A machine learning based framework for IoT devices identification using web traffic

Identification of the Internet of Things (IoT) devices has become an essential part of network management to secure the privacy of smart homes and offices. With its wide adoption in the current era, IoT has facilitated the modern age in many ways. However, such proliferation also has associated privacy and data security risks. In the case of smart homes and smart offices, unknown IoT devices increase vulnerabilities and chances of data theft. It is essential to identify the connected devices for secure communication. It is very difficult to maintain the list of rules when the number of connected devices increases and human involvement is necessary to check whether any intruder device has approached the network. Therefore, it is required to automate device identification using machine learning methods. In this article, we propose an accuracy boosting model (ABM) using machine learning models of random forest and extreme gradient boosting. Featuring engineering techniques are employed along with cross-validation to accurately identify IoT devices such as lights, smoke detectors, thermostat, motion sensors, baby monitors, socket, TV, security cameras, and watches. The proposed ensemble model utilizes random forest (RF) and extreme gradient boosting (XGB) as base learners with adaptive boosting. The proposed ensemble model is tested with extensive experiments involving the IoT Device Identification dataset from a public repository. Experimental results indicate a higher accuracy of 91%, precision of 93%, recall of 93%, and F1 score of 93%.

Breast Cancer Detection and Prevention Using Machine Learning

Breast cancer is a common cause of female mortality in developing countries. Early detection and treatment are crucial for successful outcomes. Breast cancer develops from breast cells and is considered a leading cause of death in women. This disease is classified into two subtypes: invasive ductal carcinoma (IDC) and ductal carcinoma in situ (DCIS). The advancements in artificial intelligence (AI) and machine learning (ML) techniques have made it possible to develop more accurate and reliable models for diagnosing and treating this disease. From the literature, it is evident that the incorporation of MRI and convolutional neural networks (CNNs) is helpful in breast cancer detection and prevention. In addition, the detection strategies have shown promise in identifying cancerous cells. The CNN Improvements for Breast Cancer Classification (CNNI-BCC) model helps doctors spot breast cancer using a trained deep learning neural network system to categorize breast cancer subtypes. However, they require significant computing power for imaging methods and preprocessing. Therefore, in this research, we proposed an efficient deep learning model that is capable of recognizing breast cancer in computerized mammograms of varying densities. Our research relied on three distinct modules for feature selection: the removal of low-variance features, univariate feature selection, and recursive feature elimination. The craniocaudally and medial-lateral views of mammograms are incorporated. We tested it with a large dataset of 3002 merged pictures gathered from 1501 individuals who had digital mammography performed between February 2007 and May 2015. In this paper, we applied six different categorization models for the diagnosis of breast cancer, including the random forest (RF), decision tree (DT), k-nearest neighbors (KNN), logistic regression (LR), support vector classifier (SVC), and linear support vector classifier (linear SVC). The simulation results prove that our proposed model is highly efficient, as it requires less computational power and is highly accurate.

Development of convolutional neural network model for diagnosing osteochondral lesions of the talus using anteroposterior ankle radiographs

Deep learning is an advanced machine learning technique that is used in several medical fields to diagnose diseases and predict therapeutic outcomes. In this study, using anteroposterior ankle radiographs, we developed a convolutional neural network (CNN) model to diagnose osteochondral lesions of the talus (OLTs) using ankle radiographs as input data. We evaluated whether a CNN model trained on anteroposterior ankle radiographs could help diagnose the presence of OLT. We retrospectively collected 379 cases (OLT cases = 133, non-OLT cases = 246) of anteroposterior ankle radiographs taken at a university hospital between January 2010 and December 2020. The OLT was diagnosed using ankle magnetic resonance images of each patient. Among the 379 cases, 70% of the included data were randomly selected as the training set, 10% as the validation set, and the remaining 20% were assigned to the test set to evaluate the model performance. To accurately classify OLT and non-OLT, we cropped the area of the ankle on anteroposterior ankle radiographs, resized the image to 224 × 224, and used it as the input data. We then used the Visual Geometry Group Network model to determine whether the input image was OLT or non-OLT. The performance of the CNN model for the area under the curve, accuracy, positive predictive value, and negative predictive value on the test data were 0.774 (95% confidence interval [CI], 0.673-0.875), 81.58% (95% CI, 0.729-0.903), 80.95% (95% CI, 0.773-0.846), and 81.82% (95% CI, 0.804-0.832), respectively. A CNN model trained on anteroposterior ankle radiographs achieved meaningful accuracy in diagnosing OLT and demonstrated that it could help diagnose OLT.

Implications of war on the food, beverage, and tobacco industry in South Korea

The Food, Beverage & Tobacco (F&B) industry is an essential sector in the competitive economy. Procurement of production factors mainly depends on sales forecasting and the supply chain of raw materials. However, the conflict between Russia and Ukraine has jeopardized the global supply chain. As the conflict worsened, the world faced a food crisis, which was already a significant challenge due to the Covid-19 pandemic. Understanding how conflict-related disruptions in global food markets might affect the stock return of the F&B industry of South Korea, this study forecasts the stock returns on the KOSDAQ F&B sector. This paper highlights that the conflict resulted in immediate and far-reaching consequences on the global food supply chain and future crop harvesting in South Korea. As numerous algorithms have been widely used in predicting stock market returns, we use Autoregressive Integrated Moving Average (ARIMA) model for the prediction. Using daily returns from the KOSDAQ F&B industry from January 1999 to October 2022, the study proposes an ARIMA (2,2,3) model to forecast future movements of the stock returns. With an RMSE of 0.012, the prediction performance holds good using the ARIMA model. The results show a negative trend observed in the F&B sector returns for a few months, implying that sector stock returns decline as the conflict between Russia and Ukraine becomes more pronounced. This study also suggests that South Korea has massive scope to stabilize the demand for healthy, safe food, give more attention to domestic agribusiness, and make itself a self-sufficient agri-economy.

The role of demographic and academic features in a student performance prediction

Educational Data Mining is widely used for predicting student's performance. It’s a challenging task because a plethora of features related to demographics, personality traits, socio-economic, and environmental may affect students' performance. Such varying features may depend on the level of study, program offered, nature of subject, and geographical location. This study attempted to predict the final semester’s results of students studying Doctor of Veterinary Medicine (DVM) based on their pre-admission academic achievements, demographics, and first semester performance. The imbalanced data led to non-generic prediction models, so it was addressed through synthetic minority oversampling technique. Among five prediction models, the Support Vector Machine led the best with 92% accuracy. The decision tree model identified key features affecting students’ performance. The analysis led to the conclusion that marks obtained in Biology, Islamiat, and Urdu at Matric and English at Intermediate level affected the students’ performance in their final semester. The findings provide useful information to predict students’ performance and guidelines for academic institutes’ management regarding improving students’ achievement. It is speculated that adoption of digital transformation may help reduce difficulty faced in data collection and analysis.

