• Genomics & Informatics
• /
• v.19 no.3
• /
• pp.22.1-22.5
• /
• 2021

Automatic document classification for highly interrelated classes is a demanding task that becomes more challenging when there is little labeled data for training. Such is the case of the coronavirus disease 2019 (COVID-19) clinical repository-a repository of classified and translated academic articles related to COVID-19 and relevant to the clinical practice-where a 3-way classification scheme is being applied to COVID-19 literature. During the 7th Biomedical Linked Annotation Hackathon (BLAH7) hackathon, we performed experiments to explore the use of named-entity-recognition (NER) to improve the classification. We processed the literature with OntoGene's Biomedical Entity Recogniser (OGER) and used the resulting identified Named Entities (NE) and their links to major biological databases as extra input features for the classifier. We compared the results with a baseline model without the OGER extracted features. In these proof-of-concept experiments, we observed a clear gain on COVID-19 literature classification. In particular, NE's origin was useful to classify document types and NE's type for clinical specialties. Due to the limitations of the small dataset, we can only conclude that our results suggests that NER would benefit this classification task. In order to accurately estimate this benefit, further experiments with a larger dataset would be needed.

• Tuberculosis and Respiratory Diseases
• /
• v.77 no.4
• /
• pp.155-160
• /
• 2014

Chronic obstructive pulmonary disease (COPD) is characterized by a diverse array of pulmonary and nonpulmonary manifestations, but our understanding of COPD pathogenesis and the factors that influence its heterogeneity in disease presentation is poor. Despite this heterogeneity, treatment algorithms are primarily driven by a single measurement, forced expiratory volume in 1 second ($FEV_1$) as a percentage of its predicted value ($FEV_1%$). In 2011, a major shift in Global Initiative for Chronic Obstructive Lung Disease (GOLD) treatment recommendations was proposed that stratifies patients with COPD on the basis of symptoms and exacerbation history. This article reviews the work reported in 2013 that enlightens our understanding of COPD with respect to COPD classification systems, phenotype, biomarker, exacerbation, and management for patients with COPD.

• BMB Reports
• /
• v.40 no.2
• /
• pp.135-141
• /
• 2007

Conjugation of the methyl group at the fifth carbon of cytosines within the palindromic dinucleotide 5'-CpG-3' sequence (DNA methylation) is the best studied epigenetic mechanism, which acts together with other epigenetic entities: histone modification, chromatin remodeling and microRNAs to shape the chromatin structure of DNA according to its functional state. The cancer genome is frequently characterized by hypermethylation of specific genes concurrently with an overall decrease in the level of 5-methyl cytosine, the pathological implication of which to the cancerous state has been well established. While the latest genome-wide technologies have been applied to classify and interpret the epigenetic layer of gene regulation in the physiological and disease states, the epigenetic testing has also been seriously explored in clinical practice for early detection, refining tumor staging and predicting disease recurrence. This critique reviews the latest research findings on the use of DNA methylation in cancer diagnosis, prognosis and staging/classification.

• Journal of The Korean Radiological Technologist Association
• /
• v.28 no.1
• /
• pp.61-66
• /
• 2002

Purpose : This study presents a new classification of gastroesophageal reflux to evaluate the patients with Gastroesophageal reflux disease after barium contrast reflux exam to help making the correct diagnosis and Treatment according to the symptoms and

• 한국초전도학회:학술대회논문집
• /
• v.15
• /
• pp.53-53
• /
• 2005

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.21 no.3
• /
• pp.776-780
• /
• 2007

Recently World Health Organization Western Pacific Regional Office (WHO/WPRO) has developed the WHO International Standard Terminologies on Traditional Medicine in the Western Pacific Region (IST), and is developing WHO International Classification of Traditional Medicine/Western Pacific Regional Office (ICTM/WPRO). Regarding ICTM, WHO/WPRO hoped that it will be incorporated to International Classification of Disease (ICD) 11$^{th}$ edition, published in 2015. The author reports the proceedings of these two standardizations on terminologies and diseases of traditional medicine in East Asia.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.324-330
• /
• 2021

