• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.51-55
• /
• 2016

본 논문에서는 임상 의사 결정 지원을 위한 UMLS와 위키피디아를 이용하여 지식 정보를 추출하고 질병 중심 문서 클러스터와 단어 의미 표현을 이용하여 질의 확장 및 문서를 재순위화하는 방법을 제안한다. 질의로는 해당 환자가 겪고 있는 증상들이 주어진다. UMLS와 위키피디아를 사용하여 병명과 병과 관련된 증상, 검사 방법, 치료 방법 정보를 추출하고 의학 인과 관계를 구축한다. 또한, 위키피디아에 나타나는 의학 용어들에 대하여 단어의 효율적인 의미 추정 기법을 이용하여 질병 어휘의 의미 표현 벡터를 구축하고 임상 인과 관계를 이용하여 질병 중심 문서 클러스터를 구축한다. 추출한 의학 정보를 이용하여 질의와 관련된 병명을 추출한다. 이후 질의와 관련된 병명과 단어 의미 표현을 이용하여 확장 질의를 선택한다. 또한, 질병 중심 문서 클러스터를 이용하여 문서 재순위화를 진행한다. 제안 방법의 유효성을 검증하기 위해 TREC Clinical Decision Support(CDS) 2014, 2015 테스트 컬렉션에 대해 비교 평가한다.

• Journal of Korean Ophthalmic Optics Society
• /
• v.9 no.2
• /
• pp.233-239
• /
• 2004

This study investigated the status of soft contact lens wear in college students. The results were as follows: 1. The most prevalent age of initial contact lens wear was 19 years or 20 years, with an age distribution in females from as early as 10 years to 20 years. 2. For almost all subjects, the test clinic for the contact lens wear assessment and purchase of the contact lenses was an optical shop. 3. The main advantage for most male subjects was use for sports, whereas most female subjects used contact lenses for cosmetic reasons. 4. The most common side-effects experienced due to contact lens wear were red eye, foreign body sensation, and eye pain. 5. The most frequently reported eye disease caused by contact lens wear was conjunctivitis, with only few subjects experiencing keratitis. 6. Following treatment for the side effects of contact lens wear, most subjects hoped to re-use the previous contact lenses, some subjects wanted to change to new contact lenses, and others subjects refused further contact lens wear.

• Journal of Korean Ophthalmic Optics Society
• /
• v.18 no.2
• /
• pp.93-99
• /
• 2013

Purpose: The aim of this study was to develop a dry eye test method using a paper based microfluidic device that improves inaccuracy caused by using one of current point-of-care dry eye tests such as Shirmer's. Methods: Wax printed hydrophilic chromatography papers were dyed with anthocyanin extracts to detect colorimetric display of liquid samples with varying pH. Fluid distribution rates were measured using artificial tears and human tears directly from 32 subjects. Results: With Shirmer's, fluid distribution rates with small amount of samples (less than $0.5{\mu}l$) were not displayed. However, with paper based microfluidic device, fluid imbibition distances over time were clearly showed. Also clinical results of dry eye from newly developed paper based microfluidic device showed correlation with the results from tear break up time tests. Conclusions: The newly developed paper based microfluidic devices were easy to use and exhibited more accurate clinical results than current dry eye point of care tests such as Shirmer's.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.13-22
• /
• 2021

The clinical decision support system uses accumulated medical data to apply an AI model learned by machine learning to patient diagnosis and treatment prediction. However, the existing black box-based AI application does not provide a valid reason for the result predicted by the system, so there is a limitation in that it lacks explanation. To compensate for these problems, this paper proposes a system model that applies XAI that can be explained in the development stage of the clinical decision support system. The proposed model can supplement the limitations of the black box by additionally applying a specific XAI technology that can be explained to the existing AI model. To show the application of the proposed model, we present an example of XAI application using LIME and SHAP. Through testing, it is possible to explain how data affects the prediction results of the model from various perspectives. The proposed model has the advantage of increasing the user's trust by presenting a specific reason to the user. In addition, it is expected that the active use of XAI will overcome the limitations of the existing clinical decision support system and enable better diagnosis and decision support.

• Korean Journal of Clinical Laboratory Science
• /
• v.56 no.2
• /
• pp.105-114
• /
• 2024

Clinical laboratories endeavor to secure quality by establishing effective quality management systems. However, laboratory environments are complex, and single quality control procedures may inadequately detect many errors. Patient-based real-time quality control (PBRTQC) is a laboratory tool that monitors the testing process using algorithms such as Bull's algorithm and several variables, such as average of normal, moving median, moving average, and exponentially weighted moving average. PBRTQC has many advantages over conventional quality control, including low cost, commutability, continuous real-time performance monitoring, and sensitivity to pre-analytical errors. However, PBRTQC is not easily implemented as it requires statistical algorithm selection, the design of appropriate rules and protocols, and performance verification. This review describes the basic concepts, methods, and procedures of PBRTQC and presents guidelines for implementing a patient-based quality management system. Furthermore, we propose the combined use of PBRTQC when the performance of internal quality control is limited. However, clinical evaluations were not conducted during this review, and thus, future evaluation is required.

