• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.35-40
• /
• 2022

In this paper, we propose a method of constructing clinical knowledge with clinical concept relations and predicting diseases based on a deep learning model to support clinical decision-making. Clinical terms in UMLS(Unified Medical Language System) and cancer-related medical knowledge are classified into five categories. Medical related documents in Wikipedia are extracted using the classified clinical terms. Clinical concept relations are established by matching the extracted medical related documents with the extracted clinical terms. After deep learning using clinical knowledge, a disease is predicted based on medical terms expressed in a query. Thereafter, medical terms related to the predicted disease are selected as an extended query for clinical document retrieval. To validate our method, we have experimented on TREC Clinical Decision Support (CDS) and TREC Precision Medicine (PM) test collections.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.323-325
• /
• 2014

SNOMED CT is a standard clinical terminology which is to efficiently record, manage and utilize clinical records during clinical processes. However, huge expressive power of SNOMED CT makes it difficult to select appropriate terms during short consultation hours. In addition, true meaning of a written record using the terminology may be misunderstood or even distorted since one clinical meaning could be expressed in a variety of ways. This paper analyzes such known problems in a database point of view, and presents effective selection methods of similar terminologies to mitigate the problem.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.20 no.4
• /
• pp.606-616
• /
• 2014

Purpose: This study compares differences between male and female nursing students in terms of the level of stress experienced during clinical practice settings, stress coping mechanisms and clinical competency. Method: The study population was nursing students who had taken a clinical practice course at one of five general hospitals in city D. Data were collected from September 15 to October 15, 2013 through a structured self-administered questionnaire survey given to 319 subjects (156 male students, 163 female students) enrolled in a statistical analysis course. Results: Male nursing students experienced lower stress levels during clinical practice and higher clinical competency than female students. In terms of stress coping mechanisms, male students were significantly more active than female students in deploying coping strategies. Among all students, students with higher clinical practice stress and concomitant stress coping scores exhibited higher clinical competency. Conclusion: Noticeable differences between male and female nursing students in terms of stress levels arising in the course of clinical practice, stress coping strategies, and clinical competency were revealed. However, further identification of specific stressful situations for male and female nursing students and subsequent management of clinical training circumstances are required.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.1
• /
• pp.167-173
• /
• 2011

Most of the terminologies used in medical domain is not intended to be applied directly in clinical setting but is developed to integrate the terms by defining the reference terminology or concept relations between the terms. Therefore, it is needed to develop the subsets of the terminology which classify categories properly for the purpose of use and extract and organize terms with high utility based on the classified categories in order to utilize the clinical terms conveniently as well as efficiently. Moreover, it is also necessary to develop and upgrade the terminology constantly to meet user's new demand by changing or correcting the system. This study has developed a mapping tool that allows accurate expression and interpretation of clinical terms used for medical records in electronic medical records system and can furthermore secure semantic interoperability among the terms used in the medical information model and generate common terms as well. The system is designed to execute both 1:1 and N:M mapping between the concepts of terms at a time and search for and compare various terms at a time, too. Also, in order to enhance work consistency and work reliability between the task performers, it allows work in parallel and the observation of work processes. Since it is developed with Java, it adds new terms in the form of plug-in to be used. It also reinforce database access security with Remote Method Invocation (RMI). This research still has tasks to be done such as complementing and refining and also establishing management procedures for registered data. However, it will be effectively used to reduce the time and expenses to generate terms in each of the medical institutions and improve the quality of medicine by providing consistent concepts and representative terms for the terminologies used for medical records and inducing proper selection of the terms according to their meaning.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.3
• /
• pp.537-542
• /
• 2015

SNOMED CT, which is a standard clinical terminology, imposes an ambiguity problem of terminology selections caused by its huge expressive power and structural complexity. It is very difficult to distinguish similar terms and to select an appropriate term among them within short consultation hours. This paper analyzes the ambiguity problem and proposes a novel scheme for comparative search of similar terms. The proposed scheme provides a differential view of similar terms by defining a "is-not-a" relationship based on the hierarchical structure of the concepts. The result of this work improves the utilization of SNOMED CT such that medical officers can efficiently select an appropriate term among similar terms which represents patient's status adequately.

