Machine learning-based prognostic model for 30-day mortality prediction in Sepsis-3.

BACKGROUND: Sepsis poses a critical threat to hospitalized patients, particularly those in the Intensive Care Unit (ICU). Rapid identification of Sepsis is crucial for improving survival rates. Machine learning techniques offer advantages over traditional methods for predicting outcomes. This study aimed to develop a prognostic model using a Stacking-based Meta-Classifier to predict 30-day mortality risks in Sepsis-3 patients from the MIMIC-III database. METHODS: A cohort of 4,240 Sepsis-3 patients was analyzed, with 783 experiencing 30-day mortality and 3,457 surviving. Fifteen biomarkers were selected using feature ranking methods, including Extreme Gradient Boosting (XGBoost), Random Forest, and Extra Tree, and the Logistic Regression (LR) model was used to assess their individual predictability with a fivefold cross-validation approach for the validation of the prediction. The dataset was balanced using the SMOTE-TOMEK LINK technique, and a stacking-based meta-classifier was used for 30-day mortality prediction. The SHapley Additive explanations analysis was performed to explain the model's prediction. RESULTS: Using the LR classifier, the model achieved an area under the curve or AUC score of 0.99. A nomogram provided clinical insights into the biomarkers' significance. The stacked meta-learner, LR classifier exhibited the best performance with 95.52% accuracy, 95.79% precision, 95.52% recall, 93.65% specificity, and a 95.60% F1-score. CONCLUSIONS: In conjunction with the nomogram, the proposed stacking classifier model effectively predicted 30-day mortality in Sepsis patients. This approach holds promise for early intervention and improved outcomes in treating Sepsis cases.

Editorial Topical Collection: "Explainable and Augmented Machine Learning for Biosignals and Biomedical Images".

Machine learning (ML) is a well-known subfield of artificial intelligence (AI) that aims at developing algorithms and statistical models able to empower computer systems to automatically adapt to a specific task through experience or learning from data [...].

YOLOv5s-CA: A Modified YOLOv5s Network with Coordinate Attention for Underwater Target Detection.

Underwater target detection techniques have been extensively applied to underwater vehicles for marine surveillance, aquaculture, and rescue applications. However, due to complex underwater environments and insufficient training samples, the existing underwater target recognition algorithm accuracy is still unsatisfactory. A long-term effort is essential to improving underwater target detection accuracy. To achieve this goal, in this work, we propose a modified YOLOv5s network, called YOLOv5s-CA network, by embedding a Coordinate Attention (CA) module and a Squeeze-and-Excitation (SE) module, aiming to concentrate more computing power on the target to improve detection accuracy. Based on the existing YOLOv5s network, the number of bottlenecks in the first C3 module was increased from one to three to improve the performance of shallow feature extraction. The CA module was embedded into the C3 modules to improve the attention power focused on the target. The SE layer was added to the output of the C3 modules to strengthen model attention. Experiments on the data of the 2019 China Underwater Robot Competition were conducted, and the results demonstrate that the mean Average Precision (mAP) of the modified YOLOv5s network was increased by 2.4%.

Cybersecurity Risk Analysis of Electric Vehicles Charging Stations.

The increasing availability of Electric Vehicles (EVs) is driving a shift away from traditional gasoline-powered vehicles. Subsequently, the demand for Electric Vehicle Charging Systems (EVCS) is rising, leading to the significant growth of EVCS as public and private charging infrastructure. The cybersecurity-related risks in EVCS have significantly increased due to the growing network of EVCS. In this context, this paper presents a cybersecurity risk analysis of the network of EVCS. Firstly, the recent advancements in the EVCS network, recent EV adaptation trends, and charging use cases are described as a background of the research area. Secondly, cybersecurity aspects in EVCS have been presented considering infrastructure and protocol-centric vulnerabilities with possible cyber-attack scenarios. Thirdly, threats in EVCS have been validated with real-time data-centric analysis of EV charging sessions. The paper also highlights potential open research issues in EV cyber research as new knowledge for domain researchers and practitioners.

TAKEN: A Traffic Knowledge-Based Navigation System for Connected and Autonomous Vehicles.

