• 대한핵의학회지
• /
• 제31권1호
• /
• pp.50-56
• /
• 1997

관상 동맥 질환에서 심근 혈류의 평가를 위하여 사용되는 심근 관류 SPECT는 여성에서의 유방이나 횡격막 감쇠 등 인공 산물에 의하여 위양성으로 나타날 수 있다. 이 연구에서는 게이트 SPECT를 이용하여 관류 SPECT에 나타나는 의심스러운 관류 감소 부위의 벽 운동을 평가하여 관류 감소 부위가 인공 산물인지 판정하였다. 판정 결과는 관상 동맥 조영술 결과와 비교하였다. 대상 환자 275명에서 관류 SPECT의 예민도와 특이도는 각각 87%와 55%였고 게이트 SPECT를 진단에 이용하였을 때 관류 SPECT에서 위양성을 보인 5례의 벽운동이 정상임이 확인되어 특이도가 66%로 향상되었다. 이상의 결과로 게이트 SPECT는 관상 동맥 질환의 특이도를 높이는 데 이용될 수 있을 것으로 생각한다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권16호
• /
• pp.6881-6885
• /
• 2014

Background: The present study aimed to investigate the utility and importance of the various parameters of complete blood count panel for benign-malignant differentiation of adnexal masses. Materials and Methods: This retrospective study involved 316 patients with documented benign and 253 patients with malignant adnexal masses who underwent primary surgical treatment at a tertiary referral center. Prior to the study, all benign and malignant cases were compared within their own groups and then the benign and malignant cases were compared to each other. For all cases, cut-off, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were calculated for the neutrophil lymphocyte ratio (NLR), platelet lymphocyte ratio (PLR), neutrophil, lymphocyte, platelet and CA-125 parameters, and the results were compared in regards to the groups. Results: NLR, PLR, neutrophil, CA-125, and platelet values were higher in the malignant compared to the benign cases (p<0.01). The lymphocyte value was lower in the malignant cases (p<0.01). No significant differences were found for basophils and eosinophils (p > 0.05). For CA-125, the sensitivity, specificity, PPV and NPV for all cases were 78%, 62%, 62% and 78%, respectively. For NLR, they were 65.6%, 72.1%, 65.3%, and 72.3%, and for PLR, 48%, 81%, 67%, and 66%. Additionally, the sensitivity and specificity were 55% and 77% for CA-125, 66% and 58% for NLR, and 61% and 58% for PLR in early malignant cases. Conclusions: NLR and PLR appear to be useful methods that can be applied together with CA-125 due to the relatively high sensitivity values for the malign-benign differentiation of ovarian masses. Although the specificity of these parameters is lower than CA-125, especially in cases with early malignant ovarian pathology, their sensitivity being higher is promising for the early diagnosis of ovarian cancer. It can be used to detect ovarian malignancies in the early stages, and it will increase the treatment options and improve survival rates.

