Translating Healthcare Through Intelligent Computational Methods

The word “healthcare” can be defined as the role played by medical professionals and trained professionals to retrieve back the health of each individual at different processing stages like diagnosis, treatment and prevention. Due to growth of population, minimally invasive surgical procedures, modernization of medical treatment methods, demand in supply, quick recovery and restoration, the necessity to integrate the intelligent computational methods into healthcare sectors are highly required. These computational methods provide intelligent assistance to the translation via incorporating technologies like artificial intelligence (AI), machine learning (ML), big data analytics, deep learning, cloud computing, fog computing, internet of things (IoT). It is inferred that they offer better healthcare services to mankind in the world to lead a better life. Several research opportunities are available based on integrating the computational methods into healthcare sector. Some of them can be on design and development of devices, proposing suitable system architecture, data storage, handling and accessing systems, defining suitable protocols, framing policies and guidelines. Three important revolutions occurred in the twenty-first century which focus on internet, omics and artificial intelligence.

People tend to trust traditional medicine more than conventional medicine because they believe that nature is a source of healing, refreshment, and restoration. The traditional medical culture differs depending on the civilisation and how the people live and where they live. Chinese medicine, indigenous Arabic medicine, Korean traditional medicine, Uyghur traditional medicine, traditional European medicine, traditional African medicine, traditional aboriginal Bush medicine, Japanese kampo medicine, and others are all examples of traditional medicine. These medications are used in a number of ways, including the diagnosis of illness, the prevention of illness, and the treatment of an illness. A person known as a traditional healer will offer medical care using various methods and specific plants, animals, and mineral substances. Traditional medicine contains medical aspects of traditional knowledge that was developed generation over generation within the society of people before the era of modern medicine.

Traditional medicine is a broader area in which medicinal plants, animals, fungi, minerals, etc., are used for the treatment of diseases or any symptoms and conditions associated with diseases. Amongst all, plants are used prevalently in the treatment. These practices have also gained attention in many developed countries, where conventional medicines are predominant. Knowledge of ancient civilizations and understanding their earlier accomplishments are key to progress in science, medicine and health. This chapter aims at harmonizing traditional system of medicine, as it is strongly based on the beliefs and experiences of different cultures and ethnic groups. In-depth comprehension of traditional and integrative system of medicine has propelled several, yet different traditional approaches with various theories and methodologies, which have received greater significance in different regions of the world. This paved the way for new drug discoveries for the benefits of mankind. Due to this sudden upsurge in the practice of traditional medicine worldwide, safety and ethical standards have become concerns. World Health Organization (WHO) has set international standards, efficacy, guidelines, quality and safety measures to follow the traditional medicine system. This chapter will help the readers to get an insight into well-acknowledged traditional medicine systems which are still considered as an important component in healthcare management.

In recent decades, low- and middle-income nations have accounted for at least three-quarters of all cardiovascular disease (CVD) deaths worldwide. Multiple cardiovascular disease risk variables are combined with the requirement for time to produce precise, accurate, and sensitive methods for early identification and treatment of the illness. The goal of this research is to figure out how likely it is for a patient to acquire heart disease. Because of the exponential development in the number of electronic health records, data mining has huge potential in the provision of health-related services. A lack of standardized and computable illness definitions and a lack of authorized, relevant patient-centered outcomes are all stumbling blocks in progressing cardiovascular diagnosis, therapy, and prognostic evaluation. Due to their complexity and volume, healthcare activities generate vast volumes of data that can’t be processed and interpreted using traditional methods and procedures. Different machine learning (ML) approaches help in assisting health providers in predicting cardiac issues. K-nearest neighbor (KNN), support vector machine (SVM), and random forest algorithm are the methods. The main results obtained in this article are the following: (1) The goal of this research is to build a desktop program that can predict whether or not a patient will acquire heart disease in the future; (2) machine learning classification techniques such as support vector machine, random forests, and K-nearest neighbor were used in this study, which was conducted under the Machine Learning Repository (MLR); (3) desktop prediction tool is efficient and trustworthy while requiring fewer features and tests to predict heart diseases; (4) the second step is to do exploratory data analysis, which includes exploring the content of all variables and analyzing each of them with the required plots for each of them; (5) the next step is to clean and preprocess the data that have been obtained; and (6) once the data preprocessing has been completed, classification algorithms like support vector machine, K-nearest neighbor, and random forests are employed to achieve accuracy. This gadget has been designed to monitor the client’s heart rate and sound an alarm if it climbs above the normal range. In order to demonstrate the value of the tool, we used well-known algorithms such as KNN, SVM, and random forests. Following the completion of a holdout check, the random forest algorithm was used in an attempt to increase the accuracy of the suggested tool to 96%.

