Real-time Vital Signs Monitoring and Data Management Using a Low-Cost IoT-based Health Monitoring System

Abstract

This study describes the creation and evaluation of a low-cost internet of things (IoT)-based health monitoring system for the continuous monitoring of vital signs such as temperature, pulse rate, oxygen saturation (SpO₂) and blood pressure (BP) (both systolic and diastolic). Along with an organic light-emitting diode (OLED) display and an ESP8266 microcontroller, the system includes BP, non-contact temperature, SpO₂ and electrocardiogram (ECG) sensors. Using the visual programming tool, Node-RED, the data from these sensors are gathered, processed and transmitted to the Google Cloud platform for archival and visualisation. The process involved mounting the sensors and microcontrollers on a special printed circuit board and designing the circuit with EasyEDA. The device measures systolic, diastolic and pulse rates from the BP sensor, as well as temperature, ECG and SpO₂ values. The system works by using three push switches to read and display these values on demand. The gathered data are simultaneously shown on the OLED and sent to the Node-RED dashboard, where it is then sent to a Google Spreadsheet for archiving and analysis. This research article gives a thorough overview of the health monitoring system, the way it was implemented, and how it was successfully validated in a real-time setting. This study examines certain vital signs but additional health measures, such as respiration rate or glucose monitoring, could be included. Machine learning algorithms could also be used for predictive analytics. This would uncover data anomalies and trends early, improving healthcare management.

Keywords

Organic light-emitting diode blood pressure sensor non-contact temperature sensor oxygen saturation electrocardiogram sensor Node-RED Android app

Introduction

Over a billion individuals worldwide have hypertension and coronary artery disease, which can directly or indirectly lead to life-threatening implications like congestive heart failure, other cardiac rhythm irregularities, heart attacks, strokes and damage to the kidneys. A patient may be put at risk by treatment errors or delays related to these abnormalities. The health of these individuals must thus be monitored, and any odd circumstances must be immediately reported to the physicians. There is an increasing interest in creating novel solutions for real-time health monitoring due to the rising prevalence of critical diseases and the growing need for efficient healthcare monitoring systems. System that tracks your health continuously may be a solution to this problem. However, they frequently come at a high price and have a number of restrictions, such as the inability to provide sophisticated services like real-time notification or remote monitoring. The Smart Health Monitoring System uses internet of things (IoT) technology is a cutting-edge approach that may be employed by medical professionals to timely identify and warn the patient’s abnormalities in real-time. It is common practice to collect biomedical signals from an individual’s body and wirelessly transmit them to monitor vital indicators. These sensor devices are compact and have constrained resources, such as inadequate power supply. As a result, it is critical to attain a certain level of energy efficiency in sensor devices. While retaining the high quality of signals, it is difficult to drastically lower the power consumption of sensor devices. Additionally, data capture and wireless transmission need a lot of power when high-resolution signals are required. We propose an innovative low-cost remote health monitoring system to lower the cost of healthcare and boost the quality of healthcare services. This research article developed and validated a low-cost IoT-based health monitoring system that offers accurate and reliable health data in real-time. IoT-based systems integrate a range of sensors, microcontrollers and software platforms. The system integrates an ESP8266 microprocessor with a variety of sensors, including an electrocardiogram (ECG) sensor, a pulse oximeter (oxygen saturation (SpO₂)), a non-contact temperature sensor and a blood pressure (BP) sensor. The system additionally employs an organic light-emitting diode (OLED) display to provide real-time feedback to the user. To efficiently handle, store and analyse data, the Google Cloud platform and the visual programming tool Node-RED are used together.

Figure 1.

Hardware Developed for Real-time Health Monitoring System.

This work provides insight into the development process for an IoT-based health monitoring system using EasyEDA to develop circuits, adding microcontrollers and sensors onto a specific printed circuit board (PCB), and creating software for the Arduino Uno platform. The system’s functionality is also provided, in addition to the push button user interface and data display.

