|Year : 2022 | Volume
| Issue : 7 | Page : 402-405
Smart health-care systems for rheumatology
Suneeta Mohanty, Prasant Kumar Pattnaik
School of Computer Engineering, KIIT DU, Bhubaneswar, Odisha, India
|Date of Submission||16-Oct-2021|
|Date of Acceptance||11-Feb-2022|
|Date of Web Publication||01-Jul-2022|
Dr. Suneeta Mohanty
School of Computer Engineering, KIIT DU, Bhubaneswar, Odisha
Source of Support: None, Conflict of Interest: None
Smart health care comprises e-health, m-health, electronic resource management, smart and intelligent home services, and medical devices. Wireless sensors, radio-frequency identification technology, Internet of things, and machine learning (ML) algorithms are the underlying technology to implement smart health care. Sensor plays a vital role in smart health care for the collection of real-time data. Sensors such as accelerometers, wearable sensors, and thermal infrared camera sensors are extensively used to assemble data for patients with arthritis. ML algorithms are used to observe ailments and classify patients with respect to various diseases. This article presents a basic introduction to these concepts, existing smart health-care applications for rheumatology along with the pros and cons of smart health-care system. This article will help the researchers working in the field of medicine to understand the underlying technology of smart health-care systems.
Keywords: Internet of things, rheumatology, smart health care
|How to cite this article:|
Mohanty S, Pattnaik PK. Smart health-care systems for rheumatology. Indian J Rheumatol 2022;17, Suppl S3:402-5
| Introduction|| |
In the era of Internet, the idea of smart health care has constantly arisen to the forward. Smart health care utilizes the latest generation of information technologies, such as the mobile Internet, big data, Internet of things (loT), cloud computing, microelectronics, and artificial intelligence (AI) together with modern biotechnology to change the conventional treatment technique in an expert procedure, creating medical care more powerful, more appropriate, and more demonstrated. A health-care system that permits patients and clinicians to interact with one another and distantly interchange information observed, gathered, and investigated patients' day-to-day actions over the IoT. Smart health care can be described as a combination of patients and physicians onto a usual platform for smart health observation by examining the daily activities of humans. Smart health care may build up communication between each and every party in the health-care area, guarantee that parties obtain the services they require, assist the participants to build enlightened resolutions, and promote the reasonable allotment of resources. Smart health-care system comprises four layers: Sensitive layer, networking layer, data processing layer, and application layer. Sensitive layer is responsible for data collection from patients. Networking layer is responsible for fast and secure data transmission from patient's device to doctor's device. Data processing layer uses modern data analytics tools to predict and notify if the health indicators worsen. Application layer is responsible to collect the information from the output of data processing layer and to inform the doctor about the patient conditions. This helps the doctor to take timely decisions with higher precisions. Chronic diseases are generally incurable and require continuous monitoring to avoid any kind of health hazard, if the health indicators worsen. Hence, patients with chronic diseases can take the advantage of smart health-care systems to monitor and get timely treatment by the doctors remotely.
| Technologies Used for Smart Health care|| |
Smart health care is a health facility method that utilizes technology to actively acquire information, associate people, materials, and organizations linked to health care, and subsequently earnestly directs and reacts to the treatment ecosystem smartly. In a nutshell, smart health care is a more excellent platform for information formation in the treatment area.
Radio-frequency identification (RFID) system consists of both radio transmitter and radio receiver to transmit and receive digital data. From the viewpoint of hospitals, RFID technology might be used to direct personnel materials and the supply chain, applying integrated management stages to gather information and aid decision-making. It can also be used to collect data from patients.
Wireless Sensor Network
Wireless sensor network (WSN) consists of network of sensors to collect data from a real-time environment and transmit it in a wireless environment for central processing. In health-care system, WSN is useful to collect data from the day-to-day activities of patients for extensive studies to provide efficient health-care services remotely.
Internet of things
The basic technologies used in IoT are information gathering, digital data transmission, and intelligent computation. IoT represents the physical objects comprising wireless sensors for data collection and those data transmitted over wired/wireless medium with the help of the Internet for further processing. Hence, IoT can be used in providing smart health-care applications for hassle-free patient care remotely.
Cloud computing helps physicians access a large amount of data anytime from anywhere with the help of the Internet to provide efficient patient-centric services.
Machine learning (ML) is the process of developing a system to learn something with the help of algorithms and to draw inferences from a pattern of data without human interventions. ML algorithms are used to observe ailments and classify patients correspondingly in medical science. Ensemble learning is one of the most used techniques to improve a classifier's potentiality. It is a procedure through which numerous classifiers might be integrated to categorize fresh samples to enhance forecast accuracy.