Connected and autonomous vehicles (CAVs) have witnessed significant attention from industries, and academia for research and developments towards the on-road realisation of the technology. State-of-the-art CAVs utilise existing navigation systems for mobility and travel path planning. However, reliable connectivity to navigation systems is not guaranteed, particularly in urban road traffic environments with high-rise buildings, nearby roads and multi-level flyovers. In this connection, this paper presents TAKEN-Traffic Knowledge-based Navigation for enabling CAVs in urban road traffic environments. A traffic analysis model is proposed for mining the sensor-oriented traffic data to generate a precise navigation path for the vehicle. A knowledge-sharing method is developed for collecting and generating new traffic knowledge from on-road vehicles. CAVs navigation is executed using the information enabled by traffic knowledge and analysis. The experimental performance evaluation results attest to the benefits of TAKEN in the precise navigation of CAVs in urban traffic environments.

Forecasting major impacts of COVID-19 pandemic on country-driven sectors: challenges, lessons, and future roadmap.

The pandemic caused by the coronavirus disease 2019 (COVID-19) has produced a global health calamity that has a profound impact on the way of perceiving the world and everyday lives. This has appeared as the greatest threat of the time for the entire world in terms of its impact on human mortality rate and many other societal fronts or driving forces whose estimations are yet to be known. Therefore, this study focuses on the most crucial sectors that are severely impacted due to the COVID-19 pandemic, in particular reference to India. Considered based on their direct link to a country's overall economy, these sectors include economic and financial, educational, healthcare, industrial, power and energy, oil market, employment, and environment. Based on available data about the pandemic and the above-mentioned sectors, as well as forecasted data about COVID-19 spreading, four inclusive mathematical models, namely-exponential smoothing, linear regression, Holt, and Winters, are used to analyse the gravity of the impacts due to this COVID-19 outbreak which is also graphically visualized. All the models are tested using data such as COVID-19 infection rate, number of daily cases and deaths, GDP of India, and unemployment. Comparing the obtained results, the best prediction model is presented. This study aims to evaluate the impact of this pandemic on country-driven sectors and recommends some strategies to lessen these impacts on a country's economy.

BEST-Blockchain-Enabled Secure and Trusted Public Emergency Services for Smart Cities Environment.

In the last few years, the Internet of things (IoT) has recently gained attention in developing various smart city applications such as smart healthcare, smart supply chain, smart home, smart grid, etc. The existing literature focuses on the smart healthcare system as a public emergency service (PES) to provide timely treatment to the patient. However, little attention is given to a distributed smart fire brigade system as a PES to protect human life and properties from severe fire damage. The traditional PES are developed on a centralised system, which requires high computation and does not ensure timely service fulfilment. Furthermore, these traditional PESs suffer from a lack of trust, transparency, data integrity, and a single point of failure issue. In this context, this paper proposes a Blockchain-Enabled Secure and Trusted (BEST) framework for PES in the smart city environment. The BEST framework focuses on providing a fire brigade service as a PES to the smart home based on IoT device information to protect it from serious fire damage. Further, we used two edge computing servers, an IoT controller and a service controller. The IoT and service controller are used for local storage and to enhance the data processing speed of PES requests and PES fulfilments, respectively. The IoT controller manages an access control list to keep track of registered IoT gateways and their IoT devices, avoiding misguiding the PES department. The service controller utilised the queue model to handle the PES requests based on the minimum service queue length. Further, various smart contracts are designed on the Hyperledger Fabric platform to automatically call a PES either in the presence or absence of the smart-home owner under uncertain environmental conditions. The performance evaluation of the proposed BEST framework indicates the benefits of utilising the distributed environment and the smart contract logic. The various simulation results are evaluated in terms of service queue length, utilisation, actual arrival time, expected arrival time, number of PES departments, number of PES providers, and end-to-end delay. These simulation results show the effectiveness and feasibility of the BEST framework.

Self-Sovereignty Identity Management Model for Smart Healthcare System.

An identity management system is essential in any organisation to provide quality services to each authenticated user. The smart healthcare system should use reliable identity management to ensure timely service to authorised users. Traditional healthcare uses a paper-based identity system which is converted into centralised identity management in a smart healthcare system. Centralised identity management has security issues such as denial of service attacks, single-point failure, information breaches of patients, and many privacy issues. Decentralisedidentity management can be a robust solution to these security and privacy issues. We proposed a Self-Sovereign identity management system for the smart healthcare system (SSI-SHS), which manages the identity of each stakeholder, including medical devices or sensors, in a decentralisedmanner in the Internet of Medical Things (IoMT) Environment. The proposed system gives the user complete control of their data at each point. Further, we analysed the proposed identity management system against Allen and Cameron's identity management guidelines. We also present the performance analysis of SSI as compared to the state-of-the-art techniques.