Healthcare has long been attributed to human intelligence and judgement. Twentieth century has sown the seed for a revolution that has geared up the healthcare technology towards a phenomenal development. Healthcare has entered the digital era as a process driven by need. With access to large amounts of medical information from healthcare specialities, technologies, and electronic health records, its usability to improve the healthcare processes was sought for. Specifically, precise, personalized, and proactive form of healthcare decision support system has gained attention with the integration of artificial intelligence (AI). AI systems are capable of performing intelligent tasks akin to human brain. AI in healthcare in present day is the trendsetter for the future of precision diagnostic and therapeutic interventions. This chapter deals with how artificial intelligence has brought the intersection of human judgement and scientific data closer than ever. This chapter aims at unravelling the key timelines associated with health revolution and provides an overview of the integration of AI with healthcare, its components, impact, and challenges. AI in healthcare is a vast topic with lots of subdomains involving the components of AI, each contributing to specific needs in the healthcare processes. The chapter has briefed upon the role of each AI component in addressing specific healthcare problems in relation to the datatype used. Possibility of AI integration with traditional medicine and its promising role in drug design with respect to the unprecedented rise in new diseases is also discussed. As an end note the chapter also discusses the impact, risks, and challenges associated with AI and the future role of physicians. AI undoubtedly has induced an unfathomed revolution in the field of healthcare decision support and delivery systems. However, it also requires a lot of fine-tuning adding more explainability and reliability to the outcome of intelligent models to surpass the need of human intervention.

Mutating medicine takes a vital role in precision medicine. Precision medicine enables customization and personalization of healthcare technology. Advancements in machine learning, deep learning and soft computing-based intelligent system techniques can support and improve the process in precision medicine. The machine learning-based supervised learning algorithms take training data and perform classification or prediction according to the application. It supports precision medicine and mutating medicine with improved accuracy and performance in prescribing the medicine. The proposed method uses logistic regression-based machine learning model for mutation classification in order to discover precision medicine. Logistic regression is the well-known machine learning-based statistical model for classification. The logistic regression-based method proves its efficiency by comparing it with other state-of-the-art machine learning and deep learning classification models. Based on the obtained result the proposed LRBMM model performs well in mutation classification. Applying machine learning techniques made significant improvements in precision medicine.

The healthcare system has moved from post-World War II to revolution. It focuses on infectious diseases and occupational accidents that require temporary interventions. Today’s main goal is to prevent and effectively treat chronic diseases. Healthcare productivity lags behind other service industries as these goals change. The future health ecosystem, like any other ecosystem, will focus on the consumer, which includes effective patient treatment and the healthcare workers. The skills and services that will make up the future health ecosystem include medical imaging modalities integrated with traditional care, home and self-care, patient involvement, self- and virtual care and use of telemedicine (remote monitoring) that can be increasingly provided near or at home. Social care and networks related to the patient’s overall health, with an emphasis on community problems of unmet needs, are taken care too. Patient behaviour and habits that enable well-being and health, including fitness and diet, are also seen as essential elements. The expansion of wearables and the lack of skilled nurses have increased the need for automated, real-time, personalized designs for the medical care of inpatients. Such designs require proficiency in chronic disease management, surgical methods, after care and mental health. Machine learning (ML), artificial intelligence (AI) and data science are everywhere. While data science, machine learning and artificial intelligence are separate tools, when combined together they are powerful, and using them hand in hand is transforming the way we manage the large inflow of medical data and can transform the healthcare into a new medical revolution.

The number of patients with restricted movements and contacts increased due to COVID pandemic. Realizing the value of BCI (the brain–computer interface), we have come up with the idea of building a device that allows people with physical disease or disabilities to access their minds and use their active alpha cerebral signals to move an object. For this, we decided to make a toy car as a movable application in our project, which is interconnected wirelessly with the cerebro headset that takes control over our brain signals. Henceforth, we have decided to build a cerebro, enabling mobility through wheelchair for the affected people.