AI is used to demonstrate intelligence in machine-like humans. AI in health care can be used to develop a system to analyze the complex health-care data for smart Medicare. The current American College of Rheumatology direction for the therapy of RA reveals that the remedial target is to lessen disease activity. The wide armamentarium of drugs for various rheumatic diseases including RA may be better utilized if we can harness the power of AI to provide personalized precision medicine recommendations.
Data analytics are used to analyze a huge amount of data to make effective decisions. Hence, the application of data analytics in health care helps to get the faster and personalized patient care, improved disease diagnosis, and improved decision-making.
E-health and m-health technologies comprising the above technologies enable the smart health-care system to perform efficient disease diagnosis and disease management with active patient participation. Hence, smart health-care system can be used to diagnose the autoimmune diseases in their early stages and to provide timely treatment to maintain the disease. With the advent of various analytic tools such as AI and ML, researchers are trying to gather natural history, drugs applications, and predictions for some rare diseases such as connective tissue diseases to meet the unattended needs which are still a challenge.
| Smart health-care Applications for Rheumatology|| |
Rheumatology is a sub-specialty of medicine that handles diseases of the joints, soft tissues, systemic autoimmune disorders, and inherited diseases of immunity and inflammation. Rheumatology has a significant impact on the mental health of the patients too. Procedures utilized to supervise patients in rheumatology may differ from drug therapies, physical and occupational treatment, recovery, and various adverse effects. Some smart health-care applications for rheumatology are listed below:
The IoT provides a virtual remote hospital ambiance by providing real-time updates to doctors. Doctors can supervise the conditions of rheumatic patients staying at home in online mode.
Smart disease management
Smart health-care systems are equipped with various technologies such as IoT, AI, and big data. These health-care systems are designed to send an alarm to doctors if the predicted patient's health indicators are worsened. As a result of which doctors can take effective and timely decisions to save the patients. Due to the real-time data access facility in IoT health-care devices, doctors can take decisions with higher precision. Analysis of health indicators facilitates the system to suggest whether the patients can continue their treatment remotely after discharge or not. Hence, smart health-care system can be used to reduce the patient stay in hospital physically by providing online treatment.
Smart health-care devices are designed to track the sleep record of patients. Wearable devices collect health data such as heartbeat, pulse record, and body movement from patients while sleeping through the actimetry sensors to track the sleep cycle.
Accelerometers are used to monitor the mobility rate of rheumatic patients as mobility is highly required to lead an independent life. Accelerometer can measure both dynamic acceleration and static acceleration. Falls can be a source of morbidity or death for all patients. Hence, accelerometers are used to detect falls in the case of rheumatic patients and elderly people.
Rheumatology has adverse effects on the heart of the patients. Smart health-care wearable helps the doctors to monitor the heartbeat, pulse rate, and to get electrocardiogram (ECG) reports of the patients remotely to provide an efficient lifesaving Medicare. Patients can easily measure these parameters through smart health-care wearable by pressing it against the skin. Collection and transmission of data requires no assistance.
Nowadays, many smartwatches are available in the markets which are capable of collecting various health parameters of patients and which can be shared with the doctors for timely decision-making and providing improved and personalized health-care services.
Blood pressure monitoring
IoT-based wearable devices use sensors to measure the patients' blood pressure by pressing against the skin. These data will be shared with the doctors for timely prevention of any serious health conditions such as the risks of brain, heart, kidney, and other diseases.
Glucose level monitoring
To provide optimal therapy, continuous glucose level monitoring can be done using wearable epidermal sensors.
Blood coagulation detection
Blood clotting level plays a vital role in treating diseases such as cardiac arrest, diabetes, and many more. Smart health-care applications such as blood coagulation test kits equipped with sensors are available to collect data. These data will be transferred to smartphones to calculate the blood coagulation indexes with the help of AI and ML to keep track of the blood coagulation level for timely treatment and lessens the risk factor.
Thermal infrared camera sensors
Thermal infrared camera sensors can be used as a tool to measure the inflammation level in patients.
Smart mirror equipped with 3D cameras, a weighing scale, and a mobile application is used to perform full-body scan of the patients at home. These data can be shared with the doctors for remote monitoring and timely prevention of many health hazards.
