• Asian Pacific Journal of Cancer Prevention
• /
• 제14권6호
• /
• pp.3819-3823
• /
• 2013

Background: Hepatocellular carcinoma (HCC) is a major cause of cancer mortality worldwide. The outcome of HCC depends mainly on its early diagnosis. To date, the performance of traditional biomarkers is unsatisfactory. Talins were firstly identified as cytoplasmic protein partners of integrins but Talin-1 appears to play a crucial role in cancer formation and progression. Our study was conducted to assess the diagnostic value of serum Talin-1 (TLN1) compared to the most feasible traditional biomarker alpha-fetoprotein (AFP) for the diagnosis of HCC. Methods: TLN1 was detected using enzyme linked immunosorbent assay (ELISA) in serum samples from 120 Egyptian subjects including 40 with HCC, 40 with liver cirrhosis (LC) and 40 healthy controls (HC). Results: ROC curve analysis was used to create a predictive model for TLN1 relative to AFP in HCC diagnosis. Serum levels of TLN1 in hepatocellular carcinoma patients were significantly higher compared to the other groups (p<0.0001). The diagnostic accuracy of TLN1 was higher than that of AFP regarding sensitivity, specificity, positive predictive value and negative predictive value in diagnosis of HCC. Conclusions: The present study showed for the first time that Talin-1 (TLN1) is a potential diagnostic marker for HCC, with a higher sensitivity and specificity compared to the traditional biomarker AFP.

• 치과방사선
• /
• 제29권1호
• /
• pp.149-159
• /
• 1999

Purpose: The purpose of this study was to evaluate cervical lymph node metastasis of oral squamous cell carcinoma patients by MRI film and neural network system. Materials and Methods: The oral squamous cell carcinoma patients(21 patients. 59 lymph nodes) who have visited SNU hospital and been taken by MRI. were included in this study. Neck dissection operations were done and all of the cervical lymph nodes were confirmed with biopsy. In MR images. each lymph node were evaluated by using 6 MR imaging criteria(size. roundness. heterogeneity. rim enhancement. central necrosis, grouping) respectively. Positive predictive value. negative predictive value. and accuracy of each MR imaging criteria were calculated. At neural network system. the layers of neural network system consisted of 10 input layer units. 10 hidden layer units and 1 output layer unit. 6 MR imaging criteria previously described and 4 MR imaging criteria (site I-node level II and submandibular area. site II-other node level. shape I-oval. shape II-bean) were included for input layer units. The training files were made of 39 lymph nodes(24 metastatic lymph nodes. 10 non-metastatic lymph nodes) and the testing files were made of other 20 lymph nodes(10 metastatic lymph nodes. 10 non-metastatic lymph nodes). The neural network system was trained with training files and the output level (metastatic index) of testing files were acquired. Diagnosis was decided according to 4 different standard metastatic index-68. 78. 88. 98 respectively and positive predictive values. negative predictive values and accuracy of each standard metastatic index were calculated. Results: In the diagnosis of using single MR imaging criteria. the rim enhancement criteria had highest positive predictive value (0.95) and the size criteria had highest negative predictive value (0.77). In the diagnosis of using single MR imaging criteria. the highest accurate criteria was heterogeneity (accuracy: 0.81) and the lowest one was central necrosis (accuracy: 0.59). In the diagnosis of using neural network systems. the highest accurate standard metastatic index was 78. and that time. the accuracy was 0.90. Neural network system was more accurate than any other single MR imaging criteria in evaluating cervical lymph node metastasis. Conclusion: Neural network system has been shown to be more useful than any other single MR imaging criteria. In future. Neural network system will be powerful aiding tool in evaluating cervical node metastasis.

• 한국압력기기공학회 논문집
• /
• 제19권1호
• /
• pp.6-10
• /
• 2023

Only about 10% of selected equipment in nuclear power plants are monitored by wiring to address failures or problems caused by vibration. The purpose is primarily for preventive maintenance, not for predictive maintenance. This paper shows that vibration monitoring and diagnosis using Industrial 4.0 enables the complete predictive maintenance for all vibrating equipments in nuclear power plants with the convergence of internet of things; wireless technology, big data through periodic collection and artificial intelligence. Predictive maintenance using wireless technology is possible in all areas of nuclear power plants and in all systems, but it should satisfy regulatory guides on electromagnetic interference and cyber security.