Assessment of Therapeutic Responses Using a Deep Neural Network Based on 18F-FDG PET and Blood Inflammatory Markers in Pyogenic Vertebral Osteomyelitis

Background and Objectives: This study investigated the usefulness of deep neural network (DNN) models based on ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG-PET) and blood inflammatory markers to assess the therapeutic response in pyogenic vertebral osteomyelitis (PVO). Materials and Methods: This was a retrospective study with prospectively collected data. Seventy-four patients diagnosed with PVO underwent clinical assessment for therapeutic responses based on clinical features during antibiotic therapy. The decisions of the clinical assessment were confirmed as ‘Cured’ or ‘Non-cured’. FDG-PETs were conducted concomitantly regardless of the decision at each clinical assessment. We developed DNN models depending on the use of attributes, including C-reactive protein (CRP), erythrocyte sedimentation ratio (ESR), and maximum standardized FDG uptake values of PVO lesions (SUV_max), and we compared their performances to predict PVO remission. Results: The 126 decisions (80 ‘Cured’ and 46 ‘Non-cured’ patients) were randomly assigned with training and test sets (7:3). We trained DNN models using a training set and evaluated their performances for a test set. DNN model 1 had an accuracy of 76.3% and an area under the receiver operating characteristic curve (AUC) of 0.768 [95% confidence interval, 0.625–0.910] using CRP and ESR, and these values were 79% and 0.804 [0.674–0.933] for DNN model 2 using ESR and SUV_max, 86.8% and 0.851 [0.726–0.976] for DNN model 3 using CRP and SUV_max, and 89.5% and 0.902 [0.804–0.999] for DNN model 4 using ESR, CRP, and SUV_max, respectively. Conclusions: The DNN models using SUV_max showed better performances when predicting the remission of PVO compared to CRP and ESR. The best performance was obtained in the DNN model using all attributes, including CRP, ESR, and SUV_max, which may be helpful for predicting the accurate remission of PVO.

Development of convolutional neural network model for diagnosing tear of anterior cruciate ligament using only one knee magnetic resonance image

Deep learning is an advanced machine learning approach used in diverse areas such as image analysis, bioinformatics, and natural language processing. In the current study, using only one knee magnetic resonance image of each patient, we attempted to develop a convolutional neural network (CNN) to diagnose anterior cruciate ligament (ACL) tear. We retrospectively recruited 164 patients who had knee injury and underwent knee magnetic resonance imaging evaluation. Of 164 patients, 83 patients' ACLs were torn (20 patients, partial tear; 63 patients, complete tear), whereas 81 patients' ACLs were intact. We used a CNN algorithm. Of the included subjects, 79% were assigned randomly to the training set and the remaining 21% were assigned to the test set to measure the model performance. The area under the curve was 0.941 (95% CI, 0.862-1.000) for the classification of intact and tears of the ACL. We demonstrated that a CNN model trained using one knee magnetic resonance image of each patient could be helpful in diagnosing ACL tear.

License plate identification and recognition in a non-standard environment using neural pattern matching

Non-standard license plates are a part of current traffic trends in Pakistan. Private number plates should be recognized and, monitored for several purposes including security as well as a well-developed traffic system. There is a challenging task for the authorities to recognize and trace the locations for the certain number plate vehicle. In a developing country like Pakistan, it is tough to have higher constraints on the efficiency of any license plate identification and recognition algorithm. Character recognition efficiency should be a route map for the achievement of the desired results within the specified constraints. The main goal of this study is to devise a robust detection and recognition mechanism for non-standard, transitional vehicle license plates generally found in developing countries. Improvement in the character recognition efficiency of drawn and printed plates in different styles and fonts using single using multiple state-of-the-art technologies including machine-learning (ML) models. For the mentioned study, 53-layer deep convolutional neural network (CNN) architecture based on the latest variant of object detection algorithm-You Only Look Once (YOLOv3) is employed. The proposed approach can learn the rich feature representations from the data of diversified license plates. The input image is first pre-processed for quality improvement, followed by dividing it into suitable-sized grid cells to find the correct location of the license plate. For training the CNN, license plate characters are segmented. Lastly, the results are post-processed and the accuracy of the proposed model is determined through standard benchmarks. The proposed method is successfully tested on a large image dataset consisting of eight different types of license plates from different provinces in Pakistan. The proposed system is expected to play an important role in implementing vehicle tracking, payment for parking fees, detection of vehicle over-speed limits, reducing road accidents, and identification of unauthorized vehicles. The outcome shows that the proposed approach achieves a plate detection accuracy of 97.82% and the character recognition accuracy of 96%.

Novel extreme regression-voting classifier to predict death risk in vaccinated people using VAERS data

COVID-19 vaccination raised serious concerns among the public and people are mind stuck by various rumors regarding the resulting illness, adverse reactions, and death. Such rumors are dangerous to the campaign against the COVID-19 and should be dealt with accordingly and timely. One prospective solution is to use machine learning-based models to predict the death risk for vaccinated people and clarify people’s perceptions regarding death risk. This study focuses on the prediction of the death risks associated with vaccinated people followed by a second dose for two reasons; first to build consensus among people to get the vaccines; second, to reduce the fear regarding vaccines. Given that, this study utilizes the COVID-19 VAERS dataset that records adverse events after COVID-19 vaccination as ‘recovered’, ‘not recovered’, and ‘survived’. To obtain better prediction results, a novel voting classifier extreme regression-voting classifier (ER-VC) is introduced. ER-VC ensembles extra tree classifier and logistic regression using soft voting criterion. To avoid model overfitting and get better results, two data balancing techniques synthetic minority oversampling (SMOTE) and adaptive synthetic sampling (ADASYN) have been applied. Moreover, three feature extraction techniques term frequency-inverse document frequency (TF-IDF), bag of words (BoW), and global vectors (GloVe) have been used for comparison. Both machine learning and deep learning models are deployed for experiments. Results obtained from extensive experiments reveal that the proposed model in combination with TF-TDF has shown robust results with a 0.85 accuracy when trained on the SMOTE-balanced dataset. In line with this, validation of the proposed voting classifier on binary classification shows state-of-the-art results with a 0.98 accuracy. Results show that machine learning models can predict the death risk with high accuracy and can assist the authors in taking timely measures.

Prediction of Motor Outcome of Stroke Patients Using a Deep Learning Algorithm with Brain MRI as Input Data

BACKGROUND

Deep learning techniques can outperform traditional machine learning techniques and learn from unstructured and perceptual data, such as images and languages. We evaluated whether a convolutional neural network (CNN) model using whole axial brain T2-weighted magnetic resonance (MR) images as input data can help predict motor outcomes of the upper and lower limbs at the chronic stage in stroke patients.

METHODS

We collected MR images taken at the early stage of stroke in 1,233 consecutive stroke patients. We categorized modified Brunnstrom classification (MBC) scores of ≥5 and functional ambulatory category (FAC) scores of ≥4 at 6 months after stroke as favorable outcomes in the upper and lower limbs, respectively, and MBC scores of <5 and FAC scores of <4 as poor outcomes. We applied a CNN to train the image data. Of the 1,233 patients, 70% (863 patients) were randomly selected for the training set and the remaining 30% (370 patients) were assigned to the validation set.

RESULTS

In the prediction of upper limb motor function on the validation dataset, the area under the curve (AUC) was 0.768, and for lower limb motor function, the AUC was 0.828.

CONCLUSION

We showed that a CNN model trained using whole-brain axial T2-weighted MR images of stroke patients would help predict upper and lower limb motor function at the chronic stage.

Development of convolutional neural network model for diagnosing meniscus tear using magnetic resonance image

Background

Deep learning (DL) is an advanced machine learning approach used in diverse areas, such as image analysis, bioinformatics, and natural language processing. A convolutional neural network (CNN) is a representative DL model that is advantageous for image recognition and classification. In this study, we aimed to develop a CNN to detect meniscal tears and classify tear types using coronal and sagittal magnetic resonance (MR) images of each patient.

Methods

We retrospectively collected 599 cases (medial meniscus tear = 384, lateral meniscus tear = 167, and medial and lateral meniscus tear = 48) of knee MR images from patients with meniscal tears and 449 cases of knee MR images from patients without meniscal tears. To develop the DL model for evaluating the presence of meniscal tears, all the collected knee MR images of 1048 cases were used. To develop the DL model for evaluating the type of meniscal tear, 538 cases with meniscal tears (horizontal tear = 268, complex tear = 147, radial tear = 48, and longitudinal tear = 75) and 449 cases without meniscal tears were used. Additionally, a CNN algorithm was used. To measure the model’s performance, 70% of the included data were randomly assigned to the training set, and the remaining 30% were assigned to the test set.

