• A novel framework for heart disease detection is proposed. • Handling categorical attributes based on its importance in health care and outcome. • Covariance-based multivariate outlier detection is used for the outlier detection. • Proposed Entropy-based FE (EFE) has performed well with ML models. • The proposed ML pipeline outperformed the state of art works. Machine Learning (ML) in the healthcare industry has newly made headlines. Several ML models developed in the state of the art frameworks with different databases. However, improvements are still required in terms of performance to bring the robustness of the ML models in accurate prediction of heart diseases. The main impetus of the work is to propose a new ML pipeline for accurate prediction of heart disease. It includes pre-processing and entropy based feature engineering (FE) approach to produce high quality features to provide better model performance. The heart disease dataset is curated by combining Cleveland, V A medical center, Hungarian and Switzerland databases over 14 common attributes. Imputing missing values (IMV) and Outliers are removed (OR) based on the relation exist between healthcare attributes and Mahalanobis distance respectively in the curated heart disease dataset (HDD). Experimental results revealed that the IMV + OR pre-processing dominates with better performance than other pre-processing methods applied for model evaluation. Analyses were carried out with different ML models where HDD is subjected to IMV + OR processing with Independent Component Analysis (ICA), Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and entropy based FE (proposed). Employing proposed entropy based FE with IMV + OR pre-processing has shown remarkable improvement in respect of all metrics for NB and LR classifiers. Further, experimental results shown that the ensemble model (LR + NB) performed well under proposed pipeline, with AUC (96.8%), Accuracy (92.7%), Specificity (91.5%), Precision (92.5%) and F1 Score (0.931) which outperformed the state of the art results. 

Heart disease prediction using entropy based feature engineering and ensembling of machine learning classifiers

Satisfiability is prominent in the field of computer science and mathematics because SAT provides an alternative to represent the knowledge of any datasets. Fueled by this nature, recent paradigm tends to converge towards modelling Artificial Neural Network (ANN) through SAT. Despite extensive implementation of SAT in ANN, there are severely limited strategy to control the distribution of negative and positive literals in the logical rule. One of the most feasible approaches in controlling the behavior of the literal is by employing probabilistic behavior to each neuron in the ANN. In this paper, a novel logical rule namely Probabilistic 2 Satisfiability was proposed by implementing the probability to each variable in the 2 Satisfiability clause. In this context, the negativity of each variable will be determined using the probability which leads to higher search space. The proposed Probabilistic 2 Satisfiability was implemented into the special single layered Discrete Hopfield Neural Network where the cost function of each variable was derived by minimizing the inconsistency of the logic. The behavior of the proposed Probabilistic 2 Satisfiability was assessed based on various performance metrics including several newly introduced metrics. According to the experimental results, the proposed model has a probability of at least 81.8% in outperforming the existing method. Interestingly, the proposed model was reported to have the largest solution space when the ratio of positive was within [0.1, 0.4]. The comparison of experimental results with other state of the art logical rule demonstrates that the proposed model is promising in retrieving global neuron state. 

PRO2SAT: Systematic Probabilistic Satisfiability logic in Discrete Hopfield Neural Network

The notable progress in single-cell RNA sequencing (ScRNA-seq) technology is beneficial to accurately discover the heterogeneity and diversity of cells. Clustering is an extremely important step during the ScRNA-seq data analysis. However, it cannot achieve satisfactory performances by directly clustering ScRNA-seq data due to its high dimensionality and noise. To address these issues, we propose a novel ScRNA-seq data representation model, termed Robust Graph regularized Non-Negative Matrix Factorization with Dissimilarity and Similarity constraints (RGNMF-DS), for ScRNA-seq data clustering. To accurately characterize the structure information of the labeled samples and the unlabeled samples, respectively, the proposed RGNMF-DS model adopts a couple of complementary regularizers (i.e., similarity and dissimilar regularizers) to guide matrix decomposition. In addition, we construct a graph regularizer to discover the local geometric structure hidden in ScRNA-seq data. Moreover, we adopt the l2,1-norm to measure the reconstruction error and thereby effectively improve the robustness of the proposed RGNMF-DS model to the noises. Experimental results on several ScRNA-seq datasets have demonstrated that our proposed RGNMF-DS model outperforms other state-of-the-art competitors in clustering.

