SMARTSeiz: Deep Learning with Attention Mechanism for Accurate Seizure Recognition in IoT Healthcare Devices.

The Internet of Things (IoT) is capable of controlling the healthcare monitoring system for remote-based patients. Epilepsy, a chronic brain syndrome characterized by recurrent, unpredictable attacks, affects individuals of all ages. IoT-based seizure monitoring can greatly enhance seizure patients' quality of life. IoT device acquires patient data and transmits it to a computer program so that doctors can examine it. Currently, doctors invest significant manual effort in inspecting Electroencephalograph (EEG) signals to identify seizure activity. However, EEG-based seizure detection algorithms face challenges in real-world scenarios due to non-stationary EEG data and variable seizure patterns among patients and recording sessions. Therefore, a sophisticated computer-based approach is necessary to analyze complex EEG records. In this work, the authors proposed a hybrid approach by combining traditional convolution neural (CN) and recurrent neural networks (RNN) along with an attention mechanism for the automatic recognition of epileptic seizures through EEG signal analysis. This attention mechanism focuses on significant subsets of EEG data for class recognition, resulting in improved model performance. The proposed methods are evaluated using a publicly available UCI epileptic seizure recognition dataset, which consists of five classes: four normal conditions and one abnormal seizure condition. Experimental results demonstrate that the suggested approach achieves an overall accuracy of 97.05% for the five-class EEG recognition data, with an accuracy of 99.52% for binary classification distinguishing seizure cases from normal instances. Furthermore, the proposed intelligent seizure recognition model is compatible with an IoMT (Internet of Medical Things) cloud-based smart healthcare framework.

Artificial intelligence based health indicator extraction and disease symptoms identification using medical hypothesis models.

Patient health record analysis models assist the medical field to understand the current stands and medical needs. Similarly, collecting and analyzing the disease features are the best practice for encouraging medical researchers to understand the research problems. Various research works evolve the way of medical data analysis schemes to know the actual challenges against the diseases. The computer-based diagnosis models and medical data analysis models are widely applied to have a better understanding of different diseases. Particularly, the field of medical electronics needs appropriate health indicator extraction models in near future. The existing medical schemes support baseline solutions but lack optimal hypothesis-based solutions. This work describes the optimal hypothesis model and Akin procedures for health record users, to aid health sectors in clinical decision-making on health indications. This work proposes Medical Hypothesis and Health Indicators Extraction from Electronic Medical Records (EMR) and International Classification of Diseases (ICD-10) patient examination database using the Akin Method and Friendship method. In this Health Indicators and Disease Symptoms Extraction (HIDSE), the evidence checking procedures find and collect all possible medical evidence from the existing patient examination report. Akin Method is making the hypothesis decision from count-based evidence principles. The health indicators extraction scheme extracts all relevant information based on the health indicators query and partial input. Similarly, the friendship method is used for making information associations between medical data attributes. This Akin-Friendship model helps to build hypothesis structures and trait-based feature extraction principles. This is called as Composite Akin Friendship Model (CAFM). This proposed model consists of various test cases for developing the medical hypothesis systems. On the other hand, it provides limited accuracy in disease classification. In this regard, the proposed HIDSE implements Deep Learning (DL) based Akin Friendship Method (DLAFM) for improving the accuracy of this medical hypothesis model. The proposed DLAFM, Convolutional Neural Networks (CNN) associated Legacy Prediction Model for Health Indicator (LPHI) is developed to tune the CAFM principles. The results show the proposed health indicator extraction scheme has 8-10% of better system performance than other existing techniques.

Internet of Medical Things (IoMT)-Based Smart Healthcare System: Trends and Progress.