Results

The area under the curves (AUCs) of our model were 0.889, 0.817, and 0.924 for medial meniscal tears, lateral meniscal tears, and medial and lateral meniscal tears, respectively. The AUCs of the horizontal, complex, radial, and longitudinal tears were 0.761, 0.850, 0.601, and 0.858, respectively.

Conclusion

Our study showed that the CNN model has the potential to be used in diagnosing the presence of meniscal tears and differentiating the types of meniscal tears.

PlantMWpIDB: a database for the molecular weight and isoelectric points of the plant proteomes

The molecular weight and isoelectric point of the proteins are very important parameters that control their subcellular localization and subsequent function. Although the genome sequence data of the plant kingdom improved enormously, the proteomic details have been poorly elaborated. Therefore, we have calculated the molecular weight and isoelectric point of the plant proteins and reported them in this database. A database, PlantMWpIDB, containing protein data from 342 plant proteomes was created to provide information on plant proteomes for hypothesis formulation in basic research and for biotechnological applications. The Molecular weight and isoelectric point (pI) are important molecular parameters of proteins that are useful when conducting protein studies involving 2D gel electrophoresis, liquid chromatography-mass spectrometry, and X-ray protein crystallography. PlantMWpIDB provides an easy-to-use and efficient interface for search options and generates a summary of basic protein parameters. The database represents a virtual 2D proteome map of plants, and the molecular weight and pI of a protein can be obtained by searching on the name of a protein, a keyword, or by a list of accession numbers. The PlantMWpIDB database also allows one to query protein sequences. The database can be found in the following link https://plantmwpidb.com/ . The individual 2D virtual proteome map of the plant kingdom will enable us to understand the proteome diversity between different species. Further, the molecular weight and isoelectric point of individual proteins can enable us to understand their functional significance in different species.

Classification of movie reviews using term frequency-inverse document frequency and optimized machine learning algorithms

The Internet Movie Database (IMDb), being one of the popular online databases for movies and personalities, provides a wide range of movie reviews from millions of users. This provides a diverse and large dataset to analyze users' sentiments about various personalities and movies. Despite being helpful to provide the critique of movies, the reviews on IMDb cannot be read as a whole and requires automated tools to provide insights on the sentiments in such reviews. This study provides the implementation of various machine learning models to measure the polarity of the sentiments presented in user reviews on the IMDb website. For this purpose, the reviews are first preprocessed to remove redundant information and noise, and then various classification models like support vector machines (SVM), Naïve Bayes classifier, random forest, and gradient boosting classifiers are used to predict the sentiment of these reviews. The objective is to find the optimal process and approach to attain the highest accuracy with the best generalization. Various feature engineering approaches such as term frequency-inverse document frequency (TF-IDF), bag of words, global vectors for word representations, and Word2Vec are applied along with the hyperparameter tuning of the classification models to enhance the classification accuracy. Experimental results indicate that the SVM obtains the highest accuracy when used with TF-IDF features and achieves an accuracy of 89.55%. The sentiment classification accuracy of the models is affected due to the contradictions in the user sentiments in the reviews and assigned labels. For tackling this issue, TextBlob is used to assign a sentiment to the dataset containing reviews before it can be used for training. Experimental results on TextBlob assigned sentiments indicate that an accuracy of 92% can be obtained using the proposed model.

Deep Learning Analysis to Automatically Detect the Presence of Penetration or Aspiration in Videofluoroscopic Swallowing Study

BACKGROUND

Videofluoroscopic swallowing study (VFSS) is currently considered the gold standard to precisely diagnose and quantitatively investigate dysphagia. However, VFSS interpretation is complex and requires consideration of several factors. Therefore, considering the expected impact on dysphagia management, this study aimed to apply deep learning to detect the presence of penetration or aspiration in VFSS of patients with dysphagia automatically.

METHODS

The VFSS data of 190 participants with dysphagia were collected. A total of 10 frame images from one swallowing process were selected (five high-peak images and five low-peak images) for the application of deep learning in a VFSS video of a patient with dysphagia. We applied a convolutional neural network (CNN) for deep learning using the Python programming language. For the classification of VFSS findings (normal swallowing, penetration, and aspiration), the classification was determined in both high-peak and low-peak images. Thereafter, the two classifications determined through high-peak and low-peak images were integrated into a final classification.

RESULTS

The area under the curve (AUC) for the validation dataset of the VFSS image for the CNN model was 0.942 for normal findings, 0.878 for penetration, and 1.000 for aspiration. The macro average AUC was 0.940 and micro average AUC was 0.961.

CONCLUSION

This study demonstrated that deep learning algorithms, particularly the CNN, could be applied for detecting the presence of penetration and aspiration in VFSS of patients with dysphagia.

Predicting death risk analysis in fully vaccinated people using novel extreme regression-voting classifier

Vaccination for the COVID-19 pandemic has raised serious concerns among the public and various rumours are spread regarding the resulting illness, adverse reactions, and death. Such rumours can damage the campaign against the COVID-19 and should be dealt with accordingly. One prospective solution is to use machine learning-based models to predict the death risk for vaccinated people by utilizing the available data. This study focuses on the prognosis of three significant events including ‘not survived’, ‘recovered’, and ‘not recovered’ based on the adverse events followed by the second dose of the COVID-19 vaccine. Extensive experiments are performed to analyse the efficacy of the proposed Extreme Regression- Voting Classifier model in comparison with machine learning models with Term Frequency-Inverse Document Frequency, Bag of Words, and Global Vectors, and deep learning models like Convolutional Neural Network, Long Short Term Memory, and Bidirectional Long Short Term Memory. Experiments are carried out on the original, as well as, a balanced dataset using Synthetic Minority Oversampling Approach. Results reveal that the proposed voting classifier in combination with TF-IDF outperforms with a 0.85 accuracy score on the SMOTE-balanced dataset. In line with this, the validation of the proposed voting classifier on binary classification shows state-of-the-art results with a 0.98 accuracy.

Detecting sarcasm in multi-domain datasets using convolutional neural networks and long short term memory network model

Sarcasm emerges as a common phenomenon across social networking sites because people express their negative thoughts, hatred and opinions using positive vocabulary which makes it a challenging task to detect sarcasm. Although various studies have investigated the sarcasm detection on baseline datasets, this work is the first to detect sarcasm from a multi-domain dataset that is constructed by combining Twitter and News Headlines datasets. This study proposes a hybrid approach where the convolutional neural networks (CNN) are used for feature extraction while the long short-term memory (LSTM) is trained and tested on those features. For performance analysis, several machine learning algorithms such as random forest, support vector classifier, extra tree classifier and decision tree are used. The performance of both the proposed model and machine learning algorithms is analyzed using the term frequency-inverse document frequency, bag of words approach, and global vectors for word representations. Experimental results indicate that the proposed model surpasses the performance of the traditional machine learning algorithms with an accuracy of 91.60%. Several state-of-the-art approaches for sarcasm detection are compared with the proposed model and results suggest that the proposed model outperforms these approaches concerning the precision, recall and F1 scores. The proposed model is accurate, robust, and performs sarcasm detection on a multi-domain dataset.

Diagnosis of vertebral column pathologies using concatenated resampling with machine learning algorithms

Medical diagnosis through the classification of biomedical attributes is one of the exponentially growing fields in bioinformatics. Although a large number of approaches have been presented in the past, wide use and superior performance of the machine learning (ML) methods in medical diagnosis necessitates significant consideration for automatic diagnostic methods. This study proposes a novel approach called concatenated resampling (CR) to increase the efficacy of traditional ML algorithms. The performance is analyzed leveraging four ML approaches like tree-based ensemble approaches, and linear machine learning approach for automatic diagnosis of inter-vertebral pathologies with increased. Besides, undersampling, over-sampling, and proposed CR techniques have been applied to unbalanced training dataset to analyze the impact of these techniques on the accuracy of each of the classification model. Extensive experiments have been conducted to make comparisons among different classification models using several metrics including accuracy, precision, recall, and F ₁ score. Comparative analysis has been performed on the experimental results to identify the best performing classifier along with the application of the re-sampling technique. The results show that the extra tree classifier achieves an accuracy of 0.99 in association with the proposed CR technique.