• Journal of Biomedical Engineering Research
• /
• v.16 no.4
• /
• pp.555-561
• /
• 1995

In this paper, the O-Ring Measurement System (O-R MS) has been designed to supplement such subectivity and apply to the diagnosis by constitution. A single chip microprocessor of Intel MCS-51 family has been used to control the O-R MS and process data with real time, and the O-R MS could measure the minute muscular strength, expanded width between fingers, and time of the measurement. Therefore the objective constitutional diagnosis is possible by the O-R MS. As a clinical testing for estimating credibility of O-R MS, the acupuncture points representing the constitution has been stimulated using a semiconductor laser stimulator and measure the muscular strength by the O-R MS. The result of clinical testing has been shown that the constitutional diagnosis with the O-R MS is proved highly precision of 96% and it is expected that the O-R MS can be used practically for the objective constitutional diagnosis.

• Korean Journal of Clinical Laboratory Science
• /
• v.54 no.2
• /
• pp.79-94
• /
• 2022

Due to the highly contagious nature and severity of the respiratory diseases caused by COVID-19, economical and accurate tests are required to better monitor and prevent the spread of this contagion. As the structural and molecular properties of SARS-CoV-2 were being revealed during the early stage of the COVID-19 pandemic, many manufacturers of COVID-19 diagnostic kits actively invested in the design, development, validation, verification, and implementation of diagnostic tests. Currently, diagnostic tests for SARS-CoV-2 are the most widely used and validated techniques for rapid antigen, and immuno-serological assays for specific IgG and IgM antibody tests and molecular diagnostic tests. Molecular diagnostic assays are the gold standard for direct detection of viral RNA in individuals suspected to be infected with SARS-CoV-2. Antibody-based serological tests are indirect tests applied to determine COVID-19 prevalence in the community and identify individuals who have obtained immunity. In the future, it is necessary to explore technical problems encountered in the early stages of global or regional outbreaks of pandemics and provide future directions for better diagnostic tests. This article evaluates the commercially available and FDA-approved molecular and immunological diagnostic assays and analyzes their performance characteristics.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.26 no.6
• /
• pp.447-454
• /
• 2013

A model-based method is proposed to diagnose the gear crack in the gearbox under variable loading condition with the objective to apply it to the wind turbine CMS(Condition Monitoring System). A simple test bed is installed to illustrate the approach, which consists of motors and a pair of spur gears. A crack is imbedded at the tooth root of a gear. Tachometer-based order analysis, being independent on the shaft speed, is employed as a signal processing technique to identify the crack through the impulsive change and the kurtosis. Lumped parameter dynamic model is used to simulate the operation of the test bed. In the model, the parameter related with the crack is inversely estimated by minimizing the difference between the simulated and measured features. In order to illustrate the validation of the method, a simulated signal with a specified parameter is virtually generated from the model, assuming it as the measured signal. Then the parameter is inversely estimated based on the proposed method. The result agrees with the previously specified parameter value, which verifies that the algorithm works successfully. Application to the real crack in the test bed will be addressed in the next study.

• Journal of Convergence for Information Technology
• /
• v.12 no.2
• /
• pp.192-197
• /
• 2022

Although various studies have focused on the relationship between essential oils (EOs) and skin flora, there are only few comparative studies on the antibacterial properties of EOs and their efficacy against common microorganisms. In this study, we tested the antibacterial activity of 10 different EOs against Staphylococcus epidermidis(S. epidermidis) with oxacillin as control. Optical density was used to measure the activity of solutions containing the EOs and S. epidermidis at two different concentrations. Three EOs (palmarosa, lemongrass, and Mellissa True) had higher antibacterial activity than oxacillin, but their concentrations had negligible effect on antibacterial activity.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.33 no.1 s.60
• /
• pp.29-32
• /
• 2007

We investigated new ingredients with real efficacy in both in vitro and in vivo all together. Especially we focused on the real improving effort in the clinical experiments. Because most products containing effective materials evaluated in vitro failed to show a real improving effect in the human with acne. We evaluated the well-known ingredients in a small scale clinical experiment with half-finished goods containing each ingredient. Among these products, product formulating SeleMix AN composed with germinating soy bean and magnolias bark extract remarkably improved acne and acne scar. Moreover skin redness caused by severe acne was improved. There was statistical significance between placebo and sample. Two hundred volunteers participated in our pilot study with written informed consent. After then we performed in vitro efficacy test this ingredient. SeleMix AN inhibited the growth of propionibacterium acnes at a concentration of 0.0125% and suppressed histamine release by 16.9%. Moreover human fibroblast cell activity was increased by 57% compared to control. Lastly, we performed a clinical study. Consisting of groups of 23 volunteers. Although the period of the test was in summer accelerating sebum secretion and recurring a high tate of acne, inflammation lesions were especially improved after applying product containing SeleMix AN for 4 weeks.