The study also emphasises the value of uploading the gathered sensor data to the Node-RED dashboard and archiving it in a Google Spreadsheet. This enables timely interventions and improves healthcare outcomes by enabling healthcare professionals to perform data analysis and remotely monitor patient’s vital signs. To summarise, the key contributions of this work are as follows:

A design of an efficient low-cost IoT-based health monitoring system for tracking vital signs in real-time in patients with serious illnesses.

Accurate and dependable data collection is made possible by the integration of numerous sensors, microcontrollers and software platforms for accurate health monitoring and its suitability for remote patient care by validating its readings against hospital-grade equipment.

To integrate the proposed healthcare system with Node-RED and Google Cloud, which enables effective data management and analysis for the early detection and treatment of life-threatening diseases.

Related Work and Motivation

The IoT technological possibilities have sparked considerable curiosity. The majority of IoT applications acquire data using various types of sensors and microcontrollers, which are then sent locally onto the Cloud. In the context of remote health monitoring systems for persons living in rural areas, IoT offers prospective opportunities for faster medical treatment and improved patient care.

Zeadally et al. (2020), Yang et al. (2020) and Aiswarya et al. (2021) studied the difficulties and potential solutions in smart healthcare using IoT and big data analytics. They emphasise the need of using IoT technology to solve healthcare challenges. One of the challenges is the demand for cost-effective monitoring systems.

Tunc et al. (2021), Poornima et al. (2022) and Ntehelang et al. (2019) investigated the upcoming IoT technologies in smart health research using knowledge graph analysis. They provide information about the emerging IoT landscape in healthcare. Offering a realistic application of IoT-based health monitoring contributes to the changing adverse weather and environment conditions. Hence, this study lays the groundwork for understanding the potential of IoT technology, complementing the real-world application aspects of performing tasks.

A survey on IoT-based big data analytics in the healthcare sector will be carried out by Mehmood et al. (2019), Gill et al. (2019) and Ahmed et al. (2018). They explore how data analytics may be used to extract valuable information from healthcare data. As data from the device you use is sent to Google Cloud for archiving and visualisation. Their study highlights the importance of data analysis, which may be expanded to include predictive analytics, in healthcare

IoT. The deployment of machine learning in IoT healthcare is examined by Li et al. (2021), Zamolodchikov et al. (2016), and Gaubert and Chainay (2021). This study is essential as it sheds light on how machine learning may enhance the performance of IoT-based healthcare systems, which is compatible with the future trends outlined.

Rather et al. (2021), Rodrigues et al. (2014), Troncone et al. (2016), Bachurin et al. (2017), Bar-David (1999), Baldeiras et al. (2018) and dos Santos et al. (2018) carried out an in-depth investigation of IoT-enabled smart healthcare, examining new technologies, applications, obstacles and future trends. It contributes to the more substantial discussion about IoT’s role in healthcare by demonstrating the use of IoT-based health monitoring in reality.

Abbate et al. (2014), Avvenuti et al. (2009), Abbate et al. (2010) and Baldeiras et al. (2018) studies demonstrated the objectives of the IoT for remote patient health monitoring by employing microcontrollers, sensors and Cloud-based platforms. Acquiring meaningful insights through data collection, analysis and remote real-time access enhances healthcare results. Despite these studies, dos Santos et al. (2018), Abbate et al. (2014), Masood et al. (2023), Gao (2023), Wang et al. (2023), Haque et al. (2023), Venkatraman et al. (2023), and Belgaum et al. (2023) discussed the benefits that patients cannot make use of all the parametric support provided by a single framework. The main reason for doing this study was to find a solution to this problem. The study performed by Rajagopal et al. (2023), Belfiore et al. (2022), Küçükönder and Görçün (2023) and Ebrahem et al. (2023) in literature describes the environmental and health indicators that were examined using a single approach as well as using statistical data analysis.

Health Monitoring IOT-based System Architecture

The objective of this work is to develop a prototype model to solve the challenges patients have while attempting to track their body temperature, heart rate, oxygen levels and environmental conditions. To do this, a whole system made up of hardware and software programs was developed using Arduino Uno and ESP8266-NodeMCU devices. In order to make data processing and analysis simplified, a spreadsheet was used along with the data collected, which was then sent to and kept on platforms like the Node-RED IBM cloud. A complete framework for monitoring and assessing crucial environmental and health aspects for patients is provided by this proposed model.