A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis

The spread of Covid-19 has resulted in worldwide health concerns. Social media is increasingly used to share news and opinions about it. A realistic assessment of the situation is necessary to utilize resources optimally and appropriately. In this research, we perform Covid-19 tweets sentiment analysis using a supervised machine learning approach. Identification of Covid-19 sentiments from tweets would allow informed decisions for better handling the current pandemic situation. The used dataset is extracted from Twitter using IDs as provided by the IEEE data port. Tweets are extracted by an in-house built crawler that uses the Tweepy library. The dataset is cleaned using the preprocessing techniques and sentiments are extracted using the TextBlob library. The contribution of this work is the performance evaluation of various machine learning classifiers using our proposed feature set. This set is formed by concatenating the bag-of-words and the term frequency-inverse document frequency. Tweets are classified as positive, neutral, or negative. Performance of classifiers is evaluated on the accuracy, precision, recall, and F1 score. For completeness, further investigation is made on the dataset using the Long Short-Term Memory (LSTM) architecture of the deep learning model. The results show that Extra Trees Classifiers outperform all other models by achieving a 0.93 accuracy score using our proposed concatenated features set. The LSTM achieves low accuracy as compared to machine learning classifiers. To demonstrate the effectiveness of our proposed feature set, the results are compared with the Vader sentiment analysis technique based on the GloVe feature extraction approach.

COVINet: a convolutional neural network approach for predicting COVID-19 from chest X-ray images

COVID-19 pandemic is widely spreading over the entire world and has established significant community spread. Fostering a prediction system can help prepare the officials to respond properly and quickly. Medical imaging like X-ray and computed tomography (CT) can play an important role in the early prediction of COVID-19 patients that will help the timely treatment of the patients. The x-ray images from COVID-19 patients reveal the pneumonia infections that can be used to identify the patients of COVID-19. This study presents the use of Convolutional Neural Network (CNN) that extracts the features from chest x-ray images for the prediction. Three filters are applied to get the edges from the images that help to get the desired segmented target with the infected area of the x-ray. To cope with the smaller size of the training dataset, Keras' ImageDataGenerator class is used to generate ten thousand augmented images. Classification is performed with two, three, and four classes where the four-class problem has X-ray images from COVID-19, normal people, virus pneumonia, and bacterial pneumonia. Results demonstrate that the proposed CNN model can predict COVID-19 patients with high accuracy. It can help automate screening of the patients for COVID-19 with minimal contact, especially areas where the influx of patients can not be treated by the available medical staff. The performance comparison of the proposed approach with VGG16 and AlexNet shows that classification results for two and four classes are competitive and identical for three-class classification.

Home automation using general purpose household electric appliances with Raspberry Pi and commercial smartphone

This study presents the design and implementation of a home automation system that focuses on the use of ordinary electrical appliances for remote control using Raspberry Pi and relay circuits and does not use expensive IP-based devices. Common Lights, Heating, Ventilation, and Air Conditioning (HVAC), fans, and other electronic devices are among the appliances that can be used in this system. A smartphone app is designed that helps the user to design the smart home to his actual home via easy and interactive drag & drop option. The system provides control over the appliances via both the local network and remote access. Data logging over the Microsoft Azure cloud database ensures system recovery in case of gateway failure and data record for lateral use. Periodical notifications also help the user to optimize the usage of home appliances. Moreover, the user can set his preferences and the appliances are auto turned off and on to meet user-specific requirements. Raspberry Pi acting as the server maintains the database of each appliance. HTTP web interface and apache server are used for communication between the android app and raspberry pi. With a 5v relay circuit and micro-processor Raspberry Pi, the proposed system is low-cost, energy-efficient, easy to operate, and affordable for low-income houses.

Heartbeat Sound Signal Classification Using Deep Learning

Presently, most deaths are caused by heart disease. To overcome this situation, heartbeat sound analysis is a convenient way to diagnose heart disease. Heartbeat sound classification is still a challenging problem in heart sound segmentation and feature extraction. Dataset-B applied in this study that contains three categories Normal, Murmur and Extra-systole heartbeat sound. In the purposed framework, we remove the noise from the heartbeat sound signal by applying the band filter, After that we fixed the size of the sampling rate of each sound signal. Then we applied down-sampling techniques to get more discriminant features and reduce the dimension of the frame rate. However, it does not affect the results and also decreases the computational power and time. Then we applied a purposed model Recurrent Neural Network (RNN) that is based on Long Short-Term Memory (LSTM), Dropout, Dense and Softmax layer. As a result, the purposed method is more competitive compared to other methods.

Tweets Classification on the Base of Sentiments for US Airline Companies

The use of data from social networks such as Twitter has been increased during the last few years to improve political campaigns, quality of products and services, sentiment analysis, etc. Tweets classification based on user sentiments is a collaborative and important task for many organizations. This paper proposes a voting classifier (VC) to help sentiment analysis for such organizations. The VC is based on logistic regression (LR) and stochastic gradient descent classifier (SGDC) and uses a soft voting mechanism to make the final prediction. Tweets were classified into positive, negative and neutral classes based on the sentiments they contain. In addition, a variety of machine learning classifiers were evaluated using accuracy, precision, recall and F1 score as the performance metrics. The impact of feature extraction techniques, including term frequency (TF), term frequency-inverse document frequency (TF-IDF), and word2vec, on classification accuracy was investigated as well. Moreover, the performance of a deep long short-term memory (LSTM) network was analyzed on the selected dataset. The results show that the proposed VC performs better than that of other classifiers. The VC is able to achieve an accuracy of 0.789, and 0.791 with TF and TF-IDF feature extraction, respectively. The results demonstrate that ensemble classifiers achieve higher accuracy than non-ensemble classifiers. Experiments further proved that the performance of machine learning classifiers is better when TF-IDF is used as the feature extraction method. Word2vec feature extraction performs worse than TF and TF-IDF feature extraction. The LSTM achieves a lower accuracy than machine learning classifiers.

Laparoscopic right posterior sectionectomy versus laparoscopic right hemihepatectomy for hepatocellular carcinoma in posterior segments: Propensity Score Matching Analysis

BACKGROUND AND AIMS:

This study was designed to analyze the feasibility of laparoscopic right posterior sectionectomy compared to laparoscopic right hemihepatectomy in patients with hepatocellular carcinoma located in the posterior segments.

MATERIAL AND METHODS:

The study included patients who underwent either laparoscopic right posterior sectionectomy or laparoscopic right hemihepatectomy for hepatocellular carcinoma located in segment 6 or 7 from January 2009 to December 2016 at Samsung Medical Center. After 1:1 propensity score matching, patient baseline characteristics and operative and postoperative outcomes were compared between the two groups. Disease-free survival and overall survival were compared using Kaplan-Meier log-rank test.

