ECG-based cardiac arrhythmias detection through ensemble learning and fusion of deep spatial-temporal and long-range dependency features.

Cardiac arrhythmia is one of the prime reasons for death globally. Early diagnosis of heart arrhythmia is crucial to provide timely medical treatment. Heart arrhythmias are diagnosed by analyzing the electrocardiogram (ECG) of patients. Manual analysis of ECG is time-consuming and challenging. Hence, effective automated detection of heart arrhythmias is important to produce reliable results. Different deep-learning techniques to detect heart arrhythmias such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Transformer, and Hybrid CNN-LSTM were proposed. However, these techniques, when used individually, are not sufficient to effectively learn multiple features from the ECG signal. The fusion of CNN and LSTM overcomes the limitations of CNN in the existing studies as CNN-LSTM hybrids can extract spatiotemporal features. However, LSTMs suffer from long-range dependency issues due to which certain features may be ignored. Hence, to compensate for the drawbacks of the existing models, this paper proposes a more comprehensive feature fusion technique by merging CNN, LSTM, and Transformer models. The fusion of these models facilitates learning spatial, temporal, and long-range dependency features, hence, helping to capture different attributes of the ECG signal. These features are subsequently passed to a majority voting classifier equipped with three traditional base learners. The traditional learners are enriched with deep features instead of handcrafted features. Experiments are performed on the MIT-BIH arrhythmias database and the model performance is compared with that of the state-of-art models. Results reveal that the proposed model performs better than the existing models yielding an accuracy of 99.56%.

A novel few shot learning derived architecture for long-term HbA1c prediction.

Regular monitoring of glycated hemoglobin (HbA1c) levels is important for the proper management of diabetes. Studies demonstrated that lower levels of HbA1c play an essential role in reducing or delaying microvascular difficulties that arise from diabetes. In addition, there is an association between elevated HbA1c levels and the development of diabetes-related comorbidities. The advanced prediction of HbA1c enables patients and physicians to make changes to treatment plans and lifestyle to avoid elevated HbA1c levels, which can consequently lead to irreversible health complications. Despite the impact of such prediction capabilities, no work in the literature or industry has investigated the futuristic prediction of HbA1c using current blood glucose (BG) measurements. For the first time in the literature, this work proposes a novel FSL-derived algorithm for the long-term prediction of clinical HbA1c measures. More importantly, the study specifically targeted the pediatric Type-1 diabetic population, as an early prediction of elevated HbA1c levels could help avert severe life-threatening complications in these young children. Short-term CGM time-series data are processed using both novel image transformation approaches, as well as using conventional signal processing methods. The derived images are then fed into a convolutional neural network (CNN) adapted from a few-shot learning (FSL) model for feature extraction, and all the derived features are fused together. A novel normalized FSL-distance (FSLD) metric is proposed for accurately separating the features of different HbA1c levels. Finally, a K-nearest neighbor (KNN) model with majority voting is implemented for the final classification task. The proposed FSL-derived algorithm provides a prediction accuracy of 93.2%.

Estimating age and gender from electrocardiogram signals: A comprehensive review of the past decade.

Twelve lead electrocardiogram signals capture unique fingerprints about the body's biological processes and electrical activity of heart muscles. Machine learning and deep learning-based models can learn the embedded patterns in the electrocardiogram to estimate complex metrics such as age and gender that depend on multiple aspects of human physiology. ECG estimated age with respect to the chronological age reflects the overall well-being of the cardiovascular system, with significant positive deviations indicating an aged cardiovascular system and a higher likelihood of cardiovascular mortality. Several conventional, machine learning, and deep learning-based methods have been proposed to estimate age from electronic health records, health surveys, and ECG data. This manuscript comprehensively reviews the methodologies proposed for ECG-based age and gender estimation over the last decade. Specifically, the review highlights that elevated ECG age is associated with atherosclerotic cardiovascular disease, abnormal peripheral endothelial dysfunction, and high mortality, among many other cardiovascular disorders. Furthermore, the survey presents overarching observations and insights across methods for age and gender estimation. This paper also presents several essential methodological improvements and clinical applications of ECG-estimated age and gender to encourage further improvements of the state-of-the-art methodologies.

Unveiling the future of breast cancer assessment: a critical review on generative adversarial networks in elastography ultrasound.