• 지능정보연구
• /
• 제19권2호
• /
• pp.125-140
• /
• 2013

어떤 클래스에 속한 레코드의 개수가 다른 클래스들에 속한 레코드의 개수보다 매우 많은 경우에, 이 데이터 집합을 '불균형 데이터 집합'이라고 한다. 데이터 분류에 사용되는 많은 기법들은 이러한 불균형 데이터에 대해서 저조한 성능을 보인다. 어떤 기법의 성능을 평가할 때에 적중률뿐만 아니라, 민감도와 특이도도 함께 측정하여야 한다. 고객의 이탈을 예측하는 문제에서 '유지' 레코드가 다수 클래스를 차지하고, '이탈' 레코드는 소수 클래스를 차지한다. 민감도는 실제로 '유지'인 레코드를 '유지'로 예측하는 비율이고, 특이도는 실제로 '이탈'인 레코드를 '이탈'로 예측하는 비율이다. 많은 데이터 마이닝 기법들이 불균형 데이터에 대해서 저조한 성능을 보이는 것은 바로 소수 클래스의 적중률인 특이도가 낮기 때문이다. 불균형 데이터 집합에 대처하는 과거 연구 중에는 소수 클래스를 Oversampling하여 균형 데이터 집합을 생성한 후에 데이터 마이닝 기법을 적용한 연구들이 있다. 이렇게 균형 데이터 집합을 생성하여 예측을 수행하면, 특이도는 다소 향상시킬 수 있으나 그 대신 민감도가 하락하게 된다. 본 연구에서는 민감도는 유지하면서 특이도를 향상시키는 모델을 개발하였다. 개발된 모델은 Support Vector Machine (SVM), 인공신경망(ANN) 그리고 의사결정나무 기법 등으로 구성된 하이브리드 모델로서, Hybrid SVM Model이라고 명명하였다. 구축과정 및 예측과정은 다음과 같다. 원래의 불균형 데이터 집합으로 SVM_I Model과 ANN_I Model을 구축한다. 불균형 데이터 집합으로부터 Oversampling을 하여 균형 데이터 집합을 생성하고, 이것으로 SVM_B Model을 구축한다. SVM_I Model은 민감도에서 우수하고, SVM_B Model은 특이도에서 우수하다. 입력 레코드에 대해서 SVM_I와 SVM_B가 동일한 예측치를 도출하면 그것을 최종 해로 결정한다. SVM_I와 SVM_B가 상이한 예측치를 도출한 레코드에 대해서는 ANN과 의사결정나무의 도움으로 판별 과정을 거쳐서 최종 해를 결정한다. 상이한 예측치를 도출한 레코드에 대해서는, ANN_I의 출력값을 입력속성으로, 실제 이탈 여부를 목표 속성으로 설정하여 의사결정나무 모델을 구축한다. 그 결과 다음과 같은 2개의 판별규칙을 얻었다. 'IF ANN_I output value < 0.285, THEN Final Solution = Retention' 그리고 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn'이다. 제시되어 있는 규칙의 Threshold 값인 0.285는 본 연구에서 사용한 데이터에 최적화되어 도출된 값이다. 본 연구에서 제시하는 것은 Hybrid SVM Model의 구조이지 특정한 Threshold 값이 아니기 때문에 이 Threshold 값은 대상 데이터에 따라서 얼마든지 변할 수 있다. Hybrid SVM Model의 성능을 UCI Machine Learning Repository에서 제공하는 Churn 데이터 집합을 사용하여 평가하였다. Hybrid SVM Model의 적중률은 91.08%로서 SVM_I Model이나 SVM_B Model의 적중률보다 높았다. Hybrid SVM Model의 민감도는 95.02%이었고, 특이도는 69.24%이었다. SVM_I Model의 민감도는 94.65%이었고, SVM_B Model의 특이도는 67.00%이었다. 그러므로 본 연구에서 개발한 Hybrid SVM Model이 SVM_I Model의 민감도 수준은 유지하면서 SVM_B Model의 특이도보다는 향상된 성능을 보였다.

• Tuberculosis and Respiratory Diseases
• /
• 제47권6호
• /
• pp.757-767
• /
• 1999

Background: Diagnosis by smear and/or cultures of the Mycobacterium tuberculosis from body fluid or biopsy specimen is "Gold standard". However the sensitivity of the direct microscopy is relatively low and culture of mycobacteria is time consuming. Despite an explosion in the techniques of rapid identification of mycobacteria by molecular genetic means, it is laborious and expensive and then rapid, inexpensive serodiagnosis is interested in diagnosis of tuberculosis. But sensitivity and specificity of known serologic antigen is not full sufficient level and then new antigen develop and combination cocktails of new developed antigens by ELISA are needed. Method: To compare the efficacy of different mycobacterial specific antigen and to assess the applicability of the combination of several different antigens in the diagnosis of tuberculosis, five ELISA tests derived 14KDa, 16KDa, 19KDa, 23KDa, 38KDa were evaluated in 57 active pulmonary patient and 24 inactive post-therapy follow up patient and 48 normal control. Results: The optical densities of ELISA test with 14KDa, 16KDa, 19KDa, 23KDa, 38KDa were significantly higher in active tuberculosis cases than in normal control(P<0.001, P<0.001, P<0.027, P<0.001, P<0.001) and those with 16KDa, 38KDa were significant higher in active tuberculosis cases than in inactive post-therapy follow up cases(P<0.01. P<0.001) and those of 14KDa, 16KDa, 23KDa, 38KDa were significant higher in inactive post-therapy follow up cases than in normal control(P<0.008. P<0.01. P<0.006. P<0.001). The sensitivity of 14KDa, 16KDa, 19KDa, 23KDa, 38KDa in active pulmonary patient cases was 42.1%, 43.9%, 15.8%, 28.0%, 70.2%, respectively and the specificity of 14KDa, 16KDa, 19KDa, 23KDa, 38KDa in active pulmonary patient cases was 95.8%, 95.8%, 91.7%, 89.6%, 93.8%, respectively. The sensitivity and specificity of combination 38KDa with 16KDa was 87% and 93.7%. Conclusion: The sensitivity and specificity of new antigens for serodiagnosis of the tuberculosis still remains limited at around 70%, which makes its a poor diagnostic tool for disease confirmation. A combination of cocktail antigens provided by cut-off value adjustment for serodiagnosis of tuberculosis some improved diagnostic yield than single antigen serologic test.