Human lives are very precious. Human body parts are affected due to various food habits, environment, social habits, hereditary health issues and many more. One of the most well-known disorders is liver cancer. Liver cancer causes major loss to human lives. Early detection of this can be curable at the initial stages. Due to the advancement of computer vision algorithms and progression of IoT technologies working along with image processing techniques, early detection and curing are inevitable. To improve the classification time with faster duration which can help the medical practitioner, lesion detection algorithms are developed. The work’s key contribution is to apply efficient image segmentation algorithms along with powerful deep learning algorithms to classify the cancerous lesion efficiently. This ensemble or hybrid technique is developed by combining the morphological operations and deep learning procedures for an automated liver cancer prognosis and diagnosis. This fully connected network with U-net architecture improves the classification accuracy. Also increased true positive rate is achieved in the proposed methodology with high sensitivity. This novel work achieves high classification accuracy with minimum time. In addition, it also improves the area under curve region. Work was experimented with open-source datasets as well as with mobile few clinical images.

Nowadays, cardiac problems are one of the significant reasons for loss of life globally. Prompt and powerful diagnosis of heart disease plays an essential role in the department of cardiology. In this paper, we propose a technique that is aimed at figuring out the most effective method of forecasting cardio hypotension and to analyzing aerobic disease. Here, a hybrid random forest with linear model is used to improve the detection accuracy of cardiac problems. This linear model uses a hybrid technique to find a system’s structures by observing a set of rules. Parameters such as accuracy, sensitivity, and specificity of the algorithm are measured. The findings of the proposed method have a higher potential for prediction than previous methods. In addition, this method provides accuracy of 89.01%, which might also be more robust.

Health is a vital factor for the proper functioning of the various organs in the human body. Moreover, it is directly associated with the quality of life of humans in their habitats. This central idea of the role of health was persistently emphasized by many biologists and philosophers of ancient times. Eventually, global and national organizations like the World Health Organization (WHO), Centre for Disease Control and Prevention (CDC), National Health Service (NHS), and ICMR (Indian Council of Medical Research), dedicated to monitoring the health and diseases of humans, came to be established. The epidemiology of various human diseases could be traced mainly because of the massive surveillance operations conducted by these organizations. Rational therapeutics, developed after the boom in appropriate diagnostic techniques, successfully replaced irrational treatment elixirs. This chapter dwells on human health and a selection of prognostic and diagnostic procedures for the identification of diseases. The concepts of molecular, biopotential measurement and imaging techniques used in the diagnosis of various diseases and malfunctions are discussed herein. Techniques used for the identification of diseases at the molecular level, biopotential techniques used for recognizing abnormalities in signal transduction within the nervous system and imaging techniques used in the prediction of disease with images generated from affected organs are some of the breakthroughs achieved in the detection of a disease.

Changes in healthcare is important because if changes in healthcare fail to provide desired results. High-quality healthcare helps prevent diseases and improve quality of life. Bioethics is the study of the ethical issues emerging from advances in biology, medicine, and technologies. The National Commission for the Protection of Human Subjects of Biomedical and Behavioral Research was initially established in 1974 to identify the basic ethical principles. The decision of any policies associated with health and treatment services eventually affects patients’ lives, patient participation in health affairs and the development of macro health policies. This will lead to consideration among people’s civil rights: bioethics, genetic counselling and research, involvement of patient or public in healthcare systems, epidemiological evolution and its types, and evaluation of matrix clearing explaining the way and the procedure for impacts of healthcare intervention.

Atherosclerosis is one of the major cardiac diseases that affect a huge population all over the world leading to myocardial infarction (heart attack) and apoplexy (Eason G, Noble B, Sneddon IN, Series A, Mathematical and Physical Sciences. 247:529–551, 1955). Early disorder is due to deposits of fatty material or atheroma causing blocked blood flow and plaque formation. If there is a rupture of the plague in the carotid conduit, it typically leads to cessation of neural tissue (stroke) or myocardial infarction. Studying the hemodynamic of the blood vessels can determine the important factors for the local distribution and the development of vascular plaques. Experimental studies of the vascular replicas by idealized models have not been efficient where vessel geometry construction was an issue. Computational fluid dynamics (CFD)-fluent is used to build model to study the hemodynamic, wall shear stress distribution, and streamline patterns through stenosis; the pathophysiological and hemodynamic changes in the walls could provide more estimate on the degree of the disease.

