• Journal of Chest Surgery
• /
• 제27권9호
• /
• pp.785-792
• /
• 1994

In this study, the authors analyzed the prognostic value of four clinical variables[age and sex of patients, association with myasthenia gravis and clinical stage] and histological type in 30 consecutive patients with thymoma, histologically classified as cortical[10],medullary[5] and mixed[15]type according to Marino and Muller-Hermelink classification. There were significant differences between the histological types in the frequency of the different tumor stages and myasthenia gravis and prognosis.Most of the cortical thymomas were at stage III and all of the medullary and most of the mixed tumors at stage I or II.Myasthenia gravis occurred more commonly in patients with cortical[30%] and mixed thymoma[60%] than in patients with medullary thymoma[10%]. Follow-up was conducted in 30 patients,with follow-up range from 3 months to 120 months[mean,47.3months]. 5 year actuarial survival was 100% for medullary thymoma, 73% for mixed thymoma, and 47% for cortical thymoma.The overall survival curve shows that 87.6% of the patients are alive at 2 years and 72.8% at 5 years. And 7 patients was dead during follow-up periods.By Kaplan-Meier technique, we found that the patients who had myasthenia gravis had better prognosis[P<0.05]. Medullary thymoma is a comparatively rare, benign tumor, and usually not associated with myasthenia gravis. Cortical thymoma must be regarded as malignant. Mixed thymoma is intermediate in its behavior between medullary and cortical thymoma. But these tumors should be considered potentially malignant despite of presence as stage I of II disease. Also, the patients with stageI,II had good prognosis and the patients with total resection had good prognosis[P<0.05].

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1899-1909
• /
• 2015

Glaucoma is one of the most common causes of blindness which is caused by increase of fluid pressure in the eye which damages the optic nerve and eventually causing vision loss. An automated technique to diagnose glaucoma disease can reduce the physicians’ effort in screening of Glaucoma in a person through the fundal retinal images. In this paper, optimal hyper analytic wavelet transform for Glaucoma detection technique from fundal retinal images is proposed. The optimal coefficients for transformation process are found out using the hybrid GSO-Cuckoo search algorithm. This technique consists of pre-processing module, optimal transformation module, feature extraction module and classification module. The implementation is carried out with MATLAB and the evaluation metrics employed are accuracy, sensitivity and specificity. Comparative analysis is carried out by comparing the hybrid GSO with the conventional GSO. The results reported in our paper show that the proposed technique has performed well and has achieved good evaluation metric values. Two 10- fold cross validated test runs are performed, yielding an average fitness of 91.13% and 96.2% accuracy with CGD-BPN (Conjugate Gradient Descent- Back Propagation Network) and Support Vector Machines (SVM) respectively. The techniques also gives high sensitivity and specificity values. The attained high evaluation metric values show the efficiency of detecting Glaucoma by the proposed technique.

• Journal of Korean Neurosurgical Society
• /
• 제37권4호
• /
• pp.263-267
• /
• 2005

Objective: Middle cerebral artery(MCA) anomalies are found incidentally on conventional cerebral angiography and magnetic resonance angiography(MRA). Our goal is to examine the incidence and types of MCA anomalies. Methods: Cerebral angiography was performed in 448 patients and MRA in 743; the patients had or were suspected to have cerebrovascular disease. The images were retrospectively evaluated for arterial anatomic anomalies. We use Teal's classification for definition of accessory and duplicated MCAs. Results: On cerebral angiography, the following anomalies of the MCA were found in seven patients: fenestration (n = 2, incidence = 0.45%); duplication (n = 2, incidence = 0.45%); accessory MCA (n = 2, incidence = 0.45%); aplasia (n = 1, incidence = 0.22%). On MRA, eight patients had anomalous MCAs : fenestration (n = 1, incidence = 0.14%); duplication (n= 6, incidence = 0.81%); accessory (n = 1, incidence = 0.14%). Conclusion: Although the clinical significance is not great, we find a relatively high incidence of anomalous MCAs. Knowledge and recognition of these MCA anomalies are useful and important in the interpretation of cerebral images and during neurosurgical procedures.

• 동의생리병리학회지
• /
• 제22권3호
• /
• pp.535-539
• /
• 2008

Pulse diagnosis is one of the typical examination methods in traditional oriental medicine. Pulse type classification is a major element of this diagnosis. There are more than 20 pulse types which have each clinical significance. However, pulse type's indications are implicative and obscure. In this study, we reviewed string pulse which is often diagnosed in Traditional Korean Medicine by analysis of Traditional Oriental Medical Literatures and modern medical papers. String pulse is taut and stiff pulse with high tension and low softness. It appears in 'blood vessel endothelial dysfunction', 'autonomic imbalance', 'arteriosclerosis'. Persistent string pulse can bring about cardiovascular or central nervous disease.

• 보건의료산업학회지
• /
• 제14권1호
• /
• pp.93-102
• /
• 2020

Objectives: This study analyzed the prescription characteristics of medication for acute respiratory diseases before and after pay-for-performance to provide basic data on effective medical quality management policies. Methods: The research data were collected from the 2013-2014 sample cohort of the National Health Insurance Corporation, from Internal Medicine, Pediatrics, Otorhinolaryngology, Family Medicine and General practitioner clinics (classification of disease codes: J00-J06, J20-J22, J40 outpatients). Results: The antibiotics prescription rates decreased from 43.9% in 2013 to 43.5% in 2014 when the major diagnosis was for upper respiratory infections and increased from 62.0% in 2013 to 62.5% in 2014 when the major diagnosis was for lower respiratory infections. Conclusions: There is a need to identify the correct antibiotic prescription method by expanding the current assessment standards. Such standards must include acute lower respiratory infections and minor diagnoses as the current evaluation techniques focus only on the major diagnosis of acute upper respiratory infections.