Hardware Description

The proposed model’s hardware incorporated NodeMCU and Arduino microcontrollers with an intelligent health monitoring system that was developed using the Arduino IDE. The NodeMCU, commonly known as ESP8266, is based on the low-cost System-on-Chip (SoC), whereas the Arduino Uno is an open-source microcontroller board based on the Microchip ATmega328P. In the presented model, IoT applications are controlled by master and slave approach. Master–slave protocols enable the networked devices to exchange data correctly by using lower-layer services. The NodeMCU acts as the master device in our setup and controls the majority of the sensors.

The vital information, namely BP, body temperature, oxygen level and pulse rate, were tracked by the BP sensor, temperature sensor and SpO₂ sensor that were attached to an Arduino Uno. The system also used an OLED display which is an indicator of health vital sign that shows real-time information and feedback (Figure 1). Figure 2 depicts the hardware circuit architecture for the proposed prototype model for studying patients’ health conditions and details of the components used are described in Table 1.

Figure 2.

The Circuit for Printed Circuit Board (PCB) Design.

Figure 3.

Node-RED Setting for Data.

Software Description

This section provides a detailed overview of the database configuration of the proposed IoT-based health monitoring system. The software component is critical since it relies on multiple platforms, including Node-RED IBM Cloud, Google Cloud and Spreadsheet. Many hardware-obtained indicators, such as body temperature, heart rate, oxygen level and ambient factors, require these platforms to be observed and evaluated. The collected data are safely maintained in a repository, which serves as the foundation for medical records and data analysis.

Node-RED IBM Cloud: Node-RED and its Node-RED Android app, a visual programming tool, were essential in the integration, processing and storage of data (Figure 3). It made it easier for sensor data to be seamlessly transferred to the Google Cloud platform and made it possible to build simple, interactive dashboards for data visualisation.

Arduino Uno environment: The ESP8266 microcontroller, which served as the system’s central processing unit, was programmed using the Arduino Uno environment. The system’s incorporation of various sensors and the implementation of custom firmware were both made possible by Arduino’s user-friendly IDE.

Google Cloud: For the storage, management and analysis of data, the Google Cloud platform offered a reliable and secure infrastructure. It made it possible to manage the gathered health monitoring data effectively and made it easier for medical professionals to monitor and analyse patient data remotely in real-time.

EasyEDA: To design the circuit board layout and connect the various sensors, microcontrollers and other components, EasyEDA, a web-based PCB design tool, was used. By ensuring proper connectivity and effective use of space on the custom PCB, it made the design process simpler.

Spreadsheet: We opted for Google Sheets, a web-based product developed by Google in the year 2006, as the database management system. The Google Sheets database has been modified with updated body temperature, heart rate, SpO₂ and BP data. This allowed healthcare providers to aggregate monthly data and provide medical reports to patients. The system was designed to efficiently capture and transmit data from the hardware setup to a variety of platforms. This streamlined system allowed for efficient data analysis as well as for patients regardless of their geographic location. This study has a data analysis component that takes into account both real-time environmental and health variables. The data collected by this system result in a prototypic data interpretation. Using descriptive analysis, graphs, monthly trends and patterns for environmental parameters such as body temperature, BP and heart rate were determined. Using data visualisation techniques, data variation and outliers were better comprehended.

For one week, patients’ health markers such as beats per minute (bpm), SpO₂ and body temperature were monitored. A comprehensive cost investigation was carried out to establish the economic viability as well as affordability of the IoT-based online medical monitoring system to monitor people with illnesses. The system’s cost was compared to three commercially available comparable devices that perform similar functions to provide an assessment of comparison. The data analysis gave significant insights into the wellness concerns of the patients, demonstrating the effectiveness of an intended monitoring system in collecting and analysing pertinent information.

Results and Discussion

This section describes the experimental observations like data visualisation, sensor data validation and cost comparison.

