The Internet of Things (IOT), wearable computing, and recent advances in sensor technology have stimulated research into ubiquitous healthcare, remote monitoring of people’s health, and monitoring of people’s health, as well as monitoring of patient health and activities. Health monitoring systems gather and analyse data obtained from smart phones, smart watches, smart bracelets, and other wearable’s and sensors. These devices provide ongoing monitoring of the psychological and physical problems that patients are experiencing by sensing and transmitting data such as blood pressure, heart rate, ECG, respiration rate, chest sounds, and heart rate. Pervasive healthcare is an important application area in this context since it aims to revolutionise the delivery of medical services by fostering patients’ independence in a medically supportive environment. The five subjects covered in this chapter are: (1) Large medical data analytics for remote health monitoring; (2) models, methods, and solutions for medical data processing and analysis; (3) big medical data analytics; (4) research problems and possibilities in medical data analytics; and (5) examples of case studies and workable solutions.
Recent advancements in sensor technologies, wearable computing, the Internet of Things (IOT), and wireless communications have sparked research on mobile and ubiquitous health care as well as remote monitoring of people’s health and activities. Health monitoring systems process and analyse data gathered from smartphones, smart watches, smart bracelets (also known as wristbands), as well as other linked sensors and wearables.
These gadgets enable continuous monitoring of patient’s psychological and physical conditions by recording and sending measurements including blood pressure, body temperature, respiration rate, electrocardiogram (ECG), and heart rate. The gathering, integration, and analysis of sensor data is essential for the diagnosis and treatment of patients with chronic illnesses (such diabetes and hypertension) as well as the supervision and care of the elderly.
Health informatics is studied by academics from many different academic fields, including computer scientists, physicians, mathematicians, statisticians, and sociologists. They all share a connection through sociology, marketing knowledge, and computer science (which includes simulations and data analysis) (such as, apps dissemination and social interventions). Models that are mathematical or computational can help us understand processes that are important to health (such as differential equations or system dynamics). For instance, to better determine the risk to patients, sensorics data gathered from contacts with individuals can be included into models of infectious diseases. The main challenges and future directions are covered in this chapter with regard to the gathering, modelling, and processing of medical data in the context of monitoring human health and behaviour. To show how the principles and technology discussed are applied, three case examples are given. The first case study presents a Big Data strategy for remote patient monitoring those accounts for the challenges.
In medical billing, data entry process is a part of computerization. As it takes the companies health care in the direction of superior operational efficiency, harmless, and approachable. Paper trails are turn off into a more feasible, firm, and precise electronic system, health care data entry permit to efficient information flow in the administration, grasp inventive medical technology greater and operate financial gain through component-based perception.
Medical Information Gathering:
Medicine has long tried to quantify specific patient traits in order to understand a patient’s health and illness (such as the clinical image). Afterward, computer science models would take the results of these experiments, observations, and measurements into account. Even while the use of IT in medicine has lately grown quickly, models of such systems, particularly register-based models, still lack real data.
Blockchain for Security and Privacy:
Drug traceability in multi-actor systems is where blockchain technology is most commonly used in medicine. This technique has already been applied to validate the provenance of medications in Sub-Saharan Africa and South-East Asia (fake drugs are big problem there). The traceability of goods in the supply chain with regard to storage and transit characteristics is crucial in food-borne outbreak investigations, and blockchain technology can be useful in these cases as well. Fusion of data
The goal of data fusion (DF), a multi-domain emerging discipline, is to provide knowledge for scenario interpretation. The security of facilities and threat detection are some of the major DF research areas on a global scale.
All organisations that collect, manage, and keep medical data are required to improve their data protection procedures in accordance with national and international regulatory standards. A data protection law required by the USA is the Health Insurance Portability and Accountability Act (HIPAA), which is used for compliance and the secure adoption of electronic health records Footnote.
Because real-world datasets are essential for the processing and analysis of sizable and complete personal health and activity information, several attempts have been undertaken to construct big and representative examples of these datasets.
The techniques and results of data analysis and collecting may have an impact on e-usability health. To analyse different types of data sets, several strategies must be applied (survey, diagnosis and testing, time series, geographic, panel, longitudinal data, etc). (Regressions, Decision Trees, Modelling of Structural Equations, Social Network Analysis, Modelling using Agents, Machine Learning, etc.)