• Journal of Information Science Theory and Practice
• /
• 제3권1호
• /
• pp.6-23
• /
• 2015

This study develops an effective method for sentiment analysis of user-generated content on drug review websites, which has not been investigated extensively compared to other general domains, such as product reviews. A clause-level sentiment analysis algorithm is developed since each sentence can contain multiple clauses discussing multiple aspects of a drug. The method adopts a pure linguistic approach of computing the sentiment orientation (positive, negative, or neutral) of a clause from the prior sentiment scores assigned to words, taking into consideration the grammatical relations and semantic annotation (such as disorder terms) of words in the clause. Experiment results with 2,700 clauses show the effectiveness of the proposed approach, and it performed significantly better than the baseline approaches using a machine learning approach. Various challenging issues were identified and discussed through error analysis. The application of the proposed sentiment analysis approach will be useful not only for patients, but also for drug makers and clinicians to obtain valuable summaries of public opinion. Since sentiment analysis is domain specific, domain knowledge in drug reviews is incorporated into the sentiment analysis algorithm to provide more accurate analysis. In particular, MetaMap is used to map various health and medical terms (such as disease and drug names) to semantic types in the Unified Medical Language System (UMLS) Semantic Network.

• 대한임상검사과학회지
• /
• 제46권2호
• /
• pp.59-63
• /
• 2014

The death toll of Colorectal Carcinoma in Korea was 1,826 and 7,721 in the years 1992 and 2011, respectively. This rate of increase was shown to be more than 4.23 times higher than that of any other form of cancer. Therefore, Colorectal Carcinoma requires various diagnostic methods, and Microsatellite Instability (MSI) was applied as a new diagnostic tool. From this study with several microsatellite markers, only marker #13 was detected and observed D13S160 13% (4/30), D13S292 13% (4/30), D13S153 10% (3/30) in order. From the results of amplication with microsatellite marker, D13S292 37% (11/30), D13S153 33% (10/30), D13S160 33% (10/30) in order were shown. The appearance of a genetic mutation, which depends on the loci of Colorectal Carcinoma, was shown amplication from rectal cancer (3.77) which was higher than that of right Colorectal Carcinoma (2.08) (p<0.018). The genetic mutation with lymph node (4.13) appeared higher than normal (1.93) (p<0.001). There were no great differences in the genetic mutation dependent on disease, histological classification and increased group of serum CEA. Accordingly, it is suggested that the correct primers, which can evaluate MSI well from colorectal carcinoma, should be chosen and that MSI be considered a good prognosis and quality control tool.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.849-859
• /
• 2021

Prostate cancer (PCa) is a fatal disease that occurs in men. In general, PCa cells are found in the prostate gland. Early diagnosis is the key to prevent the spreading of cancers to other parts of the body. In this case, deep learning-based systems can detect and distinguish histological patterns in microscopy images. The histological grades used for the analysis were benign, grade 3, grade 4, and grade 5. In this study, we attempt to use transfer learning and fine-tuning methods as well as different model architectures to develop and compare the models. We implemented MobileNet, ResNet50, and DenseNet121 models and used three different strategies of freezing layers techniques of fine-tuning, to get various pre-trained weights to improve accuracy. Finally, transfer learning using MobileNet with the half-layer frozen showed the best results among the nine models, and 90% accuracy was obtained on the test data set.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• 제24권6호
• /
• pp.528-534
• /
• 2021

Purpose: Living-donor liver transplant emerged as an alternative treatment for end stage liver disease due to the lack of cadaveric organs availability that met the demand. In Portugal, pediatric living-donor liver transplant (P-LDLT) was initiated in 2001 in Portugal in order to compensate for the scarcity of cadaveric organs for such cases. The aim of this study was to retrospectively analyze the morbi-mortality of the 28 donors included in P-LDLT program performed at Coimbra's Pediatric Hospital (CHUC), a Portuguese reference center. Methods: We retrospectively collected pertinent donor data and stratified complications according to Clavien's scoring system. Results: In total, 28.6% (n=8) of the donors had surgical complications. According to Clavien-Dindo's classification, two donors had major complications (Clavien grade ≥3), four donors had grade 2 complications, and two donors had grade 1 complications. There were no P-LDLT-related mortalities in the present case series. The most common verified complications were biliary tract injuries and superficial incisional infections, which are consistent with the complications reported in worldwide series. Conclusion: These patients from CHUC shows that donor hepatectomy in P-LDLT is a safe procedure, with low morbidity and without mortality.

• International Journal of Contents
• /
• 제18권2호
• /
• pp.68-80
• /
• 2022

The health of the human heart is commonly measured using ECG (Electrocardiography) signals. To identify any anomaly in the human heart, the time-sequence of ECG signals is examined manually by a cardiologist or cardiac electrophysiologist. Lightweight anomaly detection on ECG signals in an embedded system is expected to be popular in the near future, because of the increasing number of heart disease symptoms. Some previous research uses deep learning networks such as LSTM and BiLSTM to detect anomaly signals without any handcrafted feature. Unfortunately, lightweight LSTMs show low precision and heavy LSTMs require heavy computing powers and volumes of labeled dataset for symptom classification. This paper proposes an ECG anomaly detection system based on two level BiLSTM for acceptable precision with lightweight networks, which is lightweight and usable at home. Also, this paper presents a new threshold technique which considers statistics of the current ECG pattern. This paper's proposed model with BiLSTM detects ECG signal anomaly in 0.467 ~ 1.0 F₁ score, compared to 0.426 ~ 0.978 F₁ score of the similar model with LSTM except one highly noisy dataset.