Computational Intelligence and Machine Learning Approaches in Biomedical Engineering and Health Care Systems

 Medical image processing is critical in disease detection and prediction. For example, they locate lesions and measure an organ's morphological structures. Currently, cardiac magnetic resonance imaging (CMRI) plays an essential role in cardiac motion tracking and analyzing regional and global heart functions with high accuracy and reproducibility. Cardiac MRI datasets are images taken during the heart's cardiac cycles. These datasets require expert labeling to accurately recognize features and train neural networks to predict cardiac disease. Any erroneous prediction caused by image impairment will impact patients' diagnostic decisions. As a result, image preprocessing is used, including enhancement tools such as filtering and denoising. This paper introduces a denoising algorithm that uses a convolution neural network (CNN) to delineate left ventricle (LV) contours (endocardium and epicardium borders) from MRI images. With only a small amount of training data from the EMIDEC database, this network performs well for MRI image denoising.

Diabetic retinopathy is a disease in an eye caused due to the diabetic condition present in the person, resulting in blindness. Early diagnosis of the disease prevents the progression of blindness. Microaneurysms are the significant symptoms of the early detection of diabetic retinopathy and are initiated by dilating the thin blood vessels. Microaneurysms are red lesions, which may be round and sometimes irregular in shape. Generally, microaneurysms appear near the macula or close to the blood vessel. The present study concentrates on detecting microaneurysms to detect diabetic retinopathy in the early stage. This chapter utilizes the Particle Swarm Optimization (PSO) algorithm to effectively segment the microaneurysms. The segmented microaneurysm is analyzed using the measures of Entropy, Skewness, and Kurtosis. The elevated PSO clustering gives high performance irrespective of image contrast. The elevated continuous PSO clustering successfully detects microaneurysms and helps diagnose diabetic retinopathy in the early stage in an efficient way. This work uses digital image processing techniques and mainly concentrates on the effective detection of microaneurysms. The results proved that the proposed approach improves performance in the early detection of diabetic retinopathy.

E-Health and telemedicine deliver health care and health-related services using medical informatics, telecommunication, and exchange of health care data across distant places. This is one small leap of information technology that allows all to access good health care. The key fact of telemedicine is electronic signals to transfer knowledge from one computer to another through videoconferencing among health care experts to provide better treatment and care. Since many indoor and outdoor patients require referral for specialized care in remote areas, telemedicine can deliver a better solution. In addition to that, it also provides quality, low-cost health care to the poorest individuals and the rural population, thereby it bridges the rural-urban health divide. It will help avoid unnecessary transportation and the potential to chop back health care prices by reducing the burden of ill health, the danger of complications, hospitalizations, continual events, and premature death and boosting the quality of life. Through this, the public can easily get medical consultation, diagnosis, and monitoring of their health records to get proper treatment, and also it is possible to get robotic surgery. Telemedicine and E-health alternatives are widely popularized in COVID-19 pandemics and will aid future public health crisis management. However, there is a need to educate and make awareness among the people, develop policies and infrastructure in the E-health system, and telemedicine to provide equal health care access to all and improve public health and medical care. Overall, this chapter discusses detailed information about the E-health system and telemedicine and its applications in the healthcare system.

Leg pain occurs in many people nowadays due to today's lifestyle. This leads to various treatments for leg pain with an unprecedented monitoring system. However, there are some issues regarding the existing leg pain treatments concerning a suitable monitoring procedure. The first issue is the treatment method, where most treatments for leg pain use compression. Still, they are costly, time-consuming, and cumbersome, requiring patients to visit hospitals regularly and affecting patients' compliance to continue with treatments. The second issue is the treatment period for leg pain within a short time frame, whereby it is difficult to see the major effect of a certain treatment. The third issue is the lack of a system to monitor patient's rehabilitation progress to increase patients' confidence to continue treatment consistently to cure their leg pain. Therefore, a patient monitoring system needs to be developed to cover existing research issues under the main area of health informatics. This system will apply the double-loop feedback theory that includes the agile framework to continue the process. The double-loop framework will ensure all the problems and preferred modifications will undergo a simultaneous fixation once each development segment is completed. This patient monitoring system is a computational intelligence system that focuses on fuzzy logic, producing a decision-making outcome based on collected data. This process aims to perform a valid treatment analysis as accurately as possible. Its development is significant for the national agenda as it falls under the national research priority area of health and medicine. The expected outcome would be introducing a computational intelligence inpatient monitoring system for lymphatic treatment of leg pain based on double-loop feedback theory.

The COVID-19 epidemic affects humans irrespective of race, religion, standing, and caste. It has affected more than 20 million people worldwide. Wearing face masks and taking public safety measures are two advanced safety measures that need to be taken in open areas to prevent the spread of the disease. To create a secure environment that contributes to public safety, we propose a computer-based method that focuses on automatic real-time surveillance to identify safe general distance and face masks in public places using a model to monitor movement and detect camera violations. We achieve 97.6% specificity with the help of OpenCV and MobileNetV2 strategies.