RESULTS:

Among 61 patients with laparoscopic right posterior sectionectomy and 37 patients with laparoscopic right hemihepatectomy, 30 patients from each group were analyzed after propensity score matching. After matching, baseline characteristics of the two groups were similar including tumor size (3.4 ± 1.2 cm in laparoscopic right posterior sectionectomy vs 3.7 ± 2.1 cm in laparoscopic right hemihepatectomy, P = 0.483); differences were significant before matching (3.1 ± 1.3 cm in laparoscopic right posterior sectionectomy vs 4.3 ± 2.7 cm in laparoscopic right hemihepatectomy, P = 0.035). No significant differences were observed in operative and postoperative data except for free margin size (1.04 ± 0.71 cm in laparoscopic right posterior sectionectomy vs 2.95 ± 1.75 cm in laparoscopic right hemihepatectomy, P < 0.001). Disease-free survival (5-year survival: 38.0% in laparoscopic right posterior sectionectomy vs 47.0% in laparoscopic right hemihepatectomy, P = 0.510) and overall survival (5-year survival: 92.7% in laparoscopic right posterior sectionectomy vs 89.6% in laparoscopic right hemihepatectomy, P = 0.593) did not differ between the groups based on Kaplan-Meier log-rank test.

CONCLUSION:

For hepatocellular carcinoma in the posterior segments, laparoscopic right posterior sectionectomy was feasible compared to laparoscopic right hemihepatectomy when performed by experienced laparoscopic surgeons.

Early Vs Late Liver Retransplantation: Different Characteristics and Prognostic Factors

BACKGROUND

East Asia is a known endemic area for hepatitis B, and living donor liver transplantation is mainly performed. Liver retransplantation (ReLT) is expected to become an increasing problem because of a shortage of organs. This study aimed to compare early and late ReLT with consideration of specific circumstances and disease background of East Asians.

METHODS

Between October 1996 and January 2015, 51 patients underwent ReLT; we performed a retrospective analysis of data obtained from medical records of the patients. Clinical characteristics, indication, causes of death, survival rate, and prognostic factors were investigated.

RESULT

The survival rate for early ReLT (n = 18) was 51.5% and that for late ReLT (n = 33) was 50.1% at 1 year postoperatively. Continuous venovenous hemodialysis and the use of mechanical ventilators were more frequent, and pre-retransplant intensive care unit stay and prothrombin time was longer in early ReLT than in late ReLT. Operation time was longer and the amount of intraoperative blood loss was greater in late ReLT than in early ReLT. Multivariate analysis showed that a higher C-reactive protein level increased mortality in early ReLT (P = .045), whereas a higher total bilirubin level increased the risk of death in late ReLT (P = .03).

CONCLUSION

Patients with early ReLT are likely to be sicker pre-retransplantation and require adequate treatment of the pretransplant infectious disease. On the other hand, late ReLT is likely to be technically more difficult and should be decided before the total bilirubin level increases substantially.

Multi-functional magnesium alloys containing interstitial oxygen atoms

A new class of magnesium alloys has been developed by dissolving large amounts of oxygen atoms into a magnesium lattice (Mg-O alloys). The oxygen atoms are supplied by decomposing titanium dioxide nanoparticles in a magnesium melt at 720 °C; the titanium is then completely separated out from the magnesium melt after solidification. The dissolved oxygen atoms are located at the octahedral sites of magnesium, which expand the magnesium lattice. These alloys possess ionic and metallic bonding characteristics, providing outstanding mechanical and functional properties. A Mg-O-Al casting alloy made in this fashion shows superior mechanical performance, chemical resistance to corrosion, and thermal conductivity. Furthermore, a similar Mg-O-Zn wrought alloy shows high elongation to failure (>50%) at room temperature, because the alloy plastically deforms with only multiple slips in the sub-micrometer grains (<300 nm) surrounding the larger grains (~15 μm). The metal/non-metal interstitial alloys are expected to open a new paradigm in commercial alloy design.

Classification by causes of dark circles and appropriate evaluation method of dark circles

BACKGROUND

Dark circles refer to a symptom that present darkness under the eyes. Because of improvement in the quality of life, the dark circles have been recognized as one of major cosmetic concerns. However, it is not easy to classify the dark circles because they have various causes.

METHODS

To select suitable instruments and detailed evaluation items, the dark circles were classified according to the causes through visual assessment, Wood's lamp test, and medical history survey for 100 subjects with dark circles. After the classification, were newly recruited for instrument conformity assessment. Through this, suitable instruments for dark circle evaluation were selected. We performed a randomized clinical trial for dark circles, a placebo-controlled double-blind study, using effective parameters of the instruments selected from the preliminary test.

RESULTS

Dark circles of vascular type (35%) and mixed type (54%), a combination of pigmented and vascular types, were the most common. Twenty four subjects with the mixed type dark circles applied the test product (Vitamin C 3%, Vitamin A 0.1%, Vitamin E 0.5%) and placebo on randomized split-face for 8 weeks. The effective parameters (L*, a, M.I., E.I., quasi L*, quasi a* and dermal thickness) were measured during the study period. Result showed that the L* value of Chromameter(®) , Melanin index (M.I.) of Mexameter(®) and quasi L* value obtained by image analysis improved with statistical significance after applying the test product compared with the placebo product.

CONCLUSION

We classified the dark circles according to the causes of the dark circles and verified the reliability of the parameter obtained by the instrument conformity assessment used in this study through the efficacy evaluation. Also based on this study, we were to suggest newly established methods which can be applied to the evaluation of efficacy of functional cosmetics for dark circles.

LDA topics: Representation and evaluation

In recent years many automated topic coherence formulas (using the top- m words of a topic inferred by latent Dirichlet allocation) based on word similarities have been proposed and evaluated against human ratings. We treat a wordy topic as an object and quantitatively describe it via normalized mean values of pair-wise word similarities. Two types of word similarities, thesaurus and local corpus-based, are used as the descriptive features of a topic. We perform topic classification using represented topics as input and bi-level human ratings about topic coherence as class labels. Classification results (precision, recall and accuracy) based on two datasets and three supervised classification algorithms suggest that the novel topic representation is consistent with human ratings. Corpus-based word similarities are positively correlated with human ratings whereas thesaurus-based similarities have negative relations. The proposed representation of topics opens a window for us to investigate the utilization of topics with different perspectives.

Influence of hepatitis B virus reactivation on the recurrence of HBV-related hepatocellular carcinoma after curative resection in patients with low viral load

It is unclear whether the reactivation of hepatitis B virus (HBV) influences the prognosis of hepatocellular carcinoma (HCC) after resection in patients with chronic hepatitis B. The aim of this study was to identify the influence of HBV reactivation on the recurrence of hepatitis B-related HCC after curative resection in patients with low viral load (HBV DNA <2000 IU/mL). We retrospectively analysed a total of 130 patients who underwent curative resection for HBV-related early stage HCC (single nodule; <5 cm/two or three nodules; <3 cm) with pre-operative HBV DNA levels <2000 IU/mL with serial HBV DNA tests. The predictive factors including HBV reactivation for the recurrence of HBV-related HCC after curative resection were investigated. Fifty-three patients (41%) had HBV reactivation after resection among 130 patients. HBV reactivation was observed in 22 of 53 patients with undetectable baseline HBV DNA and in 31 of 77 patients with detectable baseline HBV DNA. Cumulative recurrence rates after resection at 1, 2 and 3 years were 17.0%, 23.3% and 31.4%, respectively. The multivariable analysis demonstrated that the risk factors for the recurrence were the presence of microvascular invasion (hazard ratio (HR) 2.62, P = 0.003), multinodularity (HR 4.61, P = 0.005), HBV reactivation after resection (HR 2.03, P = 0.032) and HBeAg positivity (HR 2.06, P = 0.044). HBV reactivation after curative resection is associated with the recurrence of HBV-related HCC in patients with low viral load.

Oncologic outcomes of laparoscopic nephroureterectomy for pT3 upper urinary tract urothelial carcinoma

AIM

We present the oncologic outcomes of laparoscopic nephroureterectomy management of pT3 upper urinary tract urothelial carcinoma.