Quality-of-Service-Centric Design and Analysis of Unmanned Aerial Vehicles.

Recent years have witnessed rapid development and great indignation burgeoning in the unmanned aerial vehicles (UAV) field. This growth of UAV-related research contributes to several challenges, including inter-communication from vehicle to vehicle, transportation coverage, network information gathering, network interworking effectiveness, etc. Due to ease of usage, UAVs have found novel applications in various areas such as agriculture, defence, security, medicine, and observation for traffic-monitoring applications. This paper presents an innovative drone system by designing and developing a blended-wing-body (BWB)-based configuration for next-generation drone use cases. The proposed method has several benefits, including a very low interference drag, evenly distributed load inside the body, and less radar signature compared to the state-of-the-art configurations. During the entire procedure, a standard design approach was followed to optimise the BWB framework for next-generation use cases by considering the typically associated parameters such as vertical take-off and landing and drag and stability of the BWB. Extensive simulation experiments were performed to carry out a performance analysis of the proposed model in a software-based environment. To further confirm that the model design of the BWB-UAV is fit to execute the targeted missions, the real-time working environments were tested through advanced numerical simulation and focused on avoiding cost and unwanted wastages. To enhance the trustworthiness of this said computational fluid dynamics (CFD) analysis, grid convergence test-based validation was also conducted. Two different grid convergence tests were conducted on the induced velocity of the Version I UAV and equivalent stress of the Version II UAV. Finite element analysis-based computations were involved in estimating structural outcomes. Finally, the mesh quality was obtained as 0.984 out of 1. The proposed model is very cost-effective for performing a different kind of manoeuvring activities with the help of its unique design at reasonable mobility speed and hence can be modelled for high-speed-based complex next-generation use cases.

Real-Time Artifacts Reduction during TMS-EEG Co-Registration: A Comprehensive Review on Technologies and Procedures.

Transcranial magnetic stimulation (TMS) excites neurons in the cortex, and neural activity can be simultaneously recorded using electroencephalography (EEG). However, TMS-evoked EEG potentials (TEPs) do not only reflect transcranial neural stimulation as they can be contaminated by artifacts. Over the last two decades, significant developments in EEG amplifiers, TMS-compatible technology, customized hardware and open source software have enabled researchers to develop approaches which can substantially reduce TMS-induced artifacts. In TMS-EEG experiments, various physiological and external occurrences have been identified and attempts have been made to minimize or remove them using online techniques. Despite these advances, technological issues and methodological constraints prevent straightforward recordings of early TEPs components. To the best of our knowledge, there is no review on both TMS-EEG artifacts and EEG technologies in the literature to-date. Our survey aims to provide an overview of research studies in this field over the last 40 years. We review TMS-EEG artifacts, their sources and their waveforms and present the state-of-the-art in EEG technologies and front-end characteristics. We also propose a synchronization toolbox for TMS-EEG laboratories. We then review subject preparation frameworks and online artifacts reduction maneuvers for improving data acquisition and conclude by outlining open challenges and future research directions in the field.

Automatic Lung Health Screening Using Respiratory Sounds.

Significant changes have been made on audio-based technologies over years in several different fields. Healthcare is no exception. One of such avenues is health screening based on respiratory sounds. In this paper, we developed a tool to detect respiratory sounds that come from respiratory infection carrying patients. Linear Predictive Cepstral Coefficient (LPCC)-based features were used to characterize such audio clips. With Multilayer Perceptron (MLP)-based classifier, in our experiment, we achieved the highest possible accuracy of 99.22% that was tested on a publicly available respiratory sounds dataset (ICBHI17) (Rocha et al. Physiol. Meas. 40(3):035,001 20) of size 6800+ clips. In addition to other popular machine learning classifiers, our results outperformed common works that exist in the literature.

TClustVID: A novel machine learning classification model to investigate topics and sentiment in COVID-19 tweets.