Elastography Ultrasound provides elasticity information of the tissues, which is crucial for understanding the density and texture, allowing for the diagnosis of different medical conditions such as fibrosis and cancer. In the current medical imaging scenario, elastograms for B-mode Ultrasound are restricted to well-equipped hospitals, making the modality unavailable for pocket ultrasound. To highlight the recent progress in elastogram synthesis, this article performs a critical review of generative adversarial network (GAN) methodology for elastogram generation from B-mode Ultrasound images. Along with a brief overview of cutting-edge medical image synthesis, the article highlights the contribution of the GAN framework in light of its impact and thoroughly analyzes the results to validate whether the existing challenges have been effectively addressed. Specifically, This article highlights that GANs can successfully generate accurate elastograms for deep-seated breast tumors (without having artifacts) and improve diagnostic effectiveness for pocket US. Furthermore, the results of the GAN framework are thoroughly analyzed by considering the quantitative metrics, visual evaluations, and cancer diagnostic accuracy. Finally, essential unaddressed challenges that lie at the intersection of elastography and GANs are presented, and a few future directions are shared for the elastogram synthesis research.

Automatic detection of ictal activity in EEG using synchronization and chaos-based attributes.

Automatic seizure onset detectors (SODs) have been proposed to alert epileptic patients when a seizure is about to happen and in turn improve their quality of life. Yet, the detectors proposed in literature are complex and difficult to implement in real-time as they utilize large feature sets with redundant and irrelevant features. Hence, the aim of this work is to propose a simple and lightweight SOD that exploits two characteristics that reflect the neuronal behavior during a seizure. Namely, the synchronization between EEG channels and the chaoticity of the EEG; synchronization was measured by the condition number while the recurrence period density entropy estimated the chaoticity of an EEG signal. A support vector machine was trained and tested on 10 patients from a scalp EEG dataset and was able to detect the considered seizures with a sensitivity of 100% and a false positives rate of 0.5 per hour. The results indicate that synchronization and chaos attributes can reflect the manifestation of seizures in EEG data and can be used to develop SODs. This work emphasizes that even a single relevant feature can produce an SOD with comparable performance to SODs that use many features.

An Artificial Intelligence-Based Diagnostic System for Acute Lymphoblastic Leukemia Detection.

This study suggests a novel Acute Lymphoblastic Leukemia (ALL) diagnostic model, built solely on complete blood count (CBC) records. Using a dataset comprised of CBC records of 86 ALL and 86 control patients respectively, we identified the most ALL-specific parameters using a feature selection approach. Next, Grid Search-based hyperparameter tuning with a five-fold cross-validation scheme was adopted to build classifiers using Random Forest, XGBoost, and Decision Tree algorithms. A comparison between the performances of the three models demonstrates that Decision Tree classifier outperformed XGBoost and Random Forest algorithms in ALL detection using CBC-based records.

Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results.

The comprehensive epidemiology and global disease burdens reported recently suggest that chronic lymphocytic leukemia (CLL) constitutes 25-30% of leukemias thus being the most common leukemia subtype. However, there is an insufficient presence of artificial intelligence (AI)-based techniques for CLL diagnosis. The novelty of this study is in the investigation of data-driven techniques to leverage the intricate CLL-related immune dysfunctions reflected in routine complete blood count (CBC) alone. We used statistical inferences, four feature selection methods, and multistage hyperparameter tuning to build robust classifiers. With respective accuracies of 97.05%, 97.63%, and 98.62% for Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), and XGboost (XGb)-based models, CBC-driven AI methods promise timely medical care and improved patient outcome with lesser resource usage and related cost.

Parents of Children with Cleft Lip Exhibit Heightened Visual Attention to the Perioral Area.

Following high-quality surgical repair, children born with a cleft lip anomaly may still display lasting visual differences. We exposed control adults and parents of affected children to images of children with cleft deformity and compared their visual tracking patterns. The protocol investigated whether parental exposure to secondary cleft deformity heightens or diminishes visual attraction to this type of structural facial variation. Method: Twenty participants (10 control adults, 10 parents of affected children) assessed 40 colored images of children's faces while their eye movements were tracked. Twenty-four control images and 16 repaired cleft lip images were displayed to observers. Nine bilateral facial aesthetic zones were considered as regions of interest. Percentage of time visually fixating within each region, and statistical differences in fixation duration percentage between the two participant groups and across the bilateral regions of interest were analyzed. Results: While both groups of observers directed more visual attention to the nasal and oral regions of the cleft images than control images, parents of children with cleft lip spent significantly more time fixating on these areas (25% and 24% of the time, respectively) than did unaffected adults (14.6% and 19.3%; P < 0.001). Conclusions: These results demonstrate that parents of cleft lip children exhibit heightened attention to this type of facial difference relative to the naive observer. These findings highlight that observer profile can meaningfully influence the perception of a facial deformity. Awareness of this information may enhance communication between surgeon and parents of an affected child by providing added insight into parental perspective.

