• 한국산학기술학회논문지
• /
• 제18권10호
• /
• pp.354-362
• /
• 2017

인구 고령화와 서구화된 생활로 인한 허혈성 심장질환이 지속적으로 증가하고 있으며, 우리나라는 OCED 국가 중에서 허혈성 심장질환의 재원일수가 높은 국가에 속한다. 재원일수 증가는 진료비 상승의 주요 원인이므로, 허혈성 심장질환의 재원일수 관리방안 마련이 필요하다. 이에 본 연구는 허혈성 심장질환자의 재원일수에 영향을 미치는 요인을 파악하여 재원 일수 관리에 필요한 기초자료를 제공하고자 시도되었다. 연구대상자는 일개 상급종합병원의 2015년1월1일부터 12월31일까지 순환기내과의 퇴원환자 중에서 주진단명이 허혈성 심장질환인 환자 566명이다. 자료분석은 IBM SPSS ver. 23.0을 이용하여 빈도분석, 교착분석, Fisher's test, One-way ANOVA, $Scheff{\acute{e}}$ test, 더미변수를 이용한 다중회귀분석을 실시하였다. 연구결과는 첫째, 흉통을 주호소로 입원한 환자가 가장 많았다. 둘째, 평균 재원일수는 4.89일이었으며, 허혈성 심장질환 종류별로 재원일수에 차이가 있었다. 셋째, 75세이상, 당뇨병, 호흡곤란 증상이 재원일수를 증가시키는 요인으로 나타났다. 따라서 허혈성 심장질환의 적정 재원일수 관리를 위해서는 당뇨병을 동반한 허혈성 심장질환자의 경우에는 혈당조절을 통해서 질병의 진행을 막는 것이 중요하며, 증상이 나타났을 경우 빠른 시간 내에 의료기관을 방문할 수 있는 체계마련이 필요하다.

• Journal of Hospice and Palliative Care
• /
• 제25권1호
• /
• pp.12-24
• /
• 2022

Purpose: This descriptive study compared the perceptions, determinants, and needs of patients, family members, nurses, and physicians regarding life-sustaining treatment decisions for patients with hematologic malignancies in the hematology-oncology department of a tertiary hospital in Seoul, Korea. Methods: In total, 147 subjects were recruited, gave written consent, and provided data by completing a structured questionnaire. Data were analyzed using analysis of variance, the chi-square test, and the Fisher exact test. Results: Nurses (F=3.35) and physicians (F=3.57) showed significantly greater familiarity with the Act on Decisions on Life-Sustaining Treatment than patients (F=2.69) and family members (F=2.59); (F=19.58, P<0.001). Many respondents, including 19 (51.4%) family members, 16 (43.2%) physicians, and 11 (29.7%) nurses, agreed that the patient's opinion had the greatest effect when making life-sustaining treatment decisions. Twelve (33.3%) patients answered that mental, physical, and financial burdens were the most important factors in life-sustaining treatment decisions, and there was a significant difference among the four groups (P<0.001). Twenty-four patients (66.7%), 27 (73.0%) family members, and 21(56.8%) nurses answered that physicians were the most appropriate people to provide information regarding life-sustaining treatment decisions. Unexpectedly, 19 (51.4%) physicians answered that hospice nurse practitioners were the most appropriate people to talk to about life-sustaining treatment (P<0.001). Conclusion: It is of utmost importance that the patient and physician determine when life-sustaining treatment should be withdrawn, with the patient making the ultimate decision. Doctors and nurses have the responsibility to provide detailed information. The goal of end-of-life planning is to ensure patients' dignity and respect their values.