Therapeutic merchandise comprising an instrument, contraption, apparatus, material, or along with any extras or programming is expected for the treatment. Therapeutic mediations can possibly give beneficiaries past species-ordinary body-related capacities [therapeutic upgrades, therapeutic equipment (TE)]. We trust that the powerful coincidence of TE, the change in capacity assumptions toward past species-ordinary body capacities, and the expanding want of well-being buyers to shape the well-being framework will progressively impact different parts of medical care practice, strategy, and grant. PCs are, in effect, progressively utilized in clinical calling. There are various degrees of point of interaction between medication and PC technology. Computer offices are presently viewed as necessary for much therapeutic hardware. Significant employments of PCs in medication incorporate clinic data framework, information investigation in medication, clinical imaging research center processing, PC-assisted clinically independent direction, care of fundamentally sick patients, PC-assisted treatment, etc.

Machines’ conceptual intelligence is built on the foundation of soft computing. The goal is to take use of tolerance for imprecision, ambiguity, approximate reasoning, and partial truth in order to create a close likeness to human decision-making. Soft computing is the study of reasoning, thinking, recognizing, and evaluating problems in the real world using biologically inspired methodologies. There are no mathematical models accessible in many applications, and they are impossible to use. Mathematical models don’t always provide the most accurate or precise results. Soft computing, on the other hand, establishes techniques such as neural networks, evolutionary computing, fuzzy logic, genetic algorithms, probabilistic reasoning, and statistics that are ideal for those situations. This chapter focuses on various soft computing approaches and their applications.

A non-invasive technique for skin cancer diagnostics that reliably classifies lesions as malignant or benign is analyzed and preferred using machine-learning and deep-learning algorithms. The different stages of diagnostics involve using machine learning: a collection of data images, filtering the images to remove unwanted details and noise, segmenting the images using various clustering algorithms. Feature extraction methods have been used to accomplish classification. Five distinctive classifiers have been trained and their efficiency has been compared. K-nearest neighbor, support vector machine, decision trees, multi-layer perceptron, and random forest are used to classify the skin lesion as malignant or benign. An effective comparison of two different deep-learning architectures, such as AlexNet and GoogLeNet, has been carried out. The dataset, which contains 900 images, is subjected to various identification techniques. The accuracy, F-measure precision, and recall were used to evaluate the effectiveness of the classification scheme. As a result of the findings, when compared with the random forest classifier, AlexNet has a high accuracy of 95%. The number of training samples seems to have a serious influence on the ability of deep-learning strategies. Although having a small number of training samples, the presented scheme was able to precisely discriminate among healthy and diseased lesions. Hence, the proposed method will enhance the effectiveness of early detection for skin cancer and could be used in computer-assisted systems to help dermatologists discover cancerous lesions.

There are many causes of cancers. There are many areas which are working for precise cancer treatments. It is a very complex disease and difficult to cure. There are different categories of cancers, diagnosed and located in different organs of the body sub-tissues and originating from different cell types. Cancer is categorized based on their molecular arrangements. In addition to this, they look different based on the location and stage of the cancer. Instead of complication and appearance, almost all types of cancer are treated with the same generic therapies. The objective is to reduce the effect of cancer, and to cure, it needs to be identified and treated at an early stage. There are four elements of cancer diagnosed at an early stage: physical exam, laboratory tests, imaging tests, biopsy tests, etc. If cancer is diagnosed at an early stage and proper screening is done, then only the death ratio can be reduced. I have tried to cover the positive impact of PCM (Precision Cancer Medicine) to improve the cancer care with less harm to healthy tissue.