• Journal of the Korean Society of Physical Medicine
• /
• v.16 no.4
• /
• pp.33-44
• /
• 2021

PURPOSE: This study analyzed the research trends related to the International Classification of Functioning, Disability, and Health (ICF) to suggest an ICF utilization plan in the Korean clinical field. METHODS: In the RISS, KISS, NSDL, and PubMed databases, papers published between 2016 and July 2021 were collected by applying the search terms, 'ICF', 'international classification of functioning, disability and health', 'clinic', 'patient', and 'diagno'. The 44 papers selected were classified according to the analysis criteria, and the frequency and percentage were calculated. RESULTS: In domestic clinical trials, the frequency of ICF-related studies was in the order of physical therapy (n = 19) and occupational therapy (n = 14). The frequency of each study subject was observed in the order of studies related to a specific disease (n = 34) and prior studies (n = 7). The research topics were in the order of studies using ICF as a measurement tool (n = 21) and case studies with patients with specific diseases (n = 11). There were 18 studies using ICF codes and 14 papers applying the ICF domains. CONCLUSION: Over the last five years, ICF-related research in the domestic clinical field targeted patients with more diverse diseases in more expertise fields. Research for the unification of terms should be conducted for communication among various experts in clinical practice. To promote the use of ICF in the clinical field, it will be necessary to conduct research, such as the unification of terms, standardized education, development of ICF casebook, and development of ICF coding programs and guidelines.

• Korean Journal of Clinical Laboratory Science
• /
• v.45 no.2
• /
• pp.60-65
• /
• 2013

Data from repeated measurements are accomplished through repeatedly processing the same subject under different conditions and different points of view. The power of testing enhances the choice of pertinent analysis methods that agrees with the characteristics of data concerned and the situation involved. Along with the clinical example, this paper compares the analysis of the variance on ex-post tests, gain score analysis, analysis by mixed design and analysis of covariance employable for repeating measure. Comparing the analysis of variance on ex post test, and gain score analysis on correlations, leads to the fact that the latter enhances the power of the test and diminishes the variance of error terms. The concluded probability, identified that the gain score analysis and the mixed design on interaction between "between subjects factor" and "within subjects factor", are identical. The analysis of covariance, demonstrated better power of the test and smaller error terms than the gain score analysis. Research on four analysis method found that the analysis of covariance is the most appropriate in clinical data than two repeated test with high correlation and ex ante affects ex post.

• Journal of Yeungnam Medical Science
• /
• v.36 no.3
• /
• pp.225-230
• /
• 2019

Background: It is not possible to measure how much activity is required to understand and code a medical data. We introduce an assessment method in clinical coding, and applied this method to neurosurgical terms. Methods: Coding activity consists of two stages. At first, the coders need to understand a presented medical term (informational activity). The second coding stage is about a navigating terminology browser to find a code that matches the concept (code-matching activity). Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT) was used for the coding system. A new computer application to record the trajectory of the computer mouse and record the usage time was programmed. Using this application, we measured the time that was spent. A senior neurosurgeon who has studied SNOMED CT has analyzed the accuracy of the input coding. This method was tested by five neurosurgical residents (NSRs) and five medical record administrators (MRAs), and 20 neurosurgical terms were used. Results: The mean accuracy of the NSR group was 89.33%, and the mean accuracy of the MRA group was 80% (p=0.024). The mean duration for total coding of the NSR group was 158.47 seconds, and the mean duration for total coding of the MRA group was 271.75 seconds (p=0.003). Conclusion: We proposed a method to analyze the clinical coding process. Through this method, it was possible to accurately calculate the time required for the coding. In neurosurgical terms, NSRs had shorter time to complete the coding and higher accuracy than MRAs.