Data Visualisation

The developed IoT-based health monitoring system successfully collects vital signs, displays them on the OLED screen and sends the data to the Node-RED dashboard and Google Spreadsheet for additional analysis and storage by using this methodology. Measurements from hospital-grade equipment were compared to data gathered from the IoT-based health monitoring system, including BP values, temperature and pulse rate. The findings showed that the measurements obtained from the hospital equipment and the readings from the developed system exhibited a strong correlation. Figure 4 depicts a gauge chart comparison of hospital equipment and the values obtained from the presented system on Node-RED dashboard and Android mobile app and Figure 5 shows real-time data placed in Google Sheets.

Figure 4.

Real-time Data on Node-RED Dashboard and Android Mobile App.

Figure 5.

Real-time Data on Google Sheets.

Sensors Data Validation

This section analyses the sensors employed for measuring body temperature, heart rate and oxygen level with devices that are offered commercially to assess the accuracy and dependability of the sensors utilised in the IoT-based health monitoring system. In order to do this, ten patients—seven males and three females—with different ages were chosen for the investigation.

A paired correlation study was carried out to ascertain whether there were any notable inconsistencies and whether the readings from the sensors and commercial gadgets were comparable. Table 1 presents sensor validation data for body temperature, systolic BP, diastolic BP, pulse rate and SpO₂ level.

Table 1.

Proposed Data Validation Using Ten Patient’s Data.

S. No.	Name of Patient	Sex	Age	Body Temperature (°F)		Systolic Blood Pressure		Diastolic Blood Pressure		Pulse Rate (bpm)		Oxygen Saturation (SpO₂ in %)		Date of Measurement
S. No.	Name of Patient	Sex	Age	Digital Thermometer	Proposed	Sphygmo manometer	Proposed	Sphygmomanometer	Proposed	Oximeter	Proposed	Oximeter	Proposed	Date of Measurement
1	Pawan Mishra	M	42	100.2	100.25	120	119.455	82	82.595	79	80.056	98	97.568	04-07-2023
2	Sushant Kumar	M	24	99	99.075	125	125.556	85	84.499	80	79.999	98	98.558	02-07-2023
3	Arti	F	35	98.7	98.778	122	120.225	83	83.256	98	99.951	97	96.235	29-06-2023
4	Ayush Gupta	M	37	101	101.225	110	109.559	75	75.565	87	86.595	96	96.665	29-06-2023
5	Sweety Jain	F	55	102	101.995	142	141.586	100	99.995	90	89.999	97	97.174	29-06-2023
6	Ram Kumar	M	72	100	99.988	136	132.339	98	98.011	91	89.595	97	97.584	28-06-2023
7	Ritu Raj	F	65	99	98.986	126	124.454	89	89.231	76	77.587	95	95.024	28-06-2023
8	Prabhat Singh	M	67	99.4	99.395	135	132.993	98	96.545	85	84.565	93	94.256	27-06-2023
9	Gaurav Lathar	M	69	100.5	100.505	140	139.999	99	97.656	79	77.759	98	97.595	27-06-2023
10	Kartik Jha	M	78	98.5	98.495	114	110.265	80	81.025	83	80.569	96	95.985	27-06-2023

The data also include measurements from commercial devices in addition to employed sensors in the presented model (namely digital thermometer and pulse oximeter). Table 1 compares the readings gathered from each sensor and commercially available devices. The scatterplots and fitted lines in Figure 6 show the way distinct measuring devices correspond to each other with respect to every attribute. The fitted lines improve understanding of the data by describing the relationship’s general tendency and the course of development. The R² values for the matched pairings in the first three graphs are somewhat high, indicating that the data set contains notable linear correlations. The subsequent two plots of pulse rate and SpO₂ showed a legitimately considerable relationship with R² values of 0.9622 and 0.8597. Significant correlations imply that the variables have a predictable and established relationship between them.

Figure 6.

Scatterplot Depicted the Measure of the Correlation. (a) Body Temperature; (b) Systolic Blood Pressure; (c) Diastolic Blood Pressure; (d) Oxygen Saturation.

