• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.28-37
• /
• 2011

With growing concerns about healthy life recently, although the podiatry which deals with the whole area for diagnosis, treatment of foot and leg, and prevention has been widely interested, research in our country is not active. Also, because most of the previous researches in data analysis performed the quantitative approaches, the reasonable level of reliability for clinical application could not be guaranteed. Clinical data mining utilizes various data mining analysis methods for clinical data, which provides decision support for expert's diagnosis and treatment for the patients. Because the decision tree can provide good explanation and description for the analysis procedure and is easy to interpret the results, it is simple to apply for clinical problems. This study investigate rules of item of diagnosis in disease types for adapting decision tree after collecting diagnosed data patients who are 2620 feet of 1310(males:633, females:677) in shoes clinic (department of rehabilitation medicine, Chungnam National University Hospital). and we classified 15 foot diseases followed factor of 22 foot diseases, which investigated diagnosis of 64 rules. Also, we analyzed and compared correlation relationship of characteristic of disease and factor in types through made decision tree from 5 class types(infants, child, adolescent, adult, total). Investigated results can be used qualitative and useful knowledge for clinical expert`s, also can be used tool for taking effective and accurate diagnosis.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.219-225
• /
• 2014

A Gompertz modeling, sigmoid in shape, is a widely used application for social science, natural science, engineering, and medical research to allow confident approximation and accurate analysis and has been applied to estimate an elderly population on aging of population. Due to the high toxicity of currently available drug delivery vehicles, various efforts have been made to reduce side-effects in clinical fields, but its application to preclinical and clinical studies is limited and there are some difficulties to optimize the parameters of Gompertz modeling applicable to preclinical studies. Therefore, in this study, we demonstrated the ability of sickle red blood cells loaded by hypotonic dialysis then photosensitized and light-activated ex vivo for controlled release and simultaneously optimized Gompertz function to evaluate controlled drug release properties of photosensitized sickle red blood cells to reduce pain-related treatments in cancer patients.

• Journal of the Korean Institute of Gas
• /
• v.24 no.6
• /
• pp.11-17
• /
• 2020

In order to guarantee safe storage and transportation of a flammable liquid solution, it is very important to know its flash point information. In this paper, flash points of n-octane+n-nonane system and n-nonane+n-decane system were measured by Seta flash apparatus and an empirical equation is proposed for the accurate estimation of flash point. Empirical equation is used to predict flash point of n-octane+n-nonane system and n-nonane+n-decane system, which were also compared to Unifac-based model. Absolute average errors of flash point data predicted by Unifac-based model are 0.7℃ and 0.6℃ for n-octane+n-nonane system and n-nonane+n-decane system, respectively. Absolute average errors of flash point data predicted by empirical equation are 0.2℃ and 0.4℃ for n-octane+n-nonane system and n-nonane+n-decane system, respectively. In conclusion, empirical equation proposed in this paper, presented the most satisfactory.

• Journal of Digital Convergence
• /
• v.21 no.3
• /
• pp.33-39
• /
• 2023

This study is a performance evaluation of a blood sugar monitoring system that combines a PPG sensor, which is an evaluation device for blood glucose monitoring, and a DNN algorithm when monitoring capillary blood glucose. The study is a researcher-led clinical trial conducted on participants from September 2023 to November 2023. PPG-BGMS compared predicted blood sugar levels for evaluation using 1-minute heart rate and heart rate variability information and the DNN prediction algorithm with capillary blood glucose levels measured with a blood glucose meter of the standard personal blood sugar management system. Of the 100 participants, 50 had type 2 diabetes (T2DM), and the average age was 67 years (range, 28 to 89 years). It was found that 100% of the predicted blood sugar level of PPG-BGMS was distributed in the A+B area of the Clarke error grid and Parker(Consensus) error grid. The MARD value of PPG-BGMS predicted blood glucose is 5.3 ± 4.0%. Consequentially, the non-blood-based PPG-BGMS was found to be non-inferior to the instantaneous blood sugar level of the clinical standard blood-based personal blood glucose measurement system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.54-62
• /
• 2007

In this paper, we significantly reduces the amount of computation for intra 16$\times$16 mode decision in H.264 by applying the fast algorithm, which obtains the transformed prediction residual with fewer computations. By extending the existing intra 4$\times$4 mode decision, we propose the new algorithm for fast intra 16$\times$16 mode decision. The proposed algorithm uses partial transform coefficients which consist of one DC and three adjacent AC coefficients after 4$\times$4 transform in the intra 16$\times$16 mode decision. Theoretical analysis and experimental results show that the proposed algorithm can reduce computations up to 50% in the intra 16$\times$16 mode decision process with unnoticeable degradation.

• The Journal of Engineering Geology
• /
• v.26 no.1
• /
• pp.23-32
• /
• 2016

This study evaluates landslide susceptibility using statistical analysis by SVM (support vector machine) and the illite index of clay minerals extracted from ASTER(advanced spaceborne thermal emission and reflection radiometer) imagery which can be use to create mineralogical mapping. Landslide locations in the study area were identified from aerial photographs and field surveys. A GIS spatial database was compiled containing topographic maps (slope, aspect, curvature, distance to stream, and distance to road), maps of soil properties (thickness, material, topography, and drainage), maps of timber properties (diameter, age, and density), and an ASTER satellite imagery (illite index). The landslide susceptibility map was constructed through factor correlation using SVM to analyze the spatial database. Comparison of area under the curve values showed that using the illite index model provided landslide susceptibility maps that were 76.46% accurate, which compared favorably with 74.09% accuracy achieved without them.