• 지능정보연구
• /
• 제25권4호
• /
• pp.105-122
• /
• 2019

텍스트 데이터가 특정 범주에 속하는지 판별하는 문장 분류에서, 문장의 특징을 어떻게 표현하고 어떤 특징을 선택할 것인가는 분류기의 성능에 많은 영향을 미친다. 특징 선택의 목적은 차원을 축소하여도 데이터를 잘 설명할 수 있는 방안을 찾아내는 것이다. 다양한 방법이 제시되어 왔으며 Fisher Score나 정보 이득(Information Gain) 알고리즘 등을 통해 특징을 선택 하거나 문맥의 의미와 통사론적 정보를 가지는 Word2Vec 모델로 학습된 단어들을 벡터로 표현하여 차원을 축소하는 방안이 활발하게 연구되었다. 사전에 정의된 단어의 긍정 및 부정 점수에 따라 단어의 임베딩을 수정하는 방법 또한 시도하였다. 본 연구는 문장 분류 문제에 대해 선택적 단어 제거를 수행하고 임베딩을 적용하여 문장 분류 정확도를 향상시키는 방안을 제안한다. 텍스트 데이터에서 정보 이득 값이 낮은 단어들을 제거하고 단어 임베딩을 적용하는 방식과, 정보이득 값이 낮은 단어와 코사인 유사도가 높은 주변 단어를 추가로 선택하여 텍스트 데이터에서 제거하고 단어 임베딩을 재구성하는 방식이다. 본 연구에서 제안하는 방안을 수행함에 있어 데이터는 Amazon.com의 'Kindle' 제품에 대한 고객리뷰, IMDB의 영화리뷰, Yelp의 사용자 리뷰를 사용하였다. Amazon.com의 리뷰 데이터는 유용한 득표수가 5개 이상을 만족하고, 전체 득표 중 유용한 득표의 비율이 70% 이상인 리뷰에 대해 유용한 리뷰라고 판단하였다. Yelp의 경우는 유용한 득표수가 5개 이상인 리뷰 약 75만개 중 10만개를 무작위 추출하였다. 학습에 사용한 딥러닝 모델은 CNN, Attention-Based Bidirectional LSTM을 사용하였고, 단어 임베딩은 Word2Vec과 GloVe를 사용하였다. 단어 제거를 수행하지 않고 Word2Vec 및 GloVe 임베딩을 적용한 경우와 본 연구에서 제안하는 선택적으로 단어 제거를 수행하고 Word2Vec 임베딩을 적용한 경우를 비교하여 통계적 유의성을 검정하였다.

• 여성건강간호학회지
• /
• 제6권3호
• /
• pp.413-426
• /
• 2000

The purposes of this study is to examine the degree of dysmenorrhea and self-management of dysmenorrhea in high school girls and to provide basic information for health education. This research is the contents of the characteristics and self-management of dysmenorrhea and thereby serve to provide some theoretical grounds for the health education of high school-girl students. The subjects of this study are the 376 girl students of a high school in Taegu. This study was conducted by collecting data from April 3rd to 7th, 2000. The instruments used for this study by the researcher of this study based on Choi, Myung-Ok's (1992) menstrurational symtom scale (8 items) and factors used to dysmenorrhea scale (5 items). Health locus of control is obtained from a review of references by the researcher, Sin Jae Sin (1985) translated Multidimensional health Locus of Control scale (18 items) were made by Wallston & Wallston (1976). The collected data was analysed by mean, percent, Chi-squre test, Fisher's Exact Test using the SPSS (v 6.12) and SAS program. The results of this study were as follows : 1. The characteristics of dysmenorrhea were low abdominal pain, fatigue, back pain, headache, muscle pain, diarrhea, nausea and vomiting. 2. The degree of dysmenorrhea was shown 'a few of discomfort experiment': 73%, late, leaving early and absent for school : 4.0%. 3. By means locus of control, internal health locus of control was shown 79.5% and external health locus of control was shown 20.5%. 4. The self-management of dysmenorrhea was shown 'massaging on the abdomen and bed rest' is 31.9%, 'tolerance' is 53.5%. 5. When the characteristics of dysmenorrhea was compared with demographics, low abdominal pain was significant of the number of siblings (p<.05), the family history (mother's dysmenorrhea)(p<.01) and back pain was significant of the age, family history, low abdominal pain (p<.05, p<.01, p<.01). 6. There was no significant of the locus of control. When the self-management of dysmenorrhea was compared with demographics, the age was significant (p<.05).