METHODS

Between October 2003 and January 2011, 50 patients with pT3 upper urinary tract urothelial carcinoma which had pathologically confirmed underwent laparoscopic nephroureterectomy at our institution. Demographic data, perioperative results, pathological findings and oncologic outcomes were reviewed and analyzed retrospectively.

RESULTS

There were 36 patients (72%) of high grade lesion and 14 patients (28%) of low grade lesion. Lymphovascular invasion was observed in 16 patients (32%) and the surgical margin was positive in one patient. N stage was pN0 in 16 (32%), pN1 in 3 (6%), pN2 in 1 (2%) and pN3 in 1 (2%). The 5-year overall survival rate was 52.6% and the 5-year cancer-specific survival rate was 65.3%. Overall recurrence developed in 23 patients. There were 10 patients (20%) of urothelial recurrence which were all occurred in the bladder at the mean period of 13.6 months, and 7 patients of them were invasive bladder cancer. There were 16 patients (32%) of non-urothelial recurrence developed at the mean period of 9.69 months. On multivariate analyses lymphadenopathy and lymph node involvement of cancer (N+) were identified as independent predictive factors for the cancer-specific survival, and concomitant bladder tumor, grade and lymphovascular invasion were identified as independent predictive factors for the overall recurrence free survival.

CONCLUSION

Laparoscopic nephroureterectomy in patients with high stage upper urinary tract urothelial carcinoma appear comparable to those of open surgery in the regard of oncologic outcomes.

First Report of Cucumber mosaic virus in Saintpaulia ionantha in Korea

African violet (Saintpaulia ionantha) is an ornamental species of the family Gesneriaceae and is characterized by fleshy leaves and colorful flowers. This popular, exotic ornamental, originally from Kenya and Tanzania, is vegetatively produced from cutting and tissue culture (1). In May 2013, virus-like foliar symptoms, including a mosaic with dark green islands and chlorosis surrounding the veins, were observed on an African violet plant in a greenhouse located in Icheon, Korea. Cucumber mosaic virus (CMV) was identified in the symptomatic plant by serological testing for the presence of CMV coat protein (CP) with a commercial immunostrip kit (Agdia, Elkhart, IN). The presence of CMV was confirmed by serological detection with a commercially available double-antibody sandwich (DAS)-ELISA kit (Agdia). Sap from the serologically positive sample was mechanically inoculated to test plants using 10 mM phosphate buffer (pH 7.0). The virus (named CMV-AV1) caused necrotic local lesions on Chenopodium amaranticolor at 5 days post-inoculation (dpi), while mild to severe mosaic was observed in Nicotiana glutinosa, N. tabacum 'Samsun NN,' Cucurbita pepo 'Super-Top,' Physalis angulate, and Solanum lycopersicum 'Unicorn' 10 to 14 dpi. Examination of the inoculated plant leaves by DAS-ELISA and electron microscopy (leaf dips) showed positive reactions to CMV and the presence of spherical virions ∼28 nm in diameter, respectively. To verify whether CMV-AV1 is the cause of disease symptoms observed in African violet, virus-free African violet (10 plants) was mechanically inoculated by sap from local lesions on C. amaranticolor inoculated with CMV-AV1. At 8 weeks after inoculation, all plants produced systemic mosaic and chlorosis surrounding veins, resulting in strong DAS-ELISA reactions for CMV, whereas mock-inoculated African violet plants remained symptomless and virus-free. The presence of CMV-AV1 in all naturally infected and mechanically inoculated plants was further verified by reverse transcription (RT)-PCR. Total RNAs were extracted with the RNeasy Plant Mini Kit (Qiagen, Hilden, Germany), according to the manufacturer's instructions. RT-PCR was carried out with the One-Step RT-PCR Kit (Invitrogen, Carlsbad, CA) using a pair of primers, CPTALL3 and CPTALL5 (2), amplifying the entire CP gene and part of an intergenic region and 3'-noncoding region of CMV RNA3. RT-PCR products (960 bp) were obtained from all naturally infected and mechanically inoculated plants as well as from positive control (viral RNAs from virions), but not from healthy tissues. The amplified RT-PCR products were purified with QIAquick PCR Purification Kit (Qiagen) and sequenced using BigDye Termination kit (Applied Biosystems, Foster City, CA). Multiple alignment of the CMV-AV1 CP sequence (Accession No. AB842275) with CP sequences of other CMV isolates using MEGA5 software revealed that 91.8 to 99.0% and 71.0 to 73.0% identities to those of CMV subgroup I and subgroup II, respectively. These results provide additional confirmation of CMV-AV1 infection. CMV may pose a major threat for production of African violet since the farming of African violet plants is performed using the vegetative propagation of the African violet leaves in Korea. In particular, mosaic and chlorosis symptoms in African violet cause damage to ornamental quality of African violet. To our knowledge, this is the first report of CMV infection of African violet in the world. References: (1) S. T. Baatvik. Fragm. Flor. Geobot. Suppl. 2:97, 1993. (2) S. K. Choi et al. J. Virol. Methods 83:67, 1999.

First Report of Cherry necrotic rusty mottle virus Infecting Sweet Cherry Trees in Korea

Cherry necrotic rusty mottle virus (CNRMV), an unassigned member in the family Betaflexiviridae, has been reported in sweet cherry in North America, Europe, New Zealand, Japan, China, and Chile. The virus causes brown, angular necrotic spots, shot holes on the leaves, gum blisters, and necrosis of the bark in several cultivars (1). During the 2012 growing season, 154 sweet cherry trees were tested for the presence of CNRMV by RT-PCR. Samples were randomly collected from 11 orchards located in Gyeonggi and Gyeongsang provinces in Korea. RNA was extracted from leaves using the NucliSENS easyMAG system (bioMérieux, Boxtel, The Netherlands). The primer pair CGRMV1/2 (2) was used to amplify the coat protein region of CNRMV. Although none of the collected samples showed any notable symptoms, CNRMV PCR products of the expected size (949 bp) were obtained from three sweet cherry samples from one orchard in Gyeonggi province. The PCR products were cloned into a pGEM-T easy vector (Promega, Madison, WI) and sequenced. BLAST analyses of the three Korean sequences obtained (GenBank Accession Nos. AB822635, AB822636, and AB822637) showed 97% nucleotide sequence identity with a flowering cherry isolate from Japan (EU188439), and shared 98.8 to 99.6% nucleotide and 99.6 to 100% amino acid similarities to each other. The CNRMV positive samples were also tested for Apple chlorotic leaf spot virus (ACLSV), Cherry mottle leaf virus (CMLV), Cherry rasp leaf virus (CRLV), Cherry leafroll virus (CLRV), Cherry virus A (CVA), Little cherry virus 1 (LChV-1), Prune dwarf virus (PDV), and Prunus necrotic ringspot virus (PNRSV) by RT-PCR. One of the three CNRMV-positive samples was also infected with CVA. To confirm CNRMV infection by wood indexing, Prunus serrulata cv. Kwanzan plants were graft-inoculated with chip buds from the CNRMV-positive sweet cherry trees. At 3 to 4 weeks post-inoculation, the Kwanzan plants showed quick decline with leaves wilting and dying; CNRMV infection of the indicators was confirmed by RT-PCR. To our knowledge, this is the first report of CNRMV infection of sweet cherry trees in Korea. Screening for CNRMV in propagation nurseries should minimize spread of this virus within Korea. References: (1) R. Li and R. Mock. Arch. Virol. 153:973, 2008. (2) R. Li and R. Mock. J. Virol. Methods 129:162, 2005.

Serum metabolomics reveals pathways and biomarkers associated with asthma pathogenesis

BACKGROUND

Asthma is a chronic inflammatory disease caused by complex interactions of genetic, epigenetic, and environmental factors. For this reason, new approaches are required to clarify the pathogenesis of asthma by systemic review.