Fighting cancer is a life-time challenge for the cancer patient. Early prediction and diagnosis of cancer may extend the survival rate. The advent of artificial intelligence in medicine, especially in oncology, finds a new hope in cancer research. This chapter gives an insight into imaging techniques in cancer diagnosis, biopsy, and biomarker available for breast and lung cancer. Also, accombining data analysis with computer-aided techniques gives precise result and work on mass data. Evolutionary techniques, along with neural networks and data mining techniques, give improved localization of cancer detection. Particle Swarm Optimized Wavelet Neural Network is effective in spotting mass in mammogram images. Treatment methods of breast cancer, which includes chemotherapy, radiation therapy, is disclosed.

The aim of this paper is to put forth steps to kindle research interest in health care. Health care with artificial intelligence (AI) techniques brings about the e-health system. This research article comprises cancer diagnosis and therapy using AI techniques. Mutations and AI can be applied over the problems to get the end result. The article also shows the techniques used in the diagnosis and therapy of cancer. The graph network particles are passed over the human body. The images are captured and stored in the database as a dataset. This can act as an input for the pre-processing stage. Features extraction is the next step. The neural network is used as a classifier to classify the abnormal and normal cells. Finally, this acts as an input for predictions of other patients. This is an eye-opening article on the advancements in the health care system. This paper describes the research methodologies that can be applied over the detection of the cancer cells. To study the research methodologies that can be applied over the detection of the cancer cells. This paper presents the two major classification algorithms for predicting cancer. Based on the experimental results, the decision tree and neural network classifiers improve the accuracy in the detection of cancer. The results obtained by comparing the decision tree and the artificial neural network (ANN) show that the ANN gives better accuracy than the decision tree. The datasets collected are pre-processed and the respective features are extracted from the dataset. Based on the experimental results, the ANN classifier gives a better outcome than the decision tree.

Nowadays, a new smart approach is required to maintain confidentiality and seclusion of Electronic Health Records (EHR) of patients using a multimodal biometric authentication system. To authorize access to medical records, multimodal-based encryption solutions require the patient to be present at all times. Because there are known cases where patients’ health data have been stolen and misused, patient privacy and confidentiality is a big issue in EHR. Another challenge with EHR is how to give proper therapy while also having access to relevant information, particularly in pre-hospital settings. As a result, the system was created to access patient records in the hospital utilizing multimodal biometrics of patients. Cloud computing and SQL databases were used as software tools. By restricting the amount of data available to users, the system safeguards privacy and confidentiality while yet providing reliable access to critical aspects of patients’ EHR data via patient fingerprint and voice recognition.

The clinical management of cancer data storage for cancer treatment, analyzing cancer outcomes, providing services for cancer care, accurate measurement for research in future prediction, treatment history, and comparative future research work, plays a very important role in precision cancer health care. However, cancer stage data registries are often found to be inaccurate, missing data, or data are not collected perfectly. To perform all these tasks the need for manpower increases. Therefore, centralization in monitoring and analysis of cancer patient records is an important role in order to have periodic analysis of patients’ history. There are various details on the cancer patient such as individual personal details, cancer stage details, level of growth, and type of treatment in progress. There is also very specific information called quantitative data that are generated from the radiomic features of the patient, which show the specific medical condition and diagnostic features in cancer imaging data and need to be updated periodically. Personalization of cancer patient data, the treatment of every individual, plays an important role in analytics. Data need to be saved for the best treatment options for every individual in the future. However, the processing of the entire sequence of information periodically seems to be a tedious procedure. In order to provide quality medical care and better service to the patients and to reduce the level of medical expenses a software bot called Robotic Process Automation has been introduced that has the ability to solve a problem by training the machine itself using the historical data of the patient, which can be either supervised or unsupervised. The bot supports replacing normal repetitive routine performed by skilled workers with a highly automated procedure. Robotic health care automation allows similar processes to be automated and reused, and can monitor the status of clients accurately and identify situations. Precise medicine is testing tumors at the right time, at the right stage, and to provide the best treatment.

Communication is an essential process for the interchange of information. Communication with doctors takes various forms such as medical image transaction, monitoring of vitals using communication devices, which is a part of telemedicine. Persistant well-being observance is of significant help, and it explicitly gives the older and persistently sick patients with nonstop and consistent well-being checking, benefiting the two of them and the caretakers. This chapter highlights various technologies involved in telemedicine, especially PACS and standards used in communicating medical data. This chapter also highlights the different wireless technologies used in telemedicine, especially 6G technology. Medical services will be completely AI-driven and subject to 6G correspondence innovation, which will change our impression of way of life.