• 전자공학회논문지CI
• /
• 제42권4호
• /
• pp.33-42
• /
• 2005

본 논문에서는 소속 함수와 신경망을 이용한 유전자 발현 정보의 분류 기법을 제안한다. 유전자 발현은 유전자가 mRNA와 생체의 기능을 일으키게 하는 단백질을 만들어내는 과정이다. 유전자 발현에 대한 정보는 유전자의 기능을 밝히고 유전자간의 상관 관계를 알아내는데 중요한 역할을 한다. 이러한 유전자 발현 연구를 위한 정보를 대량으로 신속하게 얻을 수 있는 도구가 DNA 칩이다. DNA 칩으로 얻은 수백$\~$수천개의 데이터는 그 데이터만으로는 의미를 갖지 못한다. 따라서 유전자 발현정도에 따라 수치적으로 획득된 데이터에서 의미적인 특성을 찾아내기 위해서는 클러스터링 방법이 필요하다. 본 논문에서는 수많은 유전자 데이터 중에서 주요 정보를 포함한 것으로 판단되는 유전자 데이터를 피셔 기준에 의하여 선택한다. 이때 선택된 데이터들이 클러스터링에 효과적인 데이터라고 보장할 수 없으므로, 클러스터링 성능을 저해하는 유전자 데이터의 영향력을 감소시키기 위해서 소속 함수를 이용하여 특징값을 계산하고, 계산된 특징값으로 얻은 특징 벡터들을 적용하여 역전파 신경망 학습을 수행한다. 본 논문에서 제안한 유전자 발현 정보의 분류 결과로 얻은 클러스터링의 성능은 기존의 연구 결과와 비교했을 때 다양한 유전자 데이터에 대하여 향상된 인식율을 보이는 것을 확인할 수 있었다.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1244-1244
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from mastitic and healthy cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from mastitic and healthy cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA and FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference, thereby providing a useful means for spectroscopy-based clinic applications.

• 한국임상약학회지
• /
• 제20권2호
• /
• pp.159-164
• /
• 2010

Radiofrequency ablation (RA) is being used to manage atrial fibrillation (AF) with patients failed at the $1^{st}$-line anti-arrhythmic medications. Patients undergoing this procedure are at increased risk of thromboembolism after ablation, and anticoagulation management surrounding the ablation remains controversial. Although no conclusive recommendations can be made, published guidelines and data support therapeutic anticoagulation with warfarin. The purpose of this study was to analyze effectiveness of current therapy and to find factors fluctuate International Normalized Ratio (INR) values in patients undergone RA followed by anticoagulation service (ACS). Retrospective review was conducted utilizing database in a hospital. Among 110 patients under warfarin around ablation between January 2006 to September 2007, 54 patients were selected and allocated into 2 groups: Group A included 47 who discontinued warfarin after ablation, while 7 in B continued the medication. Information on demographics, amount and length of warfarin dosing, INR values and measuring frequencies, and the causing factors on INR fluctuation were abstracted. Differences were analyzed using chi-squared test, Fisher's Exact test, and unpaired Student t-test. Mean amount of warfarin before and after surgery was 4.0 mg, 4.1 mg in Group A and was 5.1 mg, 4.6 mg in Group B, respectively. Average duration of warfarin doing before ablation was 73.7 days in Group A, 129.9 days in B with no significant difference (p = 0.312). The duration time of warfarin on groups after ablation lasted several months. The number of checking INRs was 4.1 and 7.6, respectively. Inter-individual variability of INR fluctuations were $2.1{\pm}0.6$ in Group A and $2.2{\pm}0.7$ in B which were not significantly different (p = 0.062). 164 cases of decreased INR were: 'omission in taking medication, stressfulness and headache, 'increased intake of high vitamin K foods', 'lifestyle change of increased physical activities', and 'increase of food-intakes'. To the contrary, 36 cases of increased INR were: 'reduce of food-intake', 'use of non-prescription drugs', 'reduction in physical activities', and 'excessive restriction on food-intake', consecutively. In conclusion, the study validated therapeutic outcomes of RA patients who we treated with standard guideline and demonstrated 9 factors of INR fluctuations in the patient. A well-trained, pharmacist-monitored anticoagulation service could reduce the risk of adverse effects and prevent complications in patients with AF around RA operation.