OBJECTIVE

We applied a (1)H-NMR metabolomics approach to investigate the altered metabolic pattern in sera from patients with asthma and sought to identify the mechanism underlying asthma and potential biomarkers.

METHOD

A global profile of sera from patients with asthma (n = 39) and controls (n = 26) was generated using (1)H-NMR spectroscopy coupled with multivariate statistical analysis. Endogenous metabolites in serum were rapidly measured using the target-profiling procedure.

RESULTS

Multivariate statistical analysis showed a clear distinction between patients with asthma and healthy subjects. Sera of asthma patients were characterized by increased levels of methionine, glutamine, and histidine and by decreased levels of formate, methanol, acetate, choline, O-phosphocholine, arginine, and glucose. The metabolites detected in the sera of patients with asthma are involved in hypermethylation, response to hypoxia, and immune reaction. Furthermore, the levels of serum metabolites from patients with asthma correlated with asthma severity; in particular, lipid metabolism was altered in patients with lower forced expiratory volume in 1 s percentage (FEV(1)%) predicted values. In addition, potential biomarkers showed strong predictive power in ROC analysis, and the presence of asthma in external validation models was predicted with high accuracy (90.9% for asthma and 100% for control subjects).

CONCLUSION & CLINICAL RELEVANCE

These data showed that (1)H-NMR-based metabolite profiling of serum may be useful for the effective diagnosis of asthma and a further understanding of its pathogenesis.

Primary versus salvage living donor liver transplantation for patients with hepatocellular carcinoma: impact of microvascular invasion on survival

OBJECTIVE

Salvage liver transplantation (LT) has been proposed for patients with a small hepatocellular carcinoma (HCC) and preserved liver function. Few reports have been issued on salvage LT in a living-donor (LD) LT setting. Therefore, we performed this study to evaluate differences in tumor invasiveness and other risk factors on survival after salvage versus primary LDLT.

METHODS

Between September 1996 and December 2008, 324 patients with HCC underwent LT. We excluded 138 patient from the analysis, leaving 186 HCC patients for analysis, including 17 (9.1%) who had undergone earlier resection, the salvage LDLT cohort. The other 169 patients underwent primary LDLT.

RESULTS

Intrahepatic metastasis, Edmonson-Steiner histologic grade, microscopic vascular invasion, and preoperative serum alpha-fetoprotein levels significantly influenced tumor recurrence. Microscopic vascular invasion, intrahepatic metastasis, Edmonson-Steiner histologic grade, and treatment by salvage LDLT were significantly associated with poor patient survival univariate analysis. However, only microscopic vascular invasion was significant on multivariate analysis. The treatment modality (primary or salvage LDLT) was not observed to affect overall or disease-free survival significantly on multivariate analysis. Disease-free survival was significantly better in the primary than in the salvage LDLT group. Furthermore, patients in the primary LDLT group tended to show better survival. However, when stratified by the presence or absence of microscopic vascular invasion, no significant group difference was found for overall or disease-free survival among those without versus with microscopic vascular invasion.

CONCLUSIONS

Five-year overall survival after primary versus salvage LDLT were similar when differences in tumor pathologic features, such as microscopic vascular invasion, were taken into account. Multivariate analysis showed that the treatment itself was not a significant prognostic factor for survival.

First Report of Blueberry red ringspot virus Infecting Highbush Blueberry in Korea

Blueberry red ringspot virus (BRRSV) of the Soymovirus genus in the family Caulimovididae causes red ringspot diseases in highbush blueberry (Vaccinium corymbosum L.) on leaves, stems, and fruits. The virus has been identified in the United States, Japan, Czech Republic, Slovenia, and Poland (1). In July 2010, highbush blueberry with red ringspots on leaves and circular blotches on ripening fruits was found in one plant of cv. Duke in Pyeongtaek, Korea. The symptoms were similar to red ringspot disease caused by BRRSV (3), although stems did not show any characteristic symptoms. Red ringspots on the upper surface of leaves were the most visible symptom and became more prominent as leaves matured in August through October. Leaves of the symptomatic plant were collected and tested for BRRSV infection by PCR, and were also embedded for electron microscopy. DNA was extracted from leaves using DNeasy Plant Mini Kit (Qiagen, Valencia, CA) according to the manufacturer's instructions. Primer pairs BR1512F/BR2377R (5'-ACAGGACGATTAGAAGATGG-3'/5'-CCTTTAGGGCAATATTTCTG-3', amplifying a fragment of the coat protein region with an expected size of 865 bp) and BR2961F/BR3726R (5'-ACCGATACATCACAGTTCAC-3'/5'-TGGTTGTGATAAGATGATTCC-3', amplifying a fragment of the reverse transcriptase region with an expected size of 766 bp) were used to amplify the indicated region of BRRV in PCR. Primers were designed on the basis of the BRRSV isolate from New Jersey (GenBank Accession No. AF404509). DNA fragments of the expected sizes were obtained from the symptomatic plant, while no amplification products were obtained from highbush blueberry without symptoms. The PCR products were cloned into pGEM-T easy vector (Promega, Madison, WI) and sequenced. BLAST analyses of obtained fragments revealed 91 to 98% nucleotide sequence identity with the coat protein gene (GenBank Accession No. JQ706341) and 96 to 98% nucleotide sequence identity with the reverse transcriptase gene (GenBank Accession No. JQ706340) of known BRRV isolates. Electron microscopy of thin sections revealed particles approximately 50 nm diameter within electron-dense inclusion bodies, characteristic of BRRSV (2) To our knowledge, this is the first report of BRRSV infection of highbush blueberry in Korea. Highbush blueberries are usually propagated by cutting, so BRRSV suspicious plants should be tested with PCR before they are propagated. References: (1) E. Kalinowska et al. Virus Genes. DOI 10.1007/s11262-011-0679-4, 2011. (2) K. S. Kim et al. Phytopathology 71:673, 1981. (3) M. Isogai et al. J. Gen. Plant Pathol. 75:140, 2009.

Living donor liver transplantation in Budd-Chiari syndrome: a single-center experience

Budd-Chiari syndrome (BCS), which is characterized by hepatic venous outflow obstruction due to occlusion of the major hepatic vein and/or the inferior vena cava (IVC), is rare. Traditionally, a caval resection is advocated for these patients; however, such a maneuver renders living donor liver transplantation (LDLT) impossible. We encountered BCS in 4/377 LDLT patients during a 5-year period (January 2003 to December 2007). This report examine the various surgical modifications in these 4 patients, who underwent to LDLT for BCS. Resection of right hepatic vein (RHV) with an adjacent fibrotic part of the IVC with direct anastomosis of the graft RHV to the IVC was performed in 2 patients. One patient underwent retrohepatic IVC excision and reconstruction with a cryopreserved autologous IVC graft. The fourth patient, with a preexisting mesoatrial shunt for BCS, underwent conversion of this to a RHV atrial shunt. Graft and patient survivals were 100%. There were few complications in either donors or recipients. LDLT for BCS can be performed safely with adequate venous drainage techniques and with anticoagulant therapy and good follow-up for early diagnosis and treatment of recurrence leading to excellent long-term results.