• Asian Pacific Journal of Cancer Prevention
• /
• 제13권8호
• /
• pp.3611-3615
• /
• 2012

Objective: The objective of this study was to establish the diagnostic accuracy, specificity and sensitivity of fine needle aspiration cytology(FNAC) for intra-oral tumors, comparing with histopathology as the gold standard. Materials and methods: Forty cases of FNA cytology from intraoral tumors was performed in AFID along with the demographic data and clinical information and then diagnosed at AFIP, Rawalpindi. Then the cytology results obtained per FNAC were compared with the histopathological biopsy results of the same lesions. The following variables were recorded for each patient: Age, gender, site of biopsy, diagnosis. The data were entered and analyzed using Open-epi version 2.0. Diagnostic accuracy, sensitivity, specificity, positive predictive value and negative predictive value were calculated. Cohen Kappa was further applied to compare the agreement between the biopsy and FNAC diagnoses. A p-value of < 0.05 was considered as statistically significant. Results: Among the total patients included in the study there were 24 males and 16 females, with a ratio of 1.5:1. Age of the patients ranged from 24 to 80 years with a mean of 52 years. A total of six sites were aspirated from the oral cavity with maximum (11) aspirates taken from alveolar ridge. The results of FNAC revealed that there were 32 malignant and 8 benign aspirates. Confirmation through histopathological analysis came for 31/32 malignant cases while one was falsely given positive for malignancy on FNAC. Among a total of 40 cases, 31(77%) cases diagnosed were found to be malignant and remaining 9(23%) were benign. The FNAC results revealed 32 malignant and 8 benign lesions. Histopathology of the subsequent surgically excised specimen showed malignant lesions in 31(77%) and benign in 9(23%) patients. As a whole, it was found that the absolute sensitivity for introral FNAC was 100% and specificity 89% with positive predictive value of 97% and negative predictive value of 100%. Conclusion: Cytological diagnosis was almost corroborative with final histopathological diagnosis in all cases, with very few exceptions, exhibiting high diagnostic accuracy.

• 대한정형도수물리치료학회지
• /
• 제16권1호
• /
• pp.64-76
• /
• 2010

The sacroiliac joint is difficult to appropriately examine and treat because it is extremely complex and also is difficult to distinguish dysfunctions from those of the spine and hip which are highly intergrated functionally. In addition generally traditional x-rays and CT scans also are not beneficial in detecting sacroiliac joint dysfunction. The manipulative physiotherapist should seek to establish a series of relevant finding that build into a case implicating the sacroiliac joint. When deciding to use these diagnostic tests, the examiner must determine if the test will give reliable and useful information that will help in the diagnosis and subsequent treatment. To be useful diagnostic tests must give reliable data and be valid and the most useful methods of determining whether a test is a good test for pathology under consideration are sensitivity and specificity. In the ideal world, one would want a test that has both high sensitivity and high specificity. The purpose of this review is to ascertain diagnostic value on the tests for sacroiliac joint dysfunction by literature.