• 대한임상검사과학회지
• /
• 제39권3호
• /
• pp.271-276
• /
• 2007

Helicobacter pylori (H. pylori) infection is common in korea and high incidence at gastric ulcer and duodenal ulcer. $^{14}C-urea$ breath test ($^{14}C-UBT$) is regarded as a highly reliable and non-invasive method for the diagnosis of H. pylori infection. The purpose of this study was to evaluate the diagnositc performance of a new and rapid $^{14}C-UBT$, which was equipped with Geiger-Muller counter and compared the results with those obtained by gastroduodenoscopic biopsies (GBx). One hundred sixty-eight patients (M : F = 118 : 50) underwent $^{14}C-UBT$, rapid urease test (CLO test), and GBx. The results of $^{14}C-UBT$ were classified as positive (>50 cpm), borderline (25$^{14}C-UBT$ or CLO test results with GBx as a glod standard. In the assessment of the presence of H. pylori infection, the $^{14}C-UBT$ global performance yielded positive predictive value, negative predictive value and accuracy of 93.3% and 83.3%, respectively. However, the CLO test had performance yielded positive predictive value, negative predictive value and accuracy of 76.9%, 50.0%, respectively. In this study $^{14}C-UBT$ is a highly accurate, simple and non-invasive method or the diagnosis of follow up H. pylori infection.

• 대한두경부종양학회지
• /
• 제8권1호
• /
• pp.31-36
• /
• 1992

Neck mass is common neoplasms, but it poses a diagnostic dilemma for the physician. The differential diagnosis include neoplastic, inflammatory and developmental causes. The FNAC is one of the most valuable tests in the initial assessment and differential diagnosis of the neck mass. FNAC was performed with 267 cases of the neck mass, during the period from April, 1988 to October, 1990 at the department of General Surgery, Soon Chun Hyang. University Hospital. Thyroid lesions were excluded from this analysis. Final diagnosis was based on resection histology in 58 cases, and surgical specimens were compared with FNAC. The following results were obtoired ; 1) Of 267 cases, there we re 9 cases(3.4%) of congenital lesion, 74 cases(27.7%) of inflammatory lesion, 40 cases(15.0%) of benign tumor, 12 cases(4.5%) of primary malignant tumor, 37 cases(13.8%) of metastatic tumor, 75cases(28.1%) of reactive hyperplasia, 20 cases(7.5%) of unsatisfactory. In the pathologic classification, inflammatory lesion was the most common. 2) In the 58 cases of excisional biopsy, sensitivity 93.8%, specificity 95.2%, false positive 11.8%, false negative 2.4%, positive predictive value 88.2%, negative predictive value 97.6%, accuracy 94.8%. 3) The most common disease was the tuberculous lymphadenitis (53 cases, 19.8%). sensitivity 57.9%, specificity 100.0%, false positive 0.0%, false negative 17.0%, positive predictive value 100.0%, negative predictive value 83.0%, accuracy 86.2%.

• 산업경영시스템학회지
• /
• 제23권54호
• /
• pp.155-165
• /
• 2000

The fault diagnosis is a systematic and unified method to find based on the observing data resulting in noises. This paper presents the fault prediction and diagnosis using fuzzy expert system technique to manipulate the uncertainties efficiently in predictive perspective. We apply a fuzzy event tree analysis to the computer system, and build up the fault prediction and diagnosis using fuzzy expert system that predicts and diagnoses the error of the system in the advance of error.

• 한국컴퓨터정보학회논문지
• /
• 제16권3호
• /
• pp.141-147
• /
• 2011

본 논문은 유도전동기의 고장검출 및 진단을 위한 효율적인 2-단계 고장예측 알고리즘을 제안한다. 첫 번째 단계에서는 고장 패턴 추출을 위해 선형 예측 부호화 (Linear Predictive Coding: LPC) 기법을 사용하고, 두 번째 단계에서는 고장 패턴 매칭을 위해 동적시간교정법 (Dynamic Time Warping: DTW)을 사용한다. 유도전동기에서 정상 및 각종 이상 상태의 조건을 발생시켜 추출한 샘플링 주파수 8kHz, 샘플링 시간 2.2초의 정상상태 및 비정상 상태의 진동데이터 8개를 사용하여 모의 실험한 결과, 제안한 고장예측 알고리즘은 기존의 고장진단 알고리즘보다 약 45%의 정확도 향상을 보였다. 또한 TI사의 TMS320F2812 DSP를 내장한 테스트베드 시스템을 제작하여 제안한 고장예측 알고리즘을 구현하고 검증하였다.