| Benefits and Challenges of Smart Health-care Systems|| |
The integration of modern-age techniques such as IoT, mobile Internet, cloud computing, AI, and ML has given a new dimension to the smart health-care systems. Real-time reporting and monitoring of patients data such as blood pressure level, glucose level, heartbeat rate, pulse rate, and ECG plot help the doctor to provide lifesaving treatment over the Internet. The physicians can get real-time data with the help of smart health-care applications which speed up the decision-making irrespective of the place and time. These data can be stored in cloud for further longitudinal studies and analysis. At the same time, smart health-care system encounters many challenges in the field of security of collected data, the accuracy of data, data overloading, end-to-end connectivity, and many more. Confidentiality of the patients' data should be the utmost priority of any smart health-care system. End-to-end encryption should be ensured while transmitting the data over the Internet to avoid data snooping which can be a passive attack. Authentication of all the entities involved in smart health-care systems can be ensured with the help of digital signature certificates. Smart health-care systems are cost-effective in terms of the advantages provided by it. It is very difficult to predict the cost of this system as it involves different types, versions, and quality of software, hardware, and service components maintenance.
| Conclusion|| |
Current techniques of determining rheumatology depend upon monitoring, questionnaire, and physical evaluation, each having its individual shortcomings. In this article, we have discussed the various technologies used for smart health-care systems. We have also given insight into the existing applications suitable for rheumatology and the benefits and challenges of smart health-care systems.
Financial support and sponsorship
Conflicts of interest
There are no conflicts of interest.
| References|| |
Bruce N, Sain M, Lee HJ. “A Support Middleware Solution for E-Healthcare System Security”, 16th
International Conference on Advanced Communication Technology; 2014. Available from: https: doi.org10.1109/ICACT.2014.6778919
. [Last accessed on 2022 Mar 30].
Pattnaik PK, Mohanty S, Mohanty S. (Eds.). Smart Healthcare Analytics in IoT Enabled Environment (Vol. 178). Springer Nature, Switzerland. 2020.
Hassani FA, Shi Q, Wen F, He T, Haroun A, Yang Y, et al.
Smart materials or smart healthcare–moving from sensors and actuators to self-sustained nanoenergy nanosystems. Smart Materials in Medicine. 2020:pp.92-184.
Islam MM, Rahaman A, Islam MR. Development of smart healthcare monitoring system in IoT environment. SN Comput Sci 2020;1:185.
Vitabile S, Marks M, Stojanovic D, Pllana S, Molina JM, Krzyszton M, et al
. Medical data processing and analysis for remote health and activities monitoring. In: High-Performance Modelling and Simulation for Big Data Applications. Cham: Springer; 2019. p. 186-220.
Mohanty S, Shekhar P, Sinha S, Poddar A, Sahu G, Dash A. RFID based patient billing automation using internet of things (IoT). In: Smart Healthcare Analytics: State of the Art. Singapore: Springer; 2022. p. 207-18.
Tarannum S, Farheen S. Wireless Sensor Networks for Healthcare Monitoring: A Review. In: Smys S, Bestak R, Rocha Á. (eds) Inventive Computation Technologies, Springer Nature Switzerland AG, 2020:pp 669-76.
Jeong JS, Han O, You YY. A design characteristics of smart healthcare system as the IoT application. Indian J Sci Technol 2016;9:52.
Dang LM, Piran M, Han D, Min K, Moon H. A survey on internet of things and cloud computing for healthcare. Electronics 2019;8:768.
Ethem A. Introduction to Machine Learning. 2nd
ed. Cambridge, MA, USA: MIT Press; 2009.
Fraenkel L, Bathon JM, England BR, St Clair EW, Arayssi T, Carandang K, et al.
2021 American College of Rheumatology guideline for the treatment of rheumatoid arthritis. Arthritis Rheumatol 2021;73:1108-23.
Belle A, Thiagarajan R, Soroushmehr SM, Navidi F, Beard DA, Najarian K. Big data analytics in healthcare. Biomed Res Int 2015;2015:370194.
Haroon N, Aggarwal A, Lawrence A, Agarwal V, Misra R. Impact of rheumatoid arthritis on quality of life. Mod Rheumatol 2007;17:290-5.
Shenoy P, Ahmed S, Cherian S, Paul A, Shenoy V, Vijayan A, et al.
Immunogenicity of the ChAdOx1 nCoV-19 and the BBV152 Vaccines in Patients with Autoimmune Rheumatic Diseases. medRxiv 2021:pp-1-8.
Mohanty S, Mohanty S, Pattnaik PK, Vaidya A, Hol A. Smart Healthcare Analytics Using Internet of Things: An Overview. Smart Healthcare Analytics: State of the Art, Springer Nature Switzerland, 2022:pp.1-11.
Li C, Raghunathan A, Jha NK. “Hijacking an Insulin Pump: Security Attacks and Defenses for a Diabetes Therapy System”, 13th
IEEE International Conference on e-Health Networking Applications and Services; 2011. p. 150-6.
Ren Y, Chen Y, Chuahy MC. “Social Closeness Based Clone Attack Detection for Mobile Healthcare System”, IEEE 9th
International Conference on Mobile Ad-Hoc and Sensor Systems (MASS 2012); 2012. p. 191-9.