Internet of Medical Thing (IoMT) is the most emerging era of the Internet of Thing (IoT), which is exponentially gaining researchers' attention with every passing day because of its wide applicability in Smart Healthcare systems (SHS). Because of the current pandemic situation, it is highly risky for an individual to visit the doctor for every small problem. Hence, using IoMT devices, we can easily monitor our day-to-day health records, and thereby initial precautions can be taken on our own. IoMT is playing a crucial role within the healthcare industry to increase the accuracy, reliability, and productivity of electronic devices. This research work provides an overview of IoMT with emphasis on various enabling techniques used in smart healthcare systems (SHS), such as radio frequency identification (RFID), artificial intelligence (AI), and blockchain. We are providing a comparative analysis of various IoMT architectures proposed by several researchers. Also, we have defined various health domains of IoMT, including the analysis of different sensors with their application environment, merits, and demerits. In addition, we have figured out key protocol design challenges, which are to be considered during the implementation of an IoMT network-based smart healthcare system. Considering these challenges, we prepared a comparative study for different data collection techniques that can be used to maintain the accuracy of collected data. In addition, this research work also provides a comprehensive study for maintaining the energy efficiency of an AI-based IoMT framework based on various parameters, such as the amount of energy consumed, packet delivery ratio, battery lifetime, quality of service, power drain, network throughput, delay, and transmission rate. Finally, we have provided different correlation equations for finding the accuracy and efficiency within the IoMT-based healthcare system using artificial intelligence. We have compared different data collection algorithms graphically based on their accuracy and error rate. Similarly, different energy efficiency algorithms are also graphically compared based on their energy consumption and packet loss percentage. We have analyzed our references used in this study, which are graphically represented based on their distribution of publication year and publication avenue.

IoT-Based Hybrid Ensemble Machine Learning Model for Efficient Diabetes Mellitus Prediction.

Nowadays, there is a growing need for Internet of Things (IoT)-based mobile healthcare applications that help to predict diseases. In recent years, several people have been diagnosed with diabetes, and according to World Health Organization (WHO), diabetes affects 346 million individuals worldwide. Therefore, we propose a noninvasive self-care system based on the IoT and machine learning (ML) that analyses blood sugar and other key indicators to predict diabetes early. The main purpose of this work is to develop enhanced diabetes management applications which help in patient monitoring and technology-assisted decision-making. The proposed hybrid ensemble ML model predicts diabetes mellitus by combining both bagging and boosting methods. An online IoT-based application and offline questionnaire with 15 questions about health, family history, and lifestyle were used to recruit a total of 10221 people for the study. For both datasets, the experimental findings suggest that our proposed model outperforms state-of-the-art techniques.

Detecting and Extracting Brain Hemorrhages from CT Images Using Generative Convolutional Imaging Scheme.

Purpose: The need for computerized medical assistance for accurate detection of brain hemorrhage from Computer Tomography (CT) images is more mandatory than conventional clinical tests. Recent technologies and advanced computerized algorithms follow Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques to improve medical diagnosis platforms. This technology is making the diagnosis practice of brain issues easier for medical practitioners to analyze and identify diseases with an assured degree of precision and performance. Methods: As the existing CT image analysis models use standard procedures to detect hemorrhages, the need for DL-based data analysis is essential to provide more accurate results. Generally, the existing techniques are limited with image training efficiency, image filtering procedures, and runtime system tuning modules. On the scope, this work develops a DL-based automated analysis of CT scan slices to find various levels of brain hemorrhages. Notably, this proposed system integrates Convolutional Neural Network (CNN) and Generative Adversarial Network (GAN) architectures as Integrated Generative Adversarial-Convolutional Imaging Model (IGACM) for extracting the CT image features for detecting brain hemorrhages. Results: This system produces good results and takes lesser training time than existing techniques. This proposed system effectively works over CT images and classifies the abnormalities with more accuracy than current techniques. The experiments and results deliver the optimal detection of hemorrhages with better accuracy. It shows that the proposed system works with 5% to 10% of the better performance compared to other diagnostic techniques. Conclusion: The complex nature of CT images leads to noncorrelated feature complexities in diagnosis models. Considering the issue, the proposed system used GAN-based effective sampling techniques for enriching complex image samples into CNN training phases. This concludes the effective contribution of the proposed IGACM technique for detecting brain hemorrhages than the existing diagnosis models.