Search

Dual-energy X-ray absorptiometry (DXA) has been traditionally used to assess body composition covering bone, fat and muscle content. Cardiovascular disease (CVD) has deleterious effects on bone health and fat composition. Therefore, early detection of bone health, fat and muscle composition would help to anticipate a proper diagnosis and treatment plan for CVD patients. In this study, we leveraged machine learning (ML)-based models to predict CVD using DXA, demonstrating that it can be considered an innovative approach for early detection of CVD. We leveraged state-of-the-art ML models to classify the CVD group from non-CVD group. The proposed logistic regression-based model achieved nearly 80% accuracy. Overall, the bone mineral density, fat content, muscle mass and bone surface area measurements were elevated in the CVD group compared to non-CVD group. Ablation study revealed a more successful discriminatory power of fat content and bone mineral density than muscle mass and bone areas. To the best of our knowledge, this work is the first ML model to reveal the association between DXA measurements and CVD in the Qatari population. We believe this study will open new avenues of introducing DXA in creating the diagnosis and treatment plan of cardiovascular diseases.

Cardiovascular diseases (CVDs) trigger a high number of deaths across the world. In this study, we investigate the food, drinking, smoking, and lifestyle-related habits for a Qatari CVD cohort to understand the implication of these factors on CVD. Statistical analysis shows that the CVD group is consuming a lower amount of fast foods, soft drinks, snacks, and meats compared to the control group. Alarmingly, the level of smoking is still higher in the CVD group, and the consumption level of healthy items (e.g., cereal, cornflakes) in breakfast is relatively lower compared to the control group. Interestingly, the CVD cohort is spending more time walking and avoiding heavy sports, compared to the control group, but their involvement in moderate physical activities is lower than the control group. Overall, we conclude that the Qatari CVD cohort is following most of the standard guidelines related to food items and heavy sports; however, the cohort should reduce smoking habits, and may modify the moderate level of physical activity based on physician guidelines.

In this study, we analyze the food and lifestyle-related factors for a Diabetic cohort from Qatar, where the prevalence of diabetes is among the top in the Middle East region. Statistical analysis shows that the diabetic group is consuming a lower amount of fast foods, soft drinks and meats as a meal but a higher amount of vegetables and fruits compared to the control group. Though the diabetic cohort consumes a lower number of snacks and desserts, they consume a higher amount of sugar for tea. Interestingly, we find the diabetes cohort is spending a lower amount of time in sedentary life but their involvement in different physical activities is lower than the control group. Overall, we conclude that the Qatari diabetic cohort, considered in this study, is following standard guidelines for food and drinks but they may need to improve the physical activity level following physician guidelines.

BACKGROUND Novel coronavirus disease 2019 (COVID-19) is taking a huge toll on public health. Along with the non-therapeutic preventive measurements, scientific efforts are currently focused, mainly, on the development of vaccines and pharmacological treatment with existing drugs. Summarizing evidences from scientific literatures on the discovery of treatment plan of COVID-19 under a platform would help the scientific community to explore the opportunities in a systematic fashion. OBJECTIVE The aim of this study is to explore the potential drugs and biomedical entities related to coronavirus related diseases, including COVID-19, that are mentioned on scientific literature through an automated computational approach. METHODS We mined the information from publicly available scientific literature and related public resources. Six topic-specific dictionaries, including human genes, human miRNAs, diseases, Protein Databank, drugs, and drug side effects, were integrated to mine all scientific evidence related to COVID-19. We employed an automated literature mining and labeling system through a novel approach to measure the effectiveness of drugs against diseases based on natural language processing, sentiment analysis, and deep learning. We also applied the concept of cosine similarity to confidently infer the associations between diseases and genes. RESULTS Based on the literature mining, we identified 1805 diseases, 2454 drugs, 1910 genes that are related to coronavirus related diseases including COVID-19. Integrating the extracted information, we developed the first knowledgebase platform dedicated to COVID-19, which highlights potential list of drugs and related biomedical entities. For COVID-19, we highlighted multiple case studies on existing drugs along with a confidence score for their applicability in the treatment plan. Based on our computational method, we found Remdesivir, Statins, Dexamethasone, and Ivermectin could be considered as potential effective drugs to improve clinical status and lower mortality in patients hospitalized with COVID-19. We also found that Hydroxychloroquine could not be considered as an effective drug for COVID-19. The resulting knowledgebase is made available as an open source tool, named COVID-19Base. CONCLUSIONS Proper investigation of the mined biomedical entities along with the identified interactions among those would help the research community to discover possible ways for the therapeutic treatment of COVID-19.