It is possible to use and find inexpensive, low-power electronic devices. Although some traits, like body temperature and blood pressure, may be precisely captured, developers are aiming for an expanding number of features. The FDA (Federal Drug Agency) and EMA have certified digital health software and equipment (European Medicines Agency). The bulk of items on the market don’t adhere to the basic standards for certification and accreditation.
Open source IOT platforms can be used as an alternative. Although Thinger.io is still a relative newcomer to the IOT space, it is extensively utilised in a variety of research projects and even in schools. However, it is also possible to instal the software locally for private, unrestricted management of linked devices and data. There is a free tier available for connecting a limited number of devices.
As the ideas of remote health monitoring and pervasive healthcare have developed, more research has been published on a variety of topics, including theory, concepts, systems, and applications of Big Medical Data Systems for healthcare services.
A mobile device (phone, watch, bracelet, etc.) or a local computing infrastructure, such as an IOT gateway or a home/hospital server, can be used to analyse data and identify health problems using edge computing concepts.
The concept of IOT healthcare systems has attracted the attention of many researchers as the Internet of Things (IOT) has evolved.
In the context of IOT for medical purposes, the fog and edge computing paradigms may offer particular benefits. They represent a model where sensitive data generated by smartphone sensors and body-worn medical devices is processed, analysed, and mined locally on these devices rather than sending vast amounts of sensor data to the cloud, which could exhaust network, processing, or storage resources and violate user privacy.
Fog computing takes use of virtualization technologies to support multiple application tenants and create flexibility in massively shared resources. Virtualization and application partitioning methodologies are the two primary technology solutions used by a fog computing platform.
We considered all the difficulties associated with health/activity monitoring data and control flows that should be implemented in a public, private, or hybrid cloud when designing the Remote Health Monitoring system architecture and implementing the system suited to analysis of mobility data for healthcare purposes. Ad Hoc Network for Smartphones (SPAN) for e-Health Applications We provide a method in this part to facilitate distributed traveller health monitoring. For the time being, let’s assume that a travel agency organises mountain climbing trips to places like Kilimanjaro. The organisation provides the guide and the participants with sensors that monitor health conditions (heart rate, blood pressure, body temperature, etc.) so it can maintain tabs on their wellness while it develops the best possible policy.
In accordance with client needs, our data processing experts may also convert previously organised data into knowledge that can be categorised, evaluated, and studied contextually. We thoroughly and accurately clean, extract, assemble, de-duplicate, filter, validate, and process all medical claims and bills while maintaining the security and confidentiality of all data using a variety of technologies and processes.
In order to comprehend the amount and data within documents that need to be digitised, we examine and interpret your needs.
EMR use has increased thanks to the evolution of digital data (Electronic Medical Records). However, competent medical data entry services are also required. This crucial task forms the core of the patient’s whole medical “picture.” Patient data entry in the healthcare industry covers patient records, drug records, instrument records, medical diagnosis, healthcare organisations, hospitals, clinics, pharmaceutical companies, and physicians.
With roots in antiquity as far back as Egypt, Greece, and Rome, medical records have a very lengthy and distinguished history. Ancient stone tablets are our earliest proof of the practise of medicine, much as today we only have medical records to show that an operation or attempt at a cure has actually occurred.
M- and e-health innovations have already been adopted into clinical practises for the twenty-first century, and health informatics is a well-established scientific field. Digital medicine can optimise decision-making procedures and precise/personal medicine due to its low-cost capacity to analyse a large quantity of data. It’s possible that using computer-assisted decision-making tools is safer and more efficient than using “analogue” procedures that include a doctor.
In this chapter, we looked at the following subjects:
(1) Issues with data collection, fusion, ownership, and privacy; (2) Models, technologies, and solutions for medical data processing and analysis; (3) Big medical data analytics for remote health monitoring; (4) Research opportunities and challenges in medical data analytics; and (5) Future directions for medical data analytics.
three case studies.
The first case study addressed a Big Data strategy for remote patient monitoring that considers the challenges of monitoring patients’ health and activity. A system designed to enable widespread traveller health monitoring was briefly discussed in the second case study. The use of machine learning to supervise dementia patients’ everyday activities was covered in the third case study.
Apache Kafka : A distributed streaming platform. https://kafka.apache.org/
Apache Spark: Lightning-fast cluster computing. https://spark.apache.org/
Apache Zookeeper. https://zookeeper.apache.org/
How useful was this post?
Tasks handled by our staff, updated in real-time.