• 생물정신의학
• /
• 제22권3호
• /
• pp.140-148
• /
• 2015

Objectives The aim of this study is to investigate the correlation between degenerative changes in brain [i.e., global cortical atrophy (GCA), medial temporal atrophy (MTA), white matter hyperintensities (WMH)] and neurocognitive dysfunction in Korean patients with Alzheimer's disease. Methods A total of 62 elderly subjects diagnosed with Alzheimer's disease were included in this study. The degenerative changes in brain MRI were rated with standardized visual rating scales (GCA or global cortical atrophy, MTA or medial temporal atrophy, and Fazekas scales) and the subjects were divided into two groups according to the degree of degeneration for each scale. Cognitive function was evaluated with Korean version of the Consortium to Establish a Registry for Alzheimer's Disease (CERAD-K) and several clinical features, including apolipoprotein E ${\varepsilon}4$ status, lipid profile and thyroid hormones, were also examined. Chi-square test and Fisher's exact test were performed to analyze the relationship between the degree of cerebral degeneration and neurocognitive functions. Results Demographic and clinical features, except for the age, did not show any significant difference between the two groups divided according to the degree of cerebral degenerative changes. However, higher degree of GCA was shown to be associated with poorer performance in verbal fluency test, word list recall test, and word list recognition test. Higher degree of MTA was shown to be associated with poorer performance in Mini-Mental State Examination in the Korean Version of CERAD Assessment Packet (MMSE-KC), word list recognition test and construction praxis recall test. Higher degree of white matter hyperintensities was shown to be associated with poorer performance in MMSE-KC. Conclusions Our results suggest that severe brain degeneration shown in MRI is associated with significantly poorer performance in neurocognitive tests in patients with Alzheimer's disease. Moreover, the degree of GCA, MTA and white matter hyperintensities, represented by scores from different visual rating scales, seems to affect certain neurocognitive domains each, which would provide useful information in clinical settings.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권18호
• /
• pp.8397-8403
• /
• 2016

Background: Breast cancer (BCa) is the most common malignancy in Mexican women. A set of histopathological markers has been established to guide BCa diagnosis, prognosis and treatment. Nevertheless, in only a few Mexican health services, such as that of the Secretariat of National Defense (SEDENA for its acronym in Spanish), are these markers commonly employed for assessing BCa. The aim of this study was to explore the association of Ki67, TP53, HER2/neu, estrogenic receptors (ERs) and progesterone receptors (PRs) with BCa risk factors. Materials and Methods: Clinical histories provided background patient information. Immunohistochemical (IHC) analysis was conducted on 48 tissue samples from women diagnosed with BCa and treated with radical mastectomy. The Chi square test or Fisher exact test together with the Pearson and Spearman correlation were applied. Results: On average, patients were $58{\pm}10.4$ years old. It was most common to find invasive ductal carcinoma (95.8%), histological grade 3 (45.8%), with a poor Nottingham Prognostic Index (NPI; 80.4%). ERs and PRs were associated with smoking and alcohol consumption, metastasis at diagnosis and Ki67 expression (p<0.05). PR+ was also related to urea and ER+ (p<0.05). Ki67 was associated with TP53 and elevated triglycerides (p<0.05), and HER2/neu with ER+, the number of pregnancies and tumor size (p<0.05). TP53 was also associated with a poor NPI (p<0.05) and CD34 with smoking (p<0.05). The triple negative status (ER-/PR-/HER2/neu-) was related to smoking, alcohol consumption, exposure to biomass, number of pregnancies, metastasis and a poor NPI (p<0.05). Moreover, the luminal B subty was associated with histological type (p=0.007), tumor size (p=0.03) and high cholesterol (p=0.02). Conclusions: Ki67, TP53, HER2/neu, ER and PR proved to be related to several clinical and pathological factors. Hence, it is crucial to determine this IHC profile in women at risk for BCa. Certain associations require further study to understand physiological/biochemical/molecular processes.

• Journal of Radiation Protection and Research
• /
• 제20권1호
• /
• pp.25-36
• /
• 1995

The purpose of this research is to develop stereotactic localization and radiation measurement system for the efficient and precise radiosurgery. The algorithm to obtain a 3-D stereotactic coordinates of the target has been developed using a Fisher CT or angio localization. The procedure of stereotactic localization was programmed with PC computer, and consists of three steps: (1) transferring patient images into PC; (2) marking the position of target and reference points of the localizer from the patient image; (3) computing the stereotactic 3-D coordinates of target associated with position information of localizer. Coordinate transformation was quickly done on a real time base. The difference of coordinates computed from between Angio and CT localization method was within 2 mm, which could be generally accepted for the reliability of the localization system developed. We measured dose distribution in small fields of NEC 6 MVX linear accelerator using various detector; ion chamber, film, diode. Specific quantities measured include output factor, percent depth dose (PDD), tissue maximum ratio (TMR), off-axis ratio (OAR). There was small variation of measured data according to the different kinds of detectors used. The overall trends of measured beam data were similar enough to rely on our measurement. The measurement was performed with the use of hand-made spherical water phantom and film for standard arc set-up. We obtained the dose distribution as we expected. In conclusion, PC-based 3-D stereotactic localization system was developed to determine the stereotactic coordinate of the target. A convenient technique for the small field measurement was demonstrated. Those methods will be much helpful for the stereotactic radiosurgery.