• Journal of dental hygiene science
• /
• v.7 no.1
• /
• pp.37-47
• /
• 2007

Targeting dental hygienists who work in clinical division and public dental health division, this study was to investigate and analyze their working environment by work division, so that it could make basic material available in the interest of efficiently employing technical manpower specializing in public health and their better work environment in the future. 1. In terms of the sociodemographic characteristics of respondents, it was found that employees in public health were married in higher percentage and had higher age with longer career than those in clinical division, and it was noted that the former group had higher percentage in longer academic career than the latter group. 2. In terms of working days and hours, it was found that dental hygienists employed in public health worked 5 days a week(95.8%), while those in clinical division worked 6 days a week(70.3%). That is, the latter group worked longer days a week than the former group. 3. In terms of annual regular holidays, it was found that dental hygienists in public health division mostly took 11 to 20 days off a year, while those in clinical division mostly took 1 to 3 days off a year. That is, the former group is significant different in annual holidays from the latter group. 4. In terms of pay and allowances, it was found that most of public health group(89.4%) got monthly pay, while most of clinical group(65.4%) got the pay in annual salary. 5. In terms of reorientation experiences, it was found that 63.5% of total respondents didn't have any opportunity of domestic and overseas reorientation. And in terms of financial sponsorship for reorientation, it was noted that 54.0% of total respondents were financially supported for their reorientation by the institution they work for. 6. In terms of in-house welfare environment for married employees, it was found that 85.5% respondents ever faced no discrimination in job opportunities. In terms of the availability of maternity leave, it was noted that 69.2% respondents used the maternity leave, and 74.8% respondents used the maternity leave during 3 months. 7. In terms of quitting job, it was found that 46.8% respondents had ever left their job(public health group: 53.8%, clinical group: 45.8%), while the remaining 53.2% respondents(public health group: 46.2%, clinical group: 54.2%) had never left their job. Here, it is found that the employees in public health accounted for somewhat higher percentage in quitting job than those in clinical division. In terms of the number of leaving job, it was noted that most(50.8%) respondents left their job once, and there were similar distributions in quitting job between these both groups. In terms of the reason for quitting job, it was found that 29.2% respondents left their job due to desire for better pay(allowance) and working conditions.

• Korean Journal of Clinical Pharmacy
• /
• v.25 no.3
• /
• pp.151-158
• /
• 2015

Objective: This study was designed to compare pegfilgrastim and filgrastim in diffuse large B-cell lymphoma (DLBCL) patients treated with a rituximab with cyclophosphamide, hydroxydaunorubicin, oncovin, and prednisone (R-CHOP) regimen in terms of clinical efficacy and cost-effectiveness. Method: Clinical efficacy was measured by trough level of absolute neutrophil count (ANC), days of ANC under 50% of baseline value, days of ANC under 90% of baseline value, duration of ANC recovery to baseline value, days of ANC less than $0.5{\times}10^9cells/L$, and difference of peak and trough level of ANC during 1 cycle of R-CHOP regimen. To evaluate cost-effectiveness, total prices of used filgrastim and pegfilgrastim within 1 cycle of R-CHOP were analyzed. Results: In terms of clinical efficacy, trough level of ANC and days to ANC recovery showed statistical significance. The median trough levels of ANC with administration of filgrastim and pegfilgrastim were 0.18 and 1.94 (p = 0.021), respectively, and the median durations of ANC recovery to baseline value were 5.5 days and 2 days (p = 0.023), respectively. For the median days of ANC under 50% of baseline value, days of ANC under 90% of baseline value, days of ANC less than $0.5{\times}10^9cells/L$, and difference of peak and trough level of ANC during 1 cycle of R-CHOP, the pegfilgrastim group performed better than the filgrastim group. However the difference was not statistically significant. In terms of overall expense during 1 cycle of R-CHOP, pegfilgrastim is about 3.43 times more expensive than filgrastim. Conclusion: Pegfilgrastim is more efficient than filgrastim in terms of clinical efficacy. In terms of prices, pegfilgrastim is more expensive than filgrastim for patients, but it is more convenient in clinical use. Therefore, pegfilgrastim should be the preferred choice of G-CSF for neutropenic patients. Further comparative study of pegfilgrastim and filgrastim is needed.