• 한국임상수의학회지
• /
• 제18권4호
• /
• pp.329-333
• /
• 2001

새로 개발되거나 혹은 기존의 어떤 진단검사를 다양한 임상상황에 적용하기 위해서는 먼저 이들 검사법의 진단적 정확도를 추정하는 연구가 반드시 선행되어야 한다. 진단의 정확도에 대한 추정치를 모른다면 검사결과를 해석하는 것이 불가능하기 때문이다. 특히 동일한 개체에서 감염부위별로 3개 이상의 시료를 얻어 진단검사를 적용하는 경우 각 시료의 검사결과는 독립적인 측정시료가 아니라 개체내에서 연관성이 매우 높은 종속적인 시료에 해당 한다. 즉 동일한 개체에서 얻은 시료일수록 검사결과에서 유사한 반응을 보이며 이 경우 분석의 단위는 각각의 개체가 아니라 검사부위가 되는데 이는 의학연구에서 매우 흔하다. 본 연구에서는 Helicobacter 균에 의한 감염을 검출하기 위하여 동일한 개로부터 위의 해부학적 구조상 pyloric antrum, body 및 cardia의 생검시료에 대하여 urease 검사와 PCR 검사를 적용하여 각 검사의 진단적 정확도를 추정하였다. urease 검사의 민감도와 특이도는 0.74 (95% 신뢰구간: 0.64-0.84)와 0.87 (95% 신뢰구간: 0.67-1.00)이었으며 PCR 검사의 민감도와 특이도는 0.95 (95% 신뢰구간: 0.89-1.00)와 0.90 (95% 신뢰구간: 0.70-1.00)로 두 검사의 특이도는 높은 것으로 나타났다. 그러나 PCR 검사에 비하여 urease 검사의 경우 가음성 (false negative)의 가능성이 높기 때문에 진단결과에 대한 신중한 해석이 요구된다.

• Imaging Science in Dentistry
• /
• 제38권4호
• /
• pp.215-218
• /
• 2008

Purpose : To evaluate the value of panoramic radiography in diagnosing maxillary sinus inflammation. Materials and Methods : A total of 214 maxillary sinuses from 114 panoramic radiographs were assessed in this study. Two independent experienced oral radiologists evaluated the images in random order for sinus inflammation. Using Cone beam CT images as the gold standard, the sensitivity and specificity of panoramic radiography were calculated, and inter- and intraobserver agreement for panoramic interpretation were obtained. Results : The mean sensitivity and specificity of panoramic radiography were 81.0% and 85.6%, respectively. The weighted kappas for inter- and intraobserver agreement of panoramic radiography were 0.56 and 0.60, respectively. Conclusion : Panoramic radiography is a reasonably accurate method for diagnosing maxillary sinus inflammation and can be used for screening. However, additional examinations should be considered in patients with potentially significant pathology. (Korean J Oral Maxillofac Radiol 2008; 38: 215-8)

• 한국컴퓨터정보학회논문지
• /
• 제21권5호
• /
• pp.167-175
• /
• 2016

The volatile component analysis of 82 commercialized liquors(44 samples of single malt whisky, 20 samples of blended whisky and 18 samples of brandy) was carried out by gas chromatography after liquid-liquid extraction with dichloromethane. Pattern recognition techniques such as principle component analysis(PCA), cluster analysis(CA), linear discriminant analysis(LDA) and partial least square discriminant analysis(PLSDA) were applied for the discrimination of different liquor categories. Classification rules were validated by considering sensitivity and specificity of each class. Both techniques, LDA and PLSDA, gave 100% sensitivity and specificity for all of the categories. These results suggested that the common characteristics and identities as typification of whiskies and brandys was founded by using multivariate data analysis method.

• Journal of Chest Surgery
• /
• 제29권1호
• /
• pp.52-58
• /
• 1996

Sixty six patients who were operated as lung cancer during the period from Mar. 1991 to Sep. 1993 at the department of Thoracic and cardiovascular surgery, were reviewed retrospectively and the accuracy of regional lymph node in preoperative CT were compared with histopathologlc report obtained from operation. The age ranged from 30 to 72 years old (mean age : 56.5), and 51 patients were male and 15 patients were female. The author analysed the true positive, true negative, false positive and false negative and sensitivity, specificity, positive predictive index, negative predictive index and accuracy of each nodes. The result is that there were differences between seven nodal groups in specificity, sensitivity, positive predictive Index, negative predictive index and accuracy. The range of each nodal group is from 81.7 to 98.3% The nodes of the most poor accuracy are aortopulmonary area and hilar area.