A Review of Artificial Intelligence Applications in Hematology Management: Current Practices and Future Prospects.

BACKGROUND: Machine learning (ML) and deep learning (DL) methods have recently garnered a great deal of attention in the field of cancer research by making a noticeable contribution to the growth of predictive medicine and modern oncological practices. Considerable focus has been particularly directed toward hematologic malignancies because of the complexity in detecting early symptoms. Many patients with blood cancer do not get properly diagnosed until their cancer has reached an advanced stage with limited treatment prospects. Hence, the state-of-the-art revolves around the latest artificial intelligence (AI) applications in hematology management. OBJECTIVE: This comprehensive review provides an in-depth analysis of the current AI practices in the field of hematology. Our objective is to explore the ML and DL applications in blood cancer research, with a special focus on the type of hematologic malignancies and the patient's cancer stage to determine future research directions in blood cancer. METHODS: We searched a set of recognized databases (Scopus, Springer, and Web of Science) using a selected number of keywords. We included studies written in English and published between 2015 and 2021. For each study, we identified the ML and DL techniques used and highlighted the performance of each model. RESULTS: Using the aforementioned inclusion criteria, the search resulted in 567 papers, of which 144 were selected for review. CONCLUSIONS: The current literature suggests that the application of AI in the field of hematology has generated impressive results in the screening, diagnosis, and treatment stages. Nevertheless, optimizing the patient's pathway to treatment requires a prior prediction of the malignancy based on the patient's symptoms or blood records, which is an area that has still not been properly investigated.

Face-Based Attention Recognition Model for Children with Autism Spectrum Disorder.

Attention recognition plays a vital role in providing learning support for children with autism spectrum disorders (ASD). The unobtrusiveness of face-tracking techniques makes it possible to build automatic systems to detect and classify attentional behaviors. However, constructing such systems is a challenging task due to the complexity of attentional behavior in ASD. This paper proposes a face-based attention recognition model using two methods. The first is based on geometric feature transformation using a support vector machine (SVM) classifier, and the second is based on the transformation of time-domain spatial features to 2D spatial images using a convolutional neural network (CNN) approach. We conducted an experimental study on different attentional tasks for 46 children (ASD n=20, typically developing children n=26) and explored the limits of the face-based attention recognition model for participant and task differences. Our results show that the geometric feature transformation using an SVM classifier outperforms the CNN approach. Also, attention detection is more generalizable within typically developing children than within ASD groups and within low-attention tasks than within high-attention tasks. This paper highlights the basis for future face-based attentional recognition for real-time learning and clinical attention interventions. Supplementary Information: The online version contains supplementary material available at 10.1007/s41666-021-00101-y.

Stress Classification Using Photoplethysmogram-Based Spatial and Frequency Domain Images.

Stress is subjective and is manifested differently from one person to another. Thus, the performance of generic classification models that classify stress status is crude. Building a person-specific model leads to a reliable classification, but it requires the collection of new data to train a new model for every individual and needs periodic upgrades because stress is dynamic. In this paper, a new binary classification (called stressed and non-stressed) approach is proposed for a subject's stress state in which the inter-beat intervals extracted from a photoplethysomogram (PPG) were transferred to spatial images and then to frequency domain images according to the number of consecutive. Then, the convolution neural network (CNN) was used to train and validate the classification accuracy of the person's stress state. Three types of classification models were built: person-specific models, generic classification models, and calibrated-generic classification models. The average classification accuracies achieved by person-specific models using spatial images and frequency domain images were 99.9%, 100%, and 99.8%, and 99.68%, 98.97%, and 96.4% for the training, validation, and test, respectively. By combining 20% of the samples collected from test subjects into the training data, the calibrated generic models' accuracy was improved and outperformed the generic performance across both the spatial and frequency domain images. The average classification accuracy of 99.6%, 99.9%, and 88.1%, and 99.2%, 97.4%, and 87.6% were obtained for the training set, validation set, and test set, respectively, using the calibrated generic classification-based method for the series of inter-beat interval (IBI) spatial and frequency domain images. The main contribution of this study is the use of the frequency domain images that are generated from the spatial domain images of the IBI extracted from the PPG signal to classify the stress state of the individual by building person-specific models and calibrated generic models.