Robust Graph Regularized NMF with Dissimilarity and Similarity Constraints for ScRNA-seq Data Clustering

Infrared image segmentation of the wind turbine blade is an important link of wind turbine condition monitoring. Nevertheless, there remain plenty of challenges when the traditional semantic segmentation networks are applied directly to the infrared image segmentation of wind turbine blade, including the blurred boundaries caused by similar thermal radiation of background and blade, the irregularity of edge identification caused by uneven heating, and the hub misidentified as blade. To address these issues, a semantic segmentation neural network based on the basic U-Net is improved for infrared image segmentation of the wind turbine blade. The hierarchical-split depthwise separable convolution block is integrated into the constructed network to have a higher segmentation accuracy. Also, the fusion of convolution layer and batch normalization layer is performed in inference to get a better speed–accuracy tradeoff. The experimental results show that the proposed approach outperforms all the comparing methods, which further demonstrates that the trained network can achieve superior runtime performance and accurate segmentation with excellent anti-interference performance.

An Improved U-Net Model for Infrared Image Segmentation of Wind Turbine Blade

Recently, a variety of non-systematic satisfiability studies on Discrete Hopfield Neural Networks have been introduced to overcome a lack of interpretation. Although a flexible structure was established to assist in the generation of a wide range of spatial solutions that converge on global minima, the fundamental problem is that the existing logic completely ignores the probability dataset’s distribution and features, as well as the literal status distribution. Thus, this study considers a new type of non-systematic logic termed S-type Random k Satisfiability, which employs a creative layer of a Discrete Hopfield Neural Network, and which plays a significant role in the identification of the prevailing attribute likelihood of a binomial distribution dataset. The goal of the probability logic phase is to establish the logical structure and assign negative literals based on two given statistical parameters. The performance of the proposed logic structure was investigated using the comparison of a proposed metric to current state-of-the-art logical rules; consequently, was found that the models have a high value in two parameters that efficiently introduce a logical structure in the probability logic phase. Additionally, by implementing a Discrete Hopfield Neural Network, it has been observed that the cost function experiences a reduction. A new form of synaptic weight assessment via statistical methods was applied to investigate the effect of the two proposed parameters in the logic structure. Overall, the investigation demonstrated that controlling the two proposed parameters has a good effect on synaptic weight management and the generation of global minima solutions.

/pdf/s-type-random-k-satisfiability-logic-in-discrete-hopfield-204suqmb.pdf

S-Type Random k Satisfiability Logic in Discrete Hopfield Neural Network Using Probability Distribution: Performance Optimization and Analysis

Diabetic retinopathy (DR) is one of the major complications caused by diabetes and can lead to severe vision loss or even complete blindness if not diagnosed and treated in a timely manner. In this paper, a new feature map global channel attention mechanism (GCA) is proposed to solve the problem of the early detection of DR. In the GCA module, an adaptive one-dimensional convolution kernel size algorithm based on the dimension of the feature map is proposed and a deep convolutional neural network model for DR color medical image severity diagnosis named GCA-EfficientNet (GENet) is designed. The training process uses transfer learning techniques with a cosine annealing learning rate adjustment strategy. The image regions of interest of GENet are visualized using a heat map. The final accuracy, precision, sensitivity and specificity of the DR dataset of the Kaggle competition reached 0.956, 0.956, 0.956, and 0.989, respectively. A large number of experiment results show that GENet based on the GCA attention mechanism can more effectively extract lesion features and classify the severity of DR.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09664550.pdf

Classification of Diabetic Retinopathy Severity Based on GCA Attention Mechanism

• Developed a novel neural network for CVD mortality prediction with clinical data. • Proposed a more time-efficient feature-based artificial neural network (ANN). • Investigated feature representation to improve ANN for practical guideline. • Boosted calibration of neural networks and enabled model to make less mistakes. • Made model updates in clinical context more accessible, flexible and reliable. Cardiovascular (CVD) is the leading cause of death worldwide and a significant public health concern. Therefore, its mortality prediction is crucial to many existing treatment guidelines. Medical claims data can be used to accurately foresee the health outcomes of patients contracting to a variety of diseases. Many machine learning algorithms, especially deep learning artificial neural networks, can predict mortality rate among patients with CVD using clinical data. Calibration of probabilistic prediction is essential for precise medical interventions as it indicates how well a model’s output matches the probability of the event. However, deep learning neural networks are poorly calibrated. Through experiments, we observe that feature representation is an important factor influencing calibration. This paper proposes a novel feature-based deep learning neural network framework to predict the mortality rate among patients with CVD. Our focus is to present a comprehensive study to achieve advanced performance calibration of mortality prediction on CVD in leveraging deep learning architecture and feature representations. Our study demonstrates that the proposed feature-based neural network framework integrated with Principal Component Analysis or Autoencoders significantly reduces training time and boosts calibration, making model updates in clinical context more flexible and decision-making in medical prevention more reliable. 