Over the past decades, Ionic liquids (ILs) have gained considerable attention from the scientific community in reason of their versatility and performance in many fields. However, they nowadays remain mainly for laboratory scale use. The main barrier hampering their use in a larger scale is their questionable ecological toxicity. This study investigated the effect of hydrophobic and hydrophilic cyclic cation-based ILs against four pathogenic bacteria that infect humans. For that, cations, either of aromatic character (imidazolium or pyridinium) or of non-aromatic nature, (pyrrolidinium or piperidinium), were selected with different alkyl chain lengths and combined with both hydrophilic and hydrophobic anionic moieties. The results clearly demonstrated that introducing of hydrophobic anion namely bis((trifluoromethyl)sulfonyl)amide, [NTF2] and the elongation of the cations substitutions dramatically affect ILs toxicity behaviour. The established toxicity data [50% effective concentration (EC50)] along with similar endpoint collected from previous work against Aeromonas hydrophila were combined to developed quantitative structure-activity relationship (QSAR) model for toxicity prediction. The model was developed and validated in the light of Organization for Economic Co-operation and Development (OECD) guidelines strategy, producing good correlation coefficient R2 of 0.904 and small mean square error (MSE) of 0.095. The reliability of the QSAR model was further determined using k-fold cross validation.

Background Novel coronavirus disease 2019 (COVID-19) is taking a huge toll on public health. Along with the non-therapeutic preventive measurements, scientific efforts are currently focused, mainly, on the development of vaccines and pharmacological treatment with existing drugs. Summarizing evidences from scientific literatures on the discovery of treatment plan of COVID-19 under a platform would help the scientific community to explore the opportunities in a systematic fashion. Objective The aim of this study is to explore the potential drugs and biomedical entities related to coronavirus related diseases, including COVID-19, that are mentioned on scientific literature through an automated computational approach. Methods We mined the information from publicly available scientific literature and related public resources. Six topic-specific dictionaries, including human genes, human miRNAs, diseases, Protein Databank, drugs, and drug side effects, were integrated to mine all scientific evidence related to COVID-19. We employed an automated literature mining and labeling system through a novel approach to measure the effectiveness of drugs against diseases based on natural language processing, sentiment analysis, and deep learning. We also applied the concept of cosine similarity to confidently infer the associations between diseases and genes. Results Based on the literature mining, we identified 1805 diseases, 2454 drugs, 1910 genes that are related to coronavirus related diseases including COVID-19. Integrating the extracted information, we developed the first knowledgebase platform dedicated to COVID-19, which highlights potential list of drugs and related biomedical entities. For COVID-19, we highlighted multiple case studies on existing drugs along with a confidence score for their applicability in the treatment plan. Based on our computational method, we found Remdesivir, Statins, Dexamethasone, and Ivermectin could be considered as potential effective drugs to improve clinical status and lower mortality in patients hospitalized with COVID-19. We also found that Hydroxychloroquine could not be considered as an effective drug for COVID-19. The resulting knowledgebase is made available as an open source tool, named COVID-19Base. Conclusions Proper investigation of the mined biomedical entities along with the identified interactions among those would help the research community to discover possible ways for the therapeutic treatment of COVID-19.

In Malaysia, as it is the case in many other countries, the population of the elderly is increasing, and as they age, unfortunately, many suffer of chronic diseases. Smart homes can enable continuous and remote monitoring of elderly health and wellbeing at a low cost. The technologies will allow the elderly to stay in their home instead of expensive and limited healthcare facilities. In smart home settings, video and camera are usually used to monitor. In this paper, we present a progress on smart home system to detect pain through the analysis of facial expressions using camera or video. The system uses deep learning techniques and is developed to work with portable devices. Preliminary result shows an accuracy of 93% in detecting pain on a standard facial dataset.

With the advancement of cyber technologies, currently many applications are run on the cyberspace which make our life easier. Since it is an open space, we need tools to ensure the security. Authentication provides a mean to verify authenticity of an entity against illegal access to a device or an application in cyberspace. Recent smartphones have already equipped with biometrics system (fingerprint and face recognition) which can be used for authentication. Iris recognition is identified as the most reliable biometrics traits. It however needs a substantial computing power. In this paper, we develop an iris recognition algorithm based on Fisher algorithm which can be run in a lighter computing platform. Experiments conducted with CASIA database shows exciting results where the system achieves a very high accuracy.