The accuracy and efficiency of the developed system emphasise the system’s potential to offer trustworthy health monitoring capabilities in real-time scenarios. The presented system’s adoption in remote patient monitoring, home healthcare and other healthcare applications is encouraged by how closely it resembles commercially available devices at the hospitals.

Cost Comparison

There has been a surge in interest in developing inexpensive and accessible health monitoring systems, particularly for persistent illnesses. Commercial systems include features like heart rate monitoring and temperature sensing; nevertheless, their high cost prevents them from being widely available. Furthermore, proprietary software and restricted customisation may fall short of meeting the demands of individual customers. To address these issues, our investigation research designed a low-cost IoT-based remote health monitoring system that monitors the health and surroundings of persistent illnesses patients. We compare the proposed system to commercial devices, analysing their costs and outlining their advantages and disadvantages in Tables 2 and 3, respectively. The presented system has the benefits of cost effectiveness, portability and ease of use by utilising IoT technology. Comprehensive health monitoring is made possible by the integration of several sensors, including the BP sensor, non-contact temperature sensor, SpO₂ sensor and ECG sensor. The OLED display gives the user immediate feedback, which improves the usability of the system.

Table 2.

Cost Analysis Comparison Between Proposed Model and Commercial Measuring Device Used at Hospitals.

Proposed Model Equipment	Commerically Available Equipment
Name	Price (in ₹)	Name	Price (in ₹)
Blood pressure sensor + pulse rate	720	BP machine	720
Non-contact type temperature sensor	500	Thermometer	1,000
Arduino board including consumable items	1,200	Oximeter	2,000
Pulse rate meter	1,500
Total	2,420	Total	5,220

Table 3.

Comparing the Benefits and Limitation of Proposed System with Reference to Commercially Available Equipment at Hospitals.

Factors	Proposed System	Commercially Available Devices
Parameters measured	Multiple parameters, including body temperature, systolic blood pressure, diastolic blood pressure, heart rate and oxygen saturation level are measured by a single device	Restricted to specific parameters Four different measuring devices needed for getting the parameter value
Cost effectiveness	Cheaper and best cost-effective alternatives. Total cost of device is ₹2,420	Comparatively costly The total amount needed to perform the same task is about ₹5,220
Tracking in instantaneous mode	Yes, with vitals level alerts	Fewer notifications are possible and data are not instantaneously accessible. It might not be available on all gadgets
Freeware versatility	Free to download software and peripherals allow for rapid customisation	Software and hardware deemed immutable The Bluetooth-based technology limits
Seamless data management	Very good, as data transfer is carried out using Wi-Fi	data transfer to lesser ranges
Framework	In the instance that there is no framework needed, additional safeguarding is required	Proper encapsulation is an essential requisite

Additionally, seamless data management, storage and analysis are made possible by the data integration with Node-RED and Google Cloud. Healthcare professionals can easily access the collected data remotely to monitor patient’s vital signs and spot any trends or anomalies in real-time. This remote access and data management capability improve healthcare services and, if necessary, allow for early intervention. Overall, the developed IoT-based health monitoring system provides accurate and reliable measures of vital indicators such as BP, temperature and pulse rate. Its potential for real-time health monitoring in varied contexts is demonstrated by the remarkable correlation between the system readings and the measures made with hospital-grade equipment. Node-RED and Google Cloud have been connected to give medical practitioners excellent data management and remote access. Applications for remote patient monitoring and home healthcare, in particular, indicate the potential for the system to improve healthcare delivery.

Conclusion

This study successfully engineered and validated a low-cost IoT-based health monitoring system that keeps track of vital indicators including BP, temperature and pulse rate in real-time. The system’s accuracy and robustness were proven by the strong correlation it exhibited with data collected with hospital-grade equipment.

