /
• pp.102-108
• /
• 2005

This paper studies medical data classification methods, comparing decision tree and system reconstruction analysis as applied to heart disease medical data mining. The data we study is collected from patients with coronary heart disease. It has 1,723 records of 71 attributes each. We use the system-reconstruction method to weight it. We use decision tree algorithms, such as induction of decision trees (ID3), classification and regression tree (C4.5), classification and regression tree (CART), Chi-square automatic interaction detector (CHAID), and exhausted CHAID. We use the results to compare the correction rate, leaf number, and tree depth of different decision-tree algorithms. According to the experiments, we know that weighted data can improve the correction rate of coronary heart disease data but has little effect on the tree depth and leaf number.