Advanced calibration of mortality prediction on cardiovascular disease using feature-based artificial neural network

Background Predicting reduced health-related quality of life (HRQoL) after resection of a benign or low-grade brain tumour provides the opportunity for early intervention, and targeted expenditure of scarce supportive care resources. We aimed to develop, and evaluate the performance of, machine learning (ML) algorithms to predict HRQoL outcomes in this patient group. Methods Using a large prospective dataset of HRQoL outcomes in patients surgically treated for low grade glioma, acoustic neuroma and meningioma, we investigated the capability of ML to predict a) HRQoL-impacting symptoms persisting between 12 and 60 months from tumour resection and b) a decline in global HRQoL by more than the minimum clinically important difference below a normative population mean within 12 and 60 months after resection. Ten-fold cross-validation was used to measure the area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (PR-AUC), sensitivity, and specificity of models. Six ML algorithms were explored per outcome: Random Forest Classifier, Decision Tree Classifier, Logistic Regression, K Neighbours Classifier, Support Vector Machine, and Gradient Boosting Machine. Results The final cohort included 262 patients. Outcome measures for which AUC>0.9 were Appetite loss, Constipation, Nausea and vomiting, Diarrhoea, Dyspnoea and Fatigue. AUC was between 0.8 and 0.9 for global HRQoL and Financial difficulty. Pain and Insomnia achieved AUCs below 0.8. PR-AUCs were similar overall to the AUC of each respective classifier. Conclusions ML algorithms based on routine demographic and perioperative data show promise in their ability to predict HRQoL outcomes in patients with low grade and benign brain tumours between 12 and 60 months after surgery.

/pdf/using-machine-learning-to-predict-health-related-quality-of-28z1msf5.pdf

Using machine learning to predict health-related quality of life outcomes in patients with low grade glioma, meningioma, and acoustic neuroma

The application of fruitful achievement of single-cell RNA-sequencing (scRNA-seq) technology has generated huge amount of gene transcriptome data. It has provided a whole new perspective to analyze the transcriptome at single-cell level. Cluster analysis of scRNA-seq is an efficient approach to reveal unknown heterogeneity and functional diversity of cell populations, which could further assist researchers to explore pathogenesis and biomarkers of diseases. In this paper, we propose a new cluster method (DSINMF) based on deep matrix factorization to detect cell type in the scRNA-seq data. In our method, the feature selection is used to reduce redundant features. Then, the imputation method is utilized to impute dropout events. Further, the dimension reduction is utilized to reduce the impact of noise. Finally, the deep matrix factorization with bi-stochastic graph regularization is employed to cluster scRNA-seq data. To evaluate the performance of DSINMF, eight datasets are used as test sets in the experiment. The experimental results show DSINMF outperformances than other state-of-the-art methods in clustering performance.

Detecting cell type from single cell RNA sequencing based on deep bi-stochastic graph regularized matrix factorization

Accumulating evidences demonstrate that circular RNA (circRNA) plays an important role in human diseases. Identification of circRNA-disease associations can help for the diagnosis of human diseases, while the traditional method based on biological experiments is time-consuming. In order to address the limitation, a series of computational methods have been proposed in recent years. However, few works have summarized these methods or compared the performance of them. In this paper, we divided the existing methods into three categories: information propagation, traditional machine learning and deep learning. Then, the baseline methods in each category are introduced in detail. Further, 5 different datasets are collected, and 14 representative methods of each category are selected and compared in the 5-fold, 10-fold cross-validation and the de novo experiment. In order to further evaluate the effectiveness of these methods, six common cancers are selected to compare the number of correctly identified circRNA-disease associations in the top-10, top-20, top-50, top-100 and top-200. In addition, according to the results, the observation about the robustness and the character of these methods are concluded. Finally, the future directions and challenges are discussed.

Yi-Ping Phoebe Chen

Papers

Classification of Diabetic Retinopathy Severity Based on GCA Attention Mechanism

Advanced calibration of mortality prediction on cardiovascular disease using feature-based artificial neural network

Using machine learning to predict health-related quality of life outcomes in patients with low grade glioma, meningioma, and acoustic neuroma

Detecting cell type from single cell RNA sequencing based on deep bi-stochastic graph regularized matrix factorization

Benchmarking of computational methods for predicting circRNA-disease associations