The advancement in medicine and healthcare system has prompted a greater focus on platform development, both at software and hardware levels. The fundamental technology consists of systems for communication established between the sensory nodes and the controlling unit, and the algorithms that process the collected data for interpretation of the result. The advent of artificial intelligence (AI) technology which includes machine learning (ML), deep learning (DL), neural networks (NN), and fuzzy logic changed the approach of healthcare system. These technologies enable healthcare in processing health records, diagnosis of the disease, and therapeutic procedures. This chapter investigates the current trend of computational techniques used in healthcare as well as the future pathway of such technologies. The impact of machine and deep learning procedures in clinical care is briefed. The advanced computational intelligence techniques used in applications such as clinical imaging, e-health records, and genomics are also investigated. This chapter concludes with a brief study of cases on the application of data mining in processing the brain tumor health record and the implementation of AI in automatic stress detection through the data recorded by wearable sensor devices.

In more ways than just one, health care facilities have altered dramatically during the previous 20 years. They have entirely transformed from their previous state to their current state. Patients’ and society’s requirements have changed, technology is more advanced than it has ever been, and health care costs are decreasing. Another essential point to consider is the advancement of health care information systems in medicine and informatics. All of the changes that have occurred in health care facilities have impacted not only the patients but also the personnel and the communities. As health care organizations and delivery models evolve, so do personnel roles, responsibilities, and training requirements. The health care industry has historically been an early adopter of technological improvements and has reaped significant benefits. Patients are now able to access a specific website where they can talk freely with a physician. After joining and interacting with a physician, the patient is able to explain their symptoms to the physician via instant messaging or email, and then wait for a physician to reply to their concerns. Machine learning (an artificial intelligence [AI] subset) is being used in a variety of health-related fields, including the invention of new medical treatments, the management of patient data and records, and the treatment of chronic diseases. Other potential machine-learning breakthroughs in health care include looking into methods to employ the technology in telemedicine. The assumption that AI and related services and platforms would revolutionize global productivity, working patterns, and lifestyles, as well as create massive wealth, is well-established. These computational techniques are capable of analyzing enormous amounts of data maintained by health care organizations in the form of photographs, research trials, and medical claims, and identifying patterns and insights that are typically invisible by integrating human skill sets.

Corona virus is a pandemic that posed a universal threat and is still predicted to reach new heights as the situation demands. We investigate the methods used for diagnosis, prognosis, and rehabilitation of Covid-19-affected persons in depth. Based on the procedures used, the methods were given a thorough examination and analysis was presented. All the potential methods were discussed in detail and common challenges among them were also elaborated. Finally, we’ve suggested some challenges and potential future routes that researchers and healthcare professionals should take in order to deal with any outbreaks of similar nature.

Conventional drugs are mainly used in elderly people and they use herbal medicine as a substitute to improve the treatment of chronic disorders. Yet, it is critical to survey whether this home-grown medication makes the huge impact of a regular medication or the other way around, as this can prompt different unfavourable impacts. To get to an evidence-based, esteem-driven wellbeing framework we need to adjust every one of our expert instructive projects to show new frameworks and abilities. Artificial intelligence (AI) is emerging in the health care field focusing on the prognosis and diagnostic methods: exploring the unease of conventional medicine and mutating medicine using intelligence; understanding the evolution of health care techniques (prognosis and diagnosis) and novelty in emerging soft computing. AI computer frameworks are utilized widely in the clinical sciences. Normal applications include diagnosing patients, start to finish drug disclosure and improvement, further developing correspondence between doctor and patient, translating clinical archives, medicines, and remotely treating patients. AI will uphold the future necessities for medication by examining the immense sums and different types of information that patients and medical care foundations record every second. Although AI is probably not going to supplant doctors soon, it is functionary on clinical experts to learn both the essentials of AI innovation and how AI-based arrangements can help them at work in giving better results to their patients. The above constraints notwithstanding, AI looks very much situated to upset the medical services industry. Computer-based intelligence additionally has the capacity to remotely diagnose patients, subsequently extending clinical benefits to distant regions, past the major metropolitan places of the world. The eventual fate of AI in medical care is brilliant and promising, but much still needs to be achieved.