COVID-19, caused by SARS-CoV2 infection, varies greatly in its severity but presents with serious respiratory symptoms with vascular and other complications, particularly in older adults. The disease can be spread by both symptomatic and asymptomatic infected individuals. Uncertainty remains over key aspects of the virus infectiousness (particularly the newly emerging variants) and the disease has had severe economic impacts globally. For these reasons, COVID-19 is the subject of intense and widespread discussion on social media platforms including Facebook and Twitter. These public forums substantially influence public opinions and in some cases can exacerbate the widespread panic and misinformation spread during the crisis. Thus, this work aimed to design an intelligent clustering-based classification and topic extracting model named TClustVID that analyzes COVID-19-related public tweets to extract significant sentiments with high accuracy. We gathered COVID-19 Twitter datasets from the IEEE Dataport repository and employed a range of data preprocessing methods to clean the raw data, then applied tokenization and produced a word-to-index dictionary. Thereafter, different classifications were employed on these datasets which enabled the exploration of the performance of traditional classification and TClustVID. Our analysis found that TClustVID showed higher performance compared to traditional methodologies that are determined by clustering criteria. Finally, we extracted significant topics from the clusters, split them into positive, neutral and negative sentiments, and identified the most frequent topics using the proposed model. This approach is able to rapidly identify commonly prevailing aspects of public opinions and attitudes related to COVID-19 and infection prevention strategies spreading among different populations.

Classification of Diabetic Retinopathy Disease Levels by Extracting Spectral Features Using Wavelet CNN.

Diabetic retinopathy (DR) arises from blood vessel damage and is a leading cause of blindness on a global scale. Clinical professionals rely on examining fundus images to diagnose the disease, but this process is frequently prone to errors and is tedious. The usage of computer-assisted techniques offers assistance to clinicians in detecting the severity levels of the disease. Experiments involving automated diagnosis employing convolutional neural networks (CNNs) have produced impressive outcomes in medical imaging. At the same time, retinal image grading for detecting DR severity levels has predominantly focused on spatial features. More spectral features must be explored for a more efficient performance of this task. Analysing spectral features plays a vital role in various tasks, including identifying specific objects or materials, anomaly detection, and differentiation between different classes or categories within an image. In this context, a model incorporating Wavelet CNN and Support Vector Machine has been introduced and assessed to classify clinically significant grades of DR from retinal fundus images. The experiments were conducted on the EyePACS dataset and the performance of the proposed model was evaluated on the following metrics: precision, recall, F1-score, accuracy, and AUC score. The results obtained demonstrate better performance compared to other state-of-the-art techniques.

Ensemble of vision transformer architectures for efficient Alzheimer's Disease classification.

Transformers have dominated the landscape of Natural Language Processing (NLP) and revolutionalized generative AI applications. Vision Transformers (VT) have recently become a new state-of-the-art for computer vision applications. Motivated by the success of VTs in capturing short and long-range dependencies and their ability to handle class imbalance, this paper proposes an ensemble framework of VTs for the efficient classification of Alzheimer's Disease (AD). The framework consists of four vanilla VTs, and ensembles formed using hard and soft-voting approaches. The proposed model was tested using two popular AD datasets: OASIS and ADNI. The ADNI dataset was employed to assess the models' efficacy under imbalanced and data-scarce conditions. The ensemble of VT saw an improvement of around 2% compared to individual models. Furthermore, the results are compared with state-of-the-art and custom-built Convolutional Neural Network (CNN) architectures and Machine Learning (ML) models under varying data conditions. The experimental results demonstrated an overall performance gain of 4.14% and 4.72% accuracy over the ML and CNN algorithms, respectively. The study has also identified specific limitations and proposes avenues for future research. The codes used in the study are made publicly available.

Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer's disease detection.

Explainable artificial intelligence (XAI) has gained much interest in recent years for its ability to explain the complex decision-making process of machine learning (ML) and deep learning (DL) models. The Local Interpretable Model-agnostic Explanations (LIME) and Shaply Additive exPlanation (SHAP) frameworks have grown as popular interpretive tools for ML and DL models. This article provides a systematic review of the application of LIME and SHAP in interpreting the detection of Alzheimer's disease (AD). Adhering to PRISMA and Kitchenham's guidelines, we identified 23 relevant articles and investigated these frameworks' prospective capabilities, benefits, and challenges in depth. The results emphasise XAI's crucial role in strengthening the trustworthiness of AI-based AD predictions. This review aims to provide fundamental capabilities of LIME and SHAP XAI frameworks in enhancing fidelity within clinical decision support systems for AD prognosis.

HyEpiSeiD: a hybrid convolutional neural network and gated recurrent unit model for epileptic seizure detection from electroencephalogram signals.