Occurrence of Poinsettia Stem Flat Disease Caused by Phytoplasma in Korea

In December 2009, commercially grown poinsettia (Euphorbia pulcherrima Willd cv. Ichibang) exhibited typical phytoplasma-like symptoms in 95% of an affected field in Yongin, Korea (Gyeonggi Province). Symptoms consisted of flat stems and fascicles and an abnormal number of apexes resulting in a cockscomb form of stem and flower bud proliferation. Leaf narrowing with curling of bracts was also associated with the disease. Symptomatic poinsettia plants were not marketable. Poinsettias, cv. Ichibang, without symptoms were obtained from a breeding collection in a glasshouse of the National Institute of Horticultural and Herbal Science in Suwon (Gyeonggi Province). The presence of phytoplasmas in symptomatic and healthy-looking flowers and stems of cv. Ichibang was demonstrated by PCR analysis with primer pair R16mF2/R16mR1 (1), which amplifies phytoplasma 16S rDNA regions. PCR products (~1,427 bp), were obtained from both symptomatic and healthy-looking plants, sequenced, and registered under the GenBank Accession Nos. of GU461275 and GU461277, respectively. Symptomatic poinsettia and healthy poinsettia sequences had 99.6 and 100% identity with U.S. PoiBI isolate FJ376625, indicating poinsettia stem flat disease is caused by PoiBI. A branch-inducing factor in poinsettia has been known for several decades, but only since 1997 was this graft transmissible factor identified as a PoiBI phytoplasma (1), belonging to the peach X-disease phytoplasma group (16S rRNA III) subgroup 16SrIII-H (2). Normally, phytoplasmas are associated with host quality loss, but abnormally, infection in poinsettia generates a desirable, free-branching growth habit. In this study we found that PoiBI could be detrimental to the quality of poinsettia depending on the cultivar and agronomic practice. Poinsettia stem flat disease presumably occurred because of increased levels of phytoplasma caused by successive stem cutting for commercial use. To our knowledge, this is the first report of PoiBI phytoplasma that affected marketability of poinsettia in Korea. References: (1) I. M. Lee et al. Nature Biotech. 15:178, 1997. (2) I. M. Lee et al. Int. J. Syst. Bacteriol. 48:1153, 1998.

Development of functional human immune system with the transplantations of human fetal liver/thymus tissues and expanded hematopoietic stem cells in RAG2-/-gamma(c)-/- MICE

BACKGROUND

There is an increasing need for suitable animal models for the study of the human immune system and disease. The purpose of this study was to develop a practical in vivo model of human immune cell repopulation using ex vivo expanded human fetal liver-derived CD34(+) hematopoietic stem cells and subrenally coimplanted fetal liver/thymus tissues.

METHODS

Freshly isolated fetal liver-derived CD34(+) hematopoietic stem cells were frozen until injected and ex vivo expanded with various cytokines for 7 days. After fetal liver/thymus tissues were subrenally coimplanted into preirradiated Rag2(-/-)gamma(c)(-/-) mice, frozen and ex vivo expanded CD34(+) cells were injected intravenously. The peripheral blood of the mice was monitored for the detection of human cell engraftment using flow cytometry. Then we confirmed human T-cell function by in vitro function assays.

RESULTS

After fetal liver/thymus tissues were coimplanted into the irradiated Rag2(-/-)gamma(c)(-/-) mice, with frozen and ex vivo expanded CD34(+) hematopoietic stem cells, human cell engraftments were determined using hCD45 and multilineage markers. The cultured cells with the cytokine combination of stem cell factor, thrombopoietin, Flk2/Flk3 ligand (FL), and interleukin-3 showed stable and long-term engraftment compared to other combinations. The ex vivo expanded human fetal liver-derived CD34(+) hematopoietic stem cells, under our culture conditions, accomplished a large volume of expanded cells that were sustained, demonstrating self-renewal of the evaluated markers, which may have indicated long- term repopulation activity.

CONCLUSION

The results of this study demonstrated a practical mouse model of expanded human immune cells especially T cells in Rag2(-/-)gamma(c)(-/-) mice.

IVS10+12A>G polymorphism in hMSH2 gene associated with prognosis for patients with colorectal cancer

BACKGROUND

The polymorphisms in DNA repair genes may contribute to a variation in the DNA repair capacity, thereby affecting the risk of carcinogenesis and prognosis of colorectal cancer. Accordingly, the present study analyzed 14 polymorphisms in DNA repair genes and their impact on the prognosis for patients with colorectal cancer.

MATERIALS AND METHODS

Three hundred and ninety-seven consecutive patients with curatively resected colorectal adenocarcinoma were enrolled in the present study. The genomic DNA was extracted from fresh colorectal tissue and 14 polymorphisms of DNA repair genes determined using a real-time PCR genotyping assay.

RESULTS

The median age of the patients was 63 years, and 218 (54.9%) patients had colon cancer, while 179 (45.1%) patients had rectal cancer. A multivariate survival analysis, including age, differentiation, carcinoembryonic antigen level, and stage, revealed a better survival for the patients with the combined IVS10+12AG and GG genotype than for the patients with the IVS10+12AA genotype [disease-free survival: hazard ratio (HR) 0.47, 95% confidence interval (CI) 0.30-0.75, P = 0.002; overall survival: HR 0.50, 95% CI 0.26-0.98, P = 0.042]. None of the other polymorphisms was associated with survival.

CONCLUSION

The IVS10+12A>G polymorphism in the hMSH2 gene was found to be an independent prognostic marker for patients with colorectal cancer.

Real-time PCR assay compared with antigenemia assay for detecting cytomegalovirus infection in kidney transplant recipients

Human cytomegalovirus (CMV) infection is a major cause of morbidity and mortality among kidney transplant recipients. The CMVpp65 antigenemia assay has been used for preemptive therapy. Real-time polymerase chain reaction (PCR) technology for CMV DNA quantification in blood has demonstrated a good correlation with the currently employed CMV antigenemia assay. In this study, 90 renal transplant recipients were prospectively enrolled from July 2004 and May 2005. Monitoring of CMV infection was routinely performed with CMV antigenemia and real-time PCR assays. Real-time plasma PCR and CMV antigenemia assays were assessed on 797 samples. CMV antigenemia correlated with a positive CMV PCR (chi(2) = 78.05; P < .0001). Not only the positive rate but also the number of positive cells correlated with the number of PCR DNA copies (F = 26.07, r(2) = .25, P < .0001). To define an optimal cutoff value of CMV DNA load to initiate treatment in kidney transplant patients, we considered a CMV antigenemia titer of >50 positive cells per 400,000 leukocytes as the gold standard in our previous study. The optimal cutoff value for the quantitative real-time PCR assay was predicted to be 86 copies/microL. Thus, we observed that CMV real-time PCR assay would not completely replace antigenemia assay in kidney transplant recipients, but can be used complementarily to screen antigenemia and monitor preemptive therapy.

Early Postoperative Renal Dysfunction in the Adult Living Donor Liver Transplantation

Living donor liver transplantation (LDLT) is a widely accepted treatment for end-stage liver diseases. Renal dysfunction, a frequent complication after liver transplantation, has an unfavorable effect on the prognosis. Despite special characteristics of LDLT, such as small-for-size graft syndrome (SFS), the relations between graft size and postoperative renal dysfunction have not been evaluated. So we described the relevance of previously known risk factors with SFS (graft-recipient body weight ratio [GRWR] < 0.8%) and early postoperative renal dysfunction in LDLT. The study population consisted of adults who received LDLT from May 1996 to November 2005. The 284 patients who were followed to 3 months after LDLT were classified as group I (n = 201, creatinine < 1.5 mg/dL) versus group II (n = 83, creatinine > or = 1.5 mg/dL). Univariate analysis showed renal dysfunction in the early postoperative period was related to preoperative total bilirubin, blood urea nitrogen, creatinine, prothrombin time level, model for end-stage liver disease (MELD) score, GRWR, presence of preoperative renal dysfunction, transfusion of packed red blood cell, fresh frozen plasma, cryoprecipitate, reoperation, and the need for renal replacement therapy (RRT). Upon multivariate analysis, MELD score, GRWR, preoperative renal dysfunction, and need for RRT were related to early postoperative renal dysfunction. In conclusion, there was a significant relationship between SFS (GRWR < 0.8) and early postoperative renal dysfunction.