• Journal of Hospice and Palliative Care
• /
• v.11 no.2
• /
• pp.99-105
• /
• 2008

Purpose: In terminally ill cancer patients, accurate prediction of survival is necessary for clinical and ethical reasons, especially in helping to avoid harm, discomfort and inappropriate therapies and in planning specific care strategies. The aim of the study was to investigate prognostic factor of dying patients. Methods: We enrolled the terminal cancer patients from Kangnam St. Mary's Hospital from 2004 until their death. We observed symptoms shown in dying patients and assess 17 common symptoms shown in terminally ill cancer patients, performance status, pain and analgesic use. Results: Average period from hospitalization to death was 11.7 days. The most important prognostic factor is performance status (KPS), average KPS at enrollment is 48% and at last 48 hours is 25%. Physical symptoms that have significant prognostic importance are poor oral intake, weakness, constipation, decreased Karnofsky performance status, bed sore, edema, jaundice, dry mouth, dyspnea. Dying patients showed markedly decreased systolic blood pressure, cyanosis, drowsiness, abnormal respiration, death rattle frequently at 48 hours before death. Conclusion: If we assess the symptoms more carefully, we can predict the more accurate prognosis. The communication about the prognostic information will influence the personal therapeutic decision and specific care planning.

• Journal of Chest Surgery
• /
• v.37 no.5
• /
• pp.423-431
• /
• 2004

Background : Tumor size in lung cancer is not as good a prognostic factor for adenocarcinoma as it is for other types of lung cancer; therefore it is difficult to estimate the prognosis preoperative. However, there have recently been some reports on the radiologic findings correlating to the clinicopathologic prognostic factors in peripheral small adenocarcinoma of lung. We tried to evaluate the prognostic importance of High-Resolution CT (HRCT) findings of such adenoearcinoma, Material and Method: One houndred and seventy-six surgically resected small peripheral adenocarcinoma measuring 3 cm or less in greatest dimension were reviewed radiologically and clinicopathologically. Result: The patients with greater extent of ground-glass attenuation (GGA) had better clinico-pathological factors. The tumors with gross appearance of GGA or bubble-like shape showed better clinicopathological prognostic factors than scar-like or solid shape. Conclusion: HRCT findings of small peripheral adenocarcinomas of the lung correlated well with the histologic and clinical prognostic factors. We can predict the post-operative prognosis with the radiologic findings.

• Clinical and Experimental Pediatrics
• /
• v.53 no.2
• /
• pp.222-227
• /
• 2010

Purpose : To evaluate the significance of clinical signs and laboratory findings as predictors of renal parenchymal lesions and vesicoureteral reflux (VUR) in childhood urinary tract infection (UTI). Methods : From July 2005 to July 2008, 180 patients admitted with a first febrile UTI at the Pediatric Department of Konkuk University Hospital were included in this study. The following were the clinical variables: leukocytosis, elevated C-reactive protein (CRP), positive urine nitrite, positive urine culture, and fever duration both before and after treatment. We evaluated the relationships between clinical variables and dimercaptosuccinic acid (DMSA) scan and voiding cystourethrography (VCUG) results. Results : VCUG was performed in 148 patients; of them, 37 (25.0%) had VUR: 18 (12.2%) had low-grade (I-II) VUR, and 19 (10.5%) had high-grade (III-V) VUR. Of the 95 patients who underwent DMSA scanning, 29 (30.5%) had cortical defects, of which 21 (63.6%) had VUR: 10 (30.3%), low-grade (I-II) VUR; and 11 (33.3%), high-grade VUR. Of the 57 patients who were normal on DMSA scan, 8 (14.0%) had low-grade VUR and 6 (10.5%) had high-grade VUR. The sensitivity, specificity, and positive and negative predictive values of the DMSA scan in predicting high-grade VUR were 64.7%, 69.9%, 33.3%, and 89.5%, respectively. Leukocytosis, elevated CRP, and prolonged fever ($36{\geq}$ hours) after treatment were significantly correlated with the cortical defects on DMSA scans and high-grade VUR. Conclusion : Clinical signs, including prolonged fever after treatment, elevated CRP, and leukocytosis, are positive predictors of acute pyelonephritis and high-grade VUR.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.541-546
• /
• 2021

Recently, there is a trend of developing various identification and prediction models for hypertension using clinical information based on artificial intelligence and machine learning around the world. However, most previous studies on identification or prediction models of hypertension lack the consideration of the ideas of non-invasive and cost-effective variables, race, region, and countries. Therefore, the objective of this study is to present hypertension prediction model that is easily understood using only general and simple sociodemographic variables. Data used in this study was based on the Korea National Health and Nutrition Examination Survey (2018). In men, the model using the naive Bayes with the wrapper-based feature subset selection method showed the highest predictive performance (ROC = 0.790, kappa = 0.396). In women, the model using the naive Bayes with correlation-based feature subset selection method showed the strongest predictive performance (ROC = 0.850, kappa = 0.495). We found that the predictive performance of hypertension based on only sociodemographic variables was higher in women than in men. We think that our models based on machine leaning may be readily used in the field of public health and epidemiology in the future because of the use of simple sociodemographic characteristics.