Narrow Results

Over the past few years, several approaches have been proposed to assist in the early diagnosis of Alzheimer’s disease (AD) and its prodromal stage of mild cognitive impairment (MCI). Using multimodal biomarkers for this high-dimensional classification problem, the widely used algorithms include Support Vector Machines (SVM), Sparse Representation-based classification (SRC), Deep Belief Networks (DBN) and Random Forest (RF). These widely used algorithms continue to yield unsatisfactory performance for delineating the MCI participants from the cognitively normal control (CN) group. A novel Gaussian discriminant analysis-based algorithm is thus introduced to achieve a more effective and accurate classification performance than the aforementioned state-of-the-art algorithms. This study makes use of magnetic resonance imaging (MRI) data uniquely as input to two separate high-dimensional decision spaces that reflect the structural measures of the two brain hemispheres. The data used include 190 CN, 305 MCI and 133 AD subjects as part of the AD Big Data DREAM Challenge #1. Using 80% data for a 10-fold cross-validation, the proposed algorithm achieved an average F1 score of 95.89% and an accuracy of 96.54% for discriminating AD from CN; and more importantly, an average F1 score of 92.08% and an accuracy of 90.26% for discriminating MCI from CN. Then, a true test was implemented on the remaining 20% held-out test data. For discriminating MCI from CN, an accuracy of 80.61%, a sensitivity of 81.97% and a specificity of 78.38% were obtained. These results show significant improvement over existing algorithms for discriminating the subtle differences between MCI participants and the CN group.

This paper proposes to model protein regulation networks associated with severe acute respiratory syndrome (SARS) for early prediction of SARS. In the approach, specific to a patient group, a regulatory network is simulated using a fully-connected neural network and is optimized towards minimizing a novel energy function that is defined as a measure of disagreement between the input and output of the network. The nonlinear version of the network is achieved by applying a sigmoid function. Experimental results show that the proposed approaches can capture regulatory patterns associated with SARS and efficiently implement early prediction of SARS.

The medical field has been revolutionized by the medical imaging system, which plays a key role in providing information on the early life-saving detection of dreadful diseases. Diabetic retinopathy is a chronic visual disease that is the primary reason for the vision loss in most of the patients, who left undiagnosed at the initial stage. As the count of the diabetic retinopathy affected people kept on increasing, there is a necessity to have an automated detection method. The accuracy of the diagnosis of the automatic detection model is related to image acquisition as well as image interpretation. In contrast to this, the analysis of medical images by using computerized models is still a limited task. Thus, different kinds of detection methods are being developed for early detection of diabetic retinopathy. Accordingly, this paper focuses on the various literature analyses on different detection algorithms and techniques for diagnosing diabetic retinopathy. Here, it reviews several research papers and exhibits the significance of each detection method. This review deals with the analysis on the segmentation as well as classification algorithms that are included in each of the researches. Besides, the adopted environment, database collection and the tool for each of the research are portrayed. It provides the details of the performance analysis of the various diabetic detection models and reveals the best value in the case of each performance measure. Finally, it widens the research issues that can be accomplished by future researchers in the detection of diabetic retinopathy.

Reducing the costs and improving the quality of treatment in hospital systems as well as demands for better treatment from patients in order to keep them away from readmissions are two main issues healthcare systems have faced. In order to solve such challenges, predicting the occurrence of re-hospitalisation with data mining techniques would be so worthwhile. In this study, we are seeking to predict the occurrence of re-hospitalisation of the heart failure patients in two time-horizons (1-month and 3-month) via deployment of classification algorithms (i.e. decision trees, artificial neural networks, support vector machines and logistic regression). Two criterions (as main criterions) such as AUC (area under curve) and ACC (accuracy) have been calculated and assessed for classifying the prediction-power of the models in each time-horizon (outcome/target). We also have calculated some other criterions such as recall, precision and F1-Score. Then, we identified the importance and contribution of the variables for each outcome. Therefore, the variables whose contribution/importance changes over time are differentiated. It is noteworthy to say that this study is done under the scrutiny of an expert cardiologist. Trained nurses and expert cardiologist monitored the dataset every day, which was a hard and valuable measure to conduct. Finally, the dataset does not have missing values and noises. This research can be the basis for prospective medical studies and projects.