Epileptic seizure (ES) detection is an active research area, that aims at patient-specific ES detection with high accuracy from electroencephalogram (EEG) signals. The early detection of seizure is crucial for timely medical intervention and prevention of further injuries of the patients. This work proposes a robust deep learning framework called HyEpiSeiD that extracts self-trained features from the pre-processed EEG signals using a hybrid combination of convolutional neural network followed by two gated recurrent unit layers and performs prediction based on those extracted features. The proposed HyEpiSeiD framework is evaluated on two public datasets, the UCI Epilepsy and Mendeley datasets. The proposed HyEpiSeiD model achieved 99.01% and 97.50% classification accuracy, respectively, outperforming most of the state-of-the-art methods in epilepsy detection domain.

Performance Evaluation of Deep, Shallow and Ensemble Machine Learning Methods for the Automated Classification of Alzheimer's Disease.

Artificial intelligence (AI)-based approaches are crucial in computer-aided diagnosis (CAD) for various medical applications. Their ability to quickly and accurately learn from complex data is remarkable. Deep learning (DL) models have shown promising results in accurately classifying Alzheimer's disease (AD) and its related cognitive states, Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI), along with the healthy conditions known as Cognitively Normal (CN). This offers valuable insights into disease progression and diagnosis. However, certain traditional machine learning (ML) classifiers perform equally well or even better than DL models, requiring less training data. This is particularly valuable in CAD in situations with limited labeled datasets. In this paper, we propose an ensemble classifier based on ML models for magnetic resonance imaging (MRI) data, which achieved an impressive accuracy of 96.52%. This represents a 3-5% improvement over the best individual classifier. We evaluated popular ML classifiers for AD classification under both data-scarce and data-rich conditions using the Alzheimer's Disease Neuroimaging Initiative and Open Access Series of Imaging Studies datasets. By comparing the results to state-of-the-art CNN-centric DL algorithms, we gain insights into the strengths and weaknesses of each approach. This work will help users to select the most suitable algorithm for AD classification based on data availability.

A Topical Review on Enabling Technologies for the Internet of Medical Things: Sensors, Devices, Platforms, and Applications.

The Internet of Things (IoT) is still a relatively new field of research, and its potential to be used in the healthcare and medical sectors is enormous. In the last five years, IoT has been a go-to option for various applications such as using sensors for different features, machine-to-machine communication, etc., but precisely in the medical sector, it is still lagging far behind compared to other sectors. Hence, this study emphasises IoT applications in medical fields, Medical IoT sensors and devices, IoT platforms for data visualisation, and artificial intelligence in medical applications. A systematic review considering PRISMA guidelines on research articles as well as the websites on IoMT sensors and devices has been carried out. After the year 2001, an integrated outcome of 986 articles was initially selected, and by applying the inclusion-exclusion criterion, a total of 597 articles were identified. 23 new studies have been finally found, including records from websites and citations. This review then analyses different sensor monitoring circuits in detail, considering an Intensive Care Unit (ICU) scenario, device applications, and the data management system, including IoT platforms for the patients. Lastly, detailed discussion and challenges have been outlined, and possible prospects have been presented.

Early Detection of Alzheimer's Disease From Cortical and Hippocampal Local Field Potentials Using an Ensembled Machine Learning Model.

Early diagnosis of Alzheimer's disease (AD) is a very challenging problem and has been attempted through data-driven methods in recent years. However, considering the inherent complexity in decoding higher cognitive functions from spontaneous neuronal signals, these data-driven methods benefit from the incorporation of multimodal data. This work proposes an ensembled machine learning model with explainability (EXML) to detect subtle patterns in cortical and hippocampal local field potential signals (LFPs) that can be considered as a potential marker for AD in the early stage of the disease. The LFPs acquired from healthy and two types of AD animal models (n = 10 each) using linear multielectrode probes were endorsed by electrocardiogram and respiration signals for their veracity. Feature sets were generated from LFPs in temporal, spatial and spectral domains and were fed into selected machine-learning models for each domain. Using late fusion, the EXML model achieved an overall accuracy of 99.4%. This provided insights into the amyloid plaque deposition process as early as 3 months of the disease onset by identifying the subtle patterns in the network activities. Lastly, the individual and ensemble models were found to be robust when evaluated by randomly masking channels to mimic the presence of artefacts.