Agriculture is one of the essential needs of human life on planet Earth. It is the source of food and earnings for many individuals around the world. The economy of many countries is associated with the agriculture sector. Lots of diseases exist that attack various fruits and crops. Apple Tree Leaves also suffer different types of pathological conditions that affect their production. These pathological conditions include apple scab, cedar apple rust, or multiple diseases, etc. In this paper, an automatic detection framework based on deep learning is investigated for apple leaves disease classification. Different pre-trained models, VGG16, ResNetV2, InceptionV3, and MobileNetV2, are considered for transfer learning. A combination of parameters like learning rate, batch size, and optimizer is analyzed, and the best combination of ResNetV2 with Adam optimizer provided the best classification accuracy of 94%.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.223-229
• /
• 2021

Classification of different blood cell types is an essential task for human's medical treatment. The white blood cells have different types of cells. Counting total White Blood Cells (WBC) and differential of the WBC types are required by the physicians to diagnose the disease correctly. This paper used transfer learning methods to the pre-trained deep learning models to classify different WBCs. The best pre-trained model was Inception ResNetV2 with Adam optimizer that produced classification accuracy of 98.4% for the dataset comprising four types of WBCs.

• BMB Reports
• /
• v.40 no.5
• /
• pp.814-824
• /
• 2007

Liver cirrhosis (LC) is defined as comprising diffuse fibrosis and regenerating nodules of the liver. The biochemical and anatomical dysfunction in LC results from both reduced liver cell number and portal vascular derangement. Although several studies have investigated dysregulated genes in cirrhotic nodules, little is known about the genes implicated in the pathophysiologic change of LC or about their relationship with the degree of decompensation. Here, we applied cDNA microarray analysis using 38 HBsAg-positive LC specimens to identify the genes dysregulated in HBV-associated LC and to evaluate their relation to disease severity. Among 1063 known cancer- and apoptosis-related genes, we identified 104 genes that were significantly up- (44) or down- (60) regulated in LC. Interestingly, this subset of 104 genes was characteristically correlated with the degree of decompensation, called the Pugh-Child classification (20 Pugh-Child A, 10 Pugh-Child B, and 8 Pugh-Child C). Patient samples from Pugh-Child C exhibited a distinct pattern of gene expression relative to those of Pugh-Child A and B. Especially in Pugh-Child C, genes encoding hepatic proteins and metabolizing enzymes were significantly down-regulated, while genes encoding various molecules related to cell replication were up-regulated. Our results suggest that subsets of genes in liver cells correspond to the pathophysiologic change of LC according to disease severity and possibly to hepatocarcinogenesis.

• Journal of Chest Surgery
• /
• v.26 no.8
• /
• pp.627-632
• /
• 1993

A clinical study was performed on 64 cases of the esophageal diseases experienced at the Department of Thoracic & Cardiovascular Surgery of Kyungpook University Hospital from Jan. 1988 through Dec. 1992. The results were as follows: The most common esophageal disease was cancer which occurred in 37.5% of the total. In esophageal cancer patients, 24 cases were operated on and cancer resection was feasible in 19 cases with 2 cases of hospital death. The overall 1 year survival rate was 41.6% and the most favorable follow up result was revealed in stage I group. Esophageal stricture occurred in 22 cases and its causes were alkali and acid. The most common stricture site was mid-esphagus. Colon interposition was performed on 15 cases. Achalasia occured in 8 cases and was treated with modified Heller`s myotomy. Esophageal perforation occurred in 6 cases and its operative mortality rate was 16.6%. Two patients with congenital bronchoesophageal fistula were treated with surgical division. The first case, which occurred in an adult, is of Braimbridge,s typeII classification. The second one which occured in an child with sequestration, is of Braimbridge,s type IV classification. Diverticulectomy was performed in 1 case of esophageal diverticulum. Enucleation of tumor was performed in 1 case of esophageal leiomyoma.