Information and communication technology usage in the healthcare sector is not perceptible due to various challenges with increased healthcare needs. With the outburst of COVID-19, when the different countries announced lockdown and social distancing rules, it is crucial to predict a person's symptoms, which will help in the early diagnosis. In such situations, there is a tremendous growth seen in the usage of various technologies, such as remote health monitoring, Wireless Body Area Networks (WBANs), Machine Learning (ML), and Decision Support system (DSS). Hence, the chapter focuses on detecting diseases and associated symptoms using various ML algorithms. A total of 3073 patient data (heartbeat, snore, and body temperature) has been collected. The collected data were preprocessed to remove empty cells and zero values by replacing the mean of the cells. Later, the extracted features were used in Empirical Mode Decomposition (EWD) and Discrete Wavelet Transformation (DWT). Then, the optimized algorithms with the threshold values were identified by consulting doctors for accurate disease prediction. With the testing performance of various ML algorithms, such as Decision Tree Classifier (DTC), K-Nearest Neighbor (KNN), Gradient Descent (SGD), Naive Bayes (NB), Multilayer perceptron (MLP), Support Vector Machine (SVM), and Random Forest (RF), was compared. Performance evaluation parameters are accuracy, precision, F1 score, and recall. The results showed an average of 100% accuracy with SGD and SVM with DWT, whereas EMD, SVM, and MLP outperformed the state-of-the-art algorithms with 99.83% accuracy.

Cardiovascular diseases (CVDs) are the primary cause of death worldwide. If these are not detected early and are not treated on time, one may lose a life. Despite using various measures and standards by doctors, the disease is unpredictable and has a significant death toll. Artificial intelligence (AI) techniques have been introduced to predict the outcome and utilization of machine learning (ML) techniques in diversified areas, showing promising results to make it more sophisticated for both medical professionals and patients. In this chapter, a cardiovascular disease preventive prediction and medication (CVDPPM) model has been developed, which utilizes various communication models for assisting the patients through constant monitoring of heart rate and blood pressure. The main focus of CVDPPM is to predict the early occurrences of artery disease, stroke, and heart failure. It helps notify the nearest cardiologist and medical team with all needed reports for immediate and appropriate medical treatment to save the patient's life. The proposed model fastens the medical procedure by alerting the regular consulted doctor and the family about the patient's condition and medical reports immediately.

The healthcare sector is rapidly evolving due to the exponential growth of the digital space and emerging technologies. Maintaining and effectively handling large quantities of data has become difficult in all industries. Furthermore, collecting helpful knowledge from extensive data collection is a daunting challenge. There would be an immense amount of data that continues to grow, making it harder and harder to find some helpful information. In the healthcare industry, big data analytics offers a variety of tools and strategies for detecting or predicting illnesses faster and delivering better healthcare facilities to the right patient at the right time to increase the quality of life. It is not as simple as one would imagine, given the myriad functional challenges that need to be addressed within current health data analytics systems that offer procedural frameworks for data collection, aggregation, processing, review, simulation, and interpretation. This chapter aims to design a long-term, commercially viable, and intelligent diabetes diagnosis approach with tailored care. Due to a lack of systematic studies in the previous literature, this chapter describes the different computational methods used in big data analytical techniques and the various phases and modules that transform the healthcare economy from data collection to knowledge distribution. The investigation findings indicate that the suggested framework will effectively offer adapted evaluation and care advice to patients, emphasizing a knowledge exchange approach and adapted data processing model for the smart diabetic system. 

The smart system integrates cloud computing and mobile computing, also known as mobile cloud computing. This smart system helps monitor the vehicle's health condition on any device, i.e., platform-independent. Using machine learning algorithms, the smart system helps predict vehicle health and maintain the vehicle's and the driving person's safety. The cloud computing used to deploy this smart system for monitoring the vehicle condition is the Google Cloud Platform. Google Cloud Platform provides various services like Computing and Hosting, Networking, Storage, etc., which help deploy and host web applications on Google Cloud using multiple services. One of the best securities is achieved using the Google Cloud Platform. Several layers are encrypted with specially designed algorithms for the safety of the customer data and applications. Google Cloud Platform helps provide data integrity, making it better for storing all the data. It also provides Denial of Service protection which helps realtime protection of servers for hosting the data. The smart system is deployed to only authenticated users eligible to monitor the vehicle's health condition. The health of the car may be tracked in the cloud and on every device with an internet connection and communication services. The mobile application is deployed from the webserver, facilitating secure and safe data browsing. The smart system is developed for displaying vehicle conditions dynamically, Google Maps for tracking the present vehicle location, and manual testing of the vehicle health by entering the values in the portal, which helps notification of risk, medium risk, and no risk of the vehicle condition using machine learning algorithm, which runs at the backend of the application.

Alzheimer’s disease (AD) is one of the most common neurodegenerative diseases (dementia) among the aged population. In this paper, we propose a unique machine learning-based framework to discriminate subjects with the first classification of AD. The training data, preprocessing, feature selection, and classifiers all affect the output of machine-learning-based methods for AD classification. This chapter discusses a new comprehensive scheme called Progression Prediction and Classification of Alzheimer’s Disease using MRI (PPC-AD-MRI). Considering the data gathered with T1-weighted MRI clinical OASIS progressive information, the consequences have been evaluated in terms of precision, recall, F1 score, and accuracy. This recommended model with enhanced accuracy confirms its suitability for use in AD classification. Other methods can also be used successfully in the disease’s early detection and diagnosis in medicine and healthcare.