Breast cancer has become a significant health problem worldwide as it is considered one of the primary causes for deaths amongst females. In order to prevent the increase of deaths caused by breast cancer, early diagnosis through computer aided diagnosis systems has been very effective. This paper introduces a computer aided system for detecting and classifying suspicious regions in digital mammograms. The system starts by extracting regions of interest that are suspicious of containing cancerous cells. Then, all these regions are classified to check whether they are normal or abnormal. For the detection phase, template matching techniques are utilized. As for the classification phase, a 3-step process is applied which enclose feature extraction with wavelet transform, feature selection with statistical techniques and classification with clustering K-Nearest Neighbor classifier. A preliminary result shows a 97.73 % accuracy rate.

This paper presents a computer aided diagnosis for lung nodules in CT images. The system consists of feature extraction, feature selection and classification. A two-step feature selection process is introduced to reduce the number of coefficients produced in the feature extraction step. This helps in enhancing the classification performance as it removes unneeded and redundant information. The classification rate of the system reached 98.10 % with minimum false negatives and zero false positives.

Cancer is a leading cause of death worldwide. Lung cancer is a type of cancer that is considered as one of the most leading causes of death globally. In Malaysia, it is the 3rd common cancer type and the 2nd type of cancer among men. In this paper, machine learning techniques have been utilized to develop a computer-aided diagnosis system for lung cancer. The system consists of feature extraction phase, feature selection phase and classification phase. For feature extraction/selection, different wavelets functions have been applied in order to find the one that produced the highest accuracy. Clustering-K-nearest-neighbor algorithm has been developed/utilized for classification. Japanese Society of Radiological Technology's standard dataset of lung cancer has been used to test the system. The data set has 154 nodule regions (abnormal) and 92 non-nodule regions (normal). Accuracy levels of over 96% for classification have been achieved which demonstrate the merits of the proposed approach. 2012 IEEE. Scopus

Medical diagnosis is one of the most important issues in healthcare. Computer aided systems have been developed in order to diagnose diseases by examining the internal human organs through medical images captured by MRI, CT scan etc. Many techniques have been utilized in order to develop these systems. In this paper, a short review on artificial neural network, fuzzy logic and genetic algorithm techniques in medical diagnostic applications is presented. The purpose of this review is to select the most suitable soft computing methodology to build a disease diagnosis system with high capabilities. The combination of artificial neural network, fuzzy logic and genetic algorithm in one methodology was reported to have a great advantage in producing systems with better performance.

Disease diagnosis often involves acquiring medical images using devices such as MRI, CT scan, x-ray, or mammograms of patients' organs. Though many medical diagnostic applications have been proposed; finding subtle cancerous cells is still an issue because they are very difficult to be identified. This paper presents an architecture that utilizes a learning algorithm, and uses soft computing to build a medical knowledge base and an inference engine for classifying new images. This system is built on the strength of artificial neural networks, fuzzy logic, and genetic algorithms. These machine intelligence are combined in a complementary approach to overcome the weakness of each other. Moreover, the system also uses Wavelet Transform and Principal Component Analysis for pre-processing and feature to produce features to be used as input to the learning algorithm. 2011 Springer-Verlag. Scopus

This paper describes an approach to overcome a situation of monitoring and managing a parking area using a vision based automated parking system. With the rapid increase of cars the need to find available parking space in the most efficient manner, to avoid traffic congestion in a parking area, is becoming a necessity in car park management. Current car park management is dependent on either human personnel keeping track of the available car park spaces or a sensor based system that monitors the availability of each car park space or the overall number of available car park spaces. In both situations, the information available was only the total number of car park spaces available and not the actual location available. In addition, the installation and maintenance cost of a sensor based system is dependent on the number of sensors used in a car park. This paper shows a vision based system that is able to detect and indicate the available parking spaces in a car park. The methods utilized to detect available car park spaces were based on coordinates to indicate the regions of interest and a car classifier. This paper shows that the initial work done here has an accuracy that ranges from 90% to 100% for a 4 space car park. The work done indicated that the application of a vision based car park management system would be able to detect and indicate the available car park spaces

This paper investigates the combination of multiresolution methods for feature extraction for lung cancer. The focus is on the impact of combining wavelet and curvelet on the accuracy of the disease diagnosis. The paper investigates feature extraction with two different levels of wavelet, two different wavelet functions and the combination of wavelet and curvelet to obtain a high classification rate. The findings suggest the potential of combining different multiresolution methods in achieving high accuracy rates.

In biological studies, species identification is considered one of the most important issues. Several methods have been suggested to identify species using the whole DNA sequences. In this study, we present new insights for species identification using only part of the DNA sequence. The Clustering k-Nearest Neighbor (K-C-NN) and Support Vector Machine (SVM) classifiers were used to test and evaluate the improved statistical features extracted from DNA sequences for four species (Aquifex aeolicus, Bacillus subtilis, Aeropyrum pernix and Buchnera sp). The results show that part of DNA sequences can be used to identify species.