Reality-Based Technologies for Children with Autism Spectrum Disorder: A Recommendation for Food Intake Intervention.

Food selectivity by children with autism spectrum disorder (ASD) is relatively high as compared to typical children and consequently puts them at risk of nutritional inadequacies. Thus, there is a need to educate children with ASD on food types and their benefits in a simple and interesting manner that will encourage food acceptance and enable a move toward healthy living. The use of technological intervention has proven to be an effective tool for educating children with ASD in maintaining attention and mastering new skills as compared to traditional methods. Some of the popularly used technologies are computer-based intervention and robotics which do not support ecological validity (i.e., mimicking natural scenario). Consideration of natural factors is essential for better learning outcomes and generalized skills which can easily be incorporated into reality-based technologies such as virtual reality, augmented reality, and mixed reality. These technologies provide evidence-based support for ecological validation of intervention and sustaining the attention of children with ASD. The main objective of this study is to review existing reality-based technology intervention for children with ASD and investigate the following: (1) commonly used reality-based technology, (2) types of intervention targeted with reality-based technology, and (3) what subjects' inclusion types are used in the reality-based interventions. These objective statements have guided our recommendation of reality-based technology that can support ecological validity of food intake intervention.

Predicting long-term type 2 diabetes with support vector machine using oral glucose tolerance test.

Diabetes is a large healthcare burden worldwide. There is substantial evidence that lifestyle modifications and drug intervention can prevent diabetes, therefore, an early identification of high risk individuals is important to design targeted prevention strategies. In this paper, we present an automatic tool that uses machine learning techniques to predict the development of type 2 diabetes mellitus (T2DM). Data generated from an oral glucose tolerance test (OGTT) was used to develop a predictive model based on the support vector machine (SVM). We trained and validated the models using the OGTT and demographic data of 1,492 healthy individuals collected during the San Antonio Heart Study. This study collected plasma glucose and insulin concentrations before glucose intake and at three time-points thereafter (30, 60 and 120 min). Furthermore, personal information such as age, ethnicity and body-mass index was also a part of the data-set. Using 11 OGTT measurements, we have deduced 61 features, which are then assigned a rank and the top ten features are shortlisted using minimum redundancy maximum relevance feature selection algorithm. All possible combinations of the 10 best ranked features were used to generate SVM based prediction models. This research shows that an individual's plasma glucose levels, and the information derived therefrom have the strongest predictive performance for the future development of T2DM. Significantly, insulin and demographic features do not provide additional performance improvement for diabetes prediction. The results of this work identify the parsimonious clinical data needed to be collected for an efficient prediction of T2DM. Our approach shows an average accuracy of 96.80% and a sensitivity of 80.09% obtained on a holdout set.

Developing a Digital Mental Health Platform for the Arab World: From Research to Action.

Individuals within the Arab world rarely access mental health services. One of the major reasons for this relates to the stigma associated with mental disorders. According to the World Health Organization (WHO), untreated and undiagnosed individuals living with moderate to severe mental health disorders are more likely to die 10-20 years earlier than the estimated life expectancy of the general population. Mental disorders also cause a large amount of costs to economies. Access to mental health services is out of reach for many individuals within in the Arab world due to insufficient planning, inadequate community resources, and military conflicts. Online mental health information and services are growing within the region; however, they are embedded and often sidelined within a wealth of other general health information. The purpose of this paper is to present the conceptual framework of the Mental Health Assistant (MeHA) digital platform being developed for the Arab world. The aim of this platform is to provide mental health information and educational resources through the use of a conversational agent, multi-media information, and to digitally connect patients with mental health service providers. The conceptual framework for the platform is based on mental health and information technology expert feedback, review of both academic and gray literature on mental health, and an examination of leading mental health digital platforms. As a result of this process, we developed a conceptual framework that will guide the development of the MeHA platform.

An Evolutionary Bootstrapping Development Approach for a Mental Health Conversational Agent.