• Archives of Plastic Surgery
• /
• 제37권4호
• /
• pp.346-350
• /
• 2010

Purpose: Diagnosis of diabetic foot infection is sometimes difficult, since the classical inflammatory signs and leukocytosis may be absent due to the decreased host immune response in diabetics. Therefore inflammatory blood markers, such as white blood cell (WBC) count, erythrocyte sedimentation rate (ESR), and C-reactive protein (CRP) have been commonly needed to confirm the diagnosis of infection. The purpose of this study is to evaluate the diagnostic usefulness of WBC, ESR and CRP for detection of diabetic foot infection. Methods: Peripheral blood samples were taken from 113 patients with diabetic foot ulcers admitted from June 2007 to April 2009. Diabetic foot infection was diagnosed according to the microbiological culture from soft tissue and bone specimens. Reference values of tests were 4500-11000 /${\mu}L$ for WBC count, 0-20 mm/hr for ESR, and 0-5 mg/L for $CRP^{13,14}$. Sensitivities, specificities, positive and negative predictive values of laboratory tests were calculated and analysed. Receiver-operator characteristic (ROC) curve was also created. Results: There was a significant difference in WBC, ESR, and CRP between infectious group and noninfectious group (p<0.05). The sensitivity of WBC>11,000 /${\mu}L$ ESR > 20 mm/hr, and CRP > 5 mg/L was 30%, 96%, and 84%. The specificity was 86%, 14%, and 50% for WBC, ESR, and CRP, respectively. Positive predictive value was 88%, 78%, and 84%, and negative predictive value was 28%, 50%, and 50% respectively. The areas under the ROC curve for WBC, ESR and CRP were 0.72, 0.75, and 0.78 respectively. Conclusion: Based on the results of this study, we conclude that CRP is more useful method in predicting and diagnosing infection than WBC, ESR in diabetic foot ulcer patients.

• 대한세포병리학회지
• /
• 제11권1호
• /
• pp.11-18
• /
• 2000

Pancreaticobiliary tract strictures are frequent Indications for endoscopic retrograde cholangiopancreatography(ERCP). We have investigated the brushing cytology in order to determine its efficacy for diagnosis of pancreaticobiliary malisnancies. Brushing cytology during ERCP was evaluated in 56 patients with biliary tract stricture presenting to the Catholic Hospital of Taegu-Hyosung from April 1997 to August 1999. A comparison was made between the cytologic and histologic diagnoses on 32 cases from 30 patients. A diagnosis of malignancy was establishied in 78.1%, benign in 15.6%, and inadequate in 6.3% of the cases. Statistical data on cytologic diagnoses in strictures of the bile duct were as follows; specificity and sensitivity of blushing procedure was 100% & 83.3%, respectively: sensitivity of interpretation was 89.3%: with no false positive cases and 3 false negative cases: predictive value for malignancy was 100% & 100%, respectively: predictive value for benign was 28.6% & 40%,, respectively: overall diagnostic efficiency was 84.4%. It is concluded that brush cytology is a diagnostically reliable, highly specific technique for malignant lesions encounted at ERCP, although a negative result does not rule out the diagnosis of malignancy.

• Journal of Medicine and Life Science
• /
• 제20권4호
• /
• pp.141-157
• /
• 2023

Stroke is a leading cause of disability and death. The condition requires prompt diagnosis and treatment. The quality of care provided to patients with stroke can vary depending on the availability of medical resources, which in turn, can affect prognosis. Recently, there has been growing interest in using machine learning (ML) to support stroke diagnosis and treatment decisions based on large medical data sets. Current ML applications in stroke care can be divided into two categories: analysis of neuroimaging data and clinical information-based predictive models. Using ML to analyze neuroimaging data can increase the efficiency and accuracy of diagnoses. Commercial software that uses ML algorithms is already being used in the medical field. Additionally, the accuracy of predictive ML models is improving with the integration of radiomics and clinical data. is expected to be important for improving the quality of care for patients with stroke.