Conversational agents are being used to help in the screening, assessment, diagnosis, and treatment of common mental health disorders. In this paper, we propose a bootstrapping approach for the development of a digital mental health conversational agent (i.e., chatbot). We start from a basic rule-based expert system and iteratively move towards a more sophisticated platform composed of specialized chatbots each aiming to assess and pre-diagnose a specific mental health disorder using machine learning and natural language processing techniques. During each iteration, user feedback from psychiatrists and patients are incorporated into the iterative design process. A survival of the fittest approach is also used to assess the continuation or removal of a specialized mental health chatbot in each generational design. We anticipate that our unique and novel approach can be used for the development of conversational mental health agents with the ultimate goal of designing a smart chatbot that delivers evidence-based care and contributes to scaling up services while decreasing the pressure on mental health care providers.

Epileptic seizure onset detection based on EEG and ECG data fusion.

This paper presents a novel method for seizure onset detection using fused information extracted from multichannel electroencephalogram (EEG) and single-channel electrocardiogram (ECG). In existing seizure detectors, the analysis of the nonlinear and nonstationary ECG signal is limited to the time-domain or frequency-domain. In this work, heart rate variability (HRV) extracted from ECG is analyzed using a Matching-Pursuit (MP) and Wigner-Ville Distribution (WVD) algorithm in order to effectively extract meaningful HRV features representative of seizure and nonseizure states. The EEG analysis relies on a common spatial pattern (CSP) based feature enhancement stage that enables better discrimination between seizure and nonseizure features. The EEG-based detector uses logical operators to pool SVM seizure onset detections made independently across different EEG spectral bands. Two fusion systems are adopted. In the first system, EEG-based and ECG-based decisions are directly fused to obtain a final decision. The second fusion system adopts an override option that allows for the EEG-based decision to override the fusion-based decision in the event that the detector observes a string of EEG-based seizure decisions. The proposed detectors exhibit an improved performance, with respect to sensitivity and detection latency, compared with the state-of-the-art detectors. Experimental results demonstrate that the second detector achieves a sensitivity of 100%, detection latency of 2.6s, and a specificity of 99.91% for the MAJ fusion case.

Band-sensitive seizure onset detection via CSP-enhanced EEG features.

This paper presents two novel epileptic seizure onset detectors. The detectors rely on a common spatial pattern (CSP)-based feature enhancement stage that increases the variance between seizure and nonseizure scalp electroencephalography (EEG). The proposed feature enhancement stage enables better discrimination between seizure and nonseizure features. The first detector adopts a conventional classification stage using a support vector machine (SVM) that feeds the energy features extracted from different subbands to an SVM for seizure onset detection. The second detector uses logical operators to pool SVM seizure onset detections made independently across different EEG spectral bands. The proposed detectors exhibit an improved performance, with respect to sensitivity and detection latency, compared with the state-of-the-art detectors. Experimental results have demonstrated that the first detector achieves a sensitivity of 95.2%, detection latency of 6.43s, and false alarm rate of 0.59perhour. The second detector achieves a sensitivity of 100%, detection latency of 7.28s, and false alarm rate of 1.2per hour for the MAJORITY fusion method.

An Overview of NCA-Based Algorithms for Transcriptional Regulatory Network Inference.

In systems biology, the regulation of gene expressions involves a complex network of regulators. Transcription factors (TFs) represent an important component of this network: they are proteins that control which genes are turned on or off in the genome by binding to specific DNA sequences. Transcription regulatory networks (TRNs) describe gene expressions as a function of regulatory inputs specified by interactions between proteins and DNA. A complete understanding of TRNs helps to predict a variety of biological processes and to diagnose, characterize and eventually develop more efficient therapies. Recent advances in biological high-throughput technologies, such as DNA microarray data and next-generation sequence (NGS) data, have made the inference of transcription factor activities (TFAs) and TF-gene regulations possible. Network component analysis (NCA) represents an efficient computational framework for TRN inference from the information provided by microarrays, ChIP-on-chip and the prior information about TF-gene regulation. However, NCA suffers from several shortcomings. Recently, several algorithms based on the NCA framework have been proposed to overcome these shortcomings. This paper first overviews the computational principles behind NCA, and then, it surveys the state-of-the-art NCA-based algorithms proposed in the literature for TRN reconstruction.