The implications of the proposed system are substantial. For the first time, because the system is affordable and portable, it may be made available to a wider range of patients, especially people living in resource-limited regions in which traditional healthcare facilities may be lacking or those who are homebound and are unable to frequently attend hospitals, like senior citizens and the physically disabled. The widespread accessibility of health monitoring tools may lead to earlier diagnosis of health problems and more prompt medical interventions. Second, as a result of real-time monitoring capabilities, data can be observed and studied on a constant basis, making it simpler to spot trends or patterns in an individual’s vitals. This continual monitoring can be especially advantageous for persons who have chronic illnesses or are at high risk of developing certain diseases. The instantaneous input of the system can also enable people to become more active in their treatment, perhaps leading to improved health outcomes. Furthermore, the system’s independently proven performance when compared to hospital-grade equipment suggests that it may be used as a complement to traditional healthcare systems. It offers the ability to bridge the gap between traditional healthcare visits by keeping patients under observation and empowering healthcare professionals with an improved comprehension of their patient’s health. It may be able to cater to a broad spectrum of individuals and regions by offering a low-cost, accurate and portable solution.

Footnotes

Declaration of Conflicting Interests

The authors declared no potential conflicts of interest with respect to the research, authorship and/or publication of this article.

Funding

The authors received no financial support for the research, authorship and/or publication of this article.

References

Abbate

, Avvenuti

, Corsini

, Light

, & Vecchio

(2010). Monitoring of human movements for fall detection and activities recognition in elderly care using wireless sensor network: A survey. Wireless Sensor Networks: Application—Centric Design .

Abbate

, Avvenuti

, & Light

(2014). Usability study of a wireless monitoring system among Alzheimer’s disease elderly population. International Journal of Telemedicine and Applications , 2014, 617495.

Ahmed

, Latif

, Abbas

, & Khan

F. A.

(2018) Malicious insiders attack in IoT based multi-cloud e-healthcare environment: A systematic literature review. Multimedia Tools and Applications , 77, 21947–21965.

Aiswarya

, Ramesh

, & Sasikumar

S S.

(2021). IoT based big data analytics in healthcare: A survey . Proceedings of the First International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICASISET 2020, 16–17 May 2020, Chennai, India.

Avvenuti

, Baker

, Light

, Tulpan

, & Vecchio

(2009). Non-intrusive patient monitoring of Alzheimer’s disease subjects using wireless sensor networks . 2009 World Congress on Privacy, Security, Trust and the Management of e-Business (pp. 161–165). IEEE.

Bachurin

S. O.

, Bovina

E. V.

, & Ustyugov

A. A.

(2017). Drugs in clinical trials for Alzheimer’s disease: The major trends. Medicinal Research Reviews , 37(5), 1186–1225.

Baldeiras

, Santana

, Leitão

M. J.

, Gens

, Pascoal

, Tábuas-Pereira

, Beato-Coelho

, Duro

, Almeida

M. R.

, & Oliveira

C. R.

(2018). Addition of the aβ42/40 ratio to the cerebrospinal fluid biomarker profile increases the predictive value for underlying Alzheimer’s disease dementia in mild cognitive impairment. Alzheimer’s Research & Therapy , 10(1), 1–15.

Bar-David

(1999). Three phase development of caring capacity in primary caregivers for relatives with Alzheimer’s disease. Journal of Aging Studies , 13(2), 177–197.

Belfiore

, Cuccurullo

, & Aria

(2022). IoT in healthcare: A scientometric analysis. Technological Forecasting and Social Change , 184, 122001.

10.

Belgaum

M. R.

, Momina

S. M.

, Farhath

L. N.

, Nikhitha

, & Naga Jyothi

(2023). Development of IoT-healthcare model for gastric cancer from pathological images . International Conference on Mining Intelligence and Knowledge Exploration (pp. 193–201). Springer.

11.

dos Santos Pianco

L. C.

, Ozela

P. F.

, de Fatima de Brito Brito

, Pinheiro

A. A.

, Padilha

E. C.

, Braga

F. S.

, de Paula da Silva

C. H.

, dos Santos

C. B. R.

, Rosa

J. M. C.

, & da Silva Hage-Melim

L. I.

(2018). Alzheimer’s disease: A review from the pathophysiology to diagnosis, new perspectives for pharmacological treatment. Current Medicinal Chemistry , 25(26), 3141–3159.

12.

Ebrahem

A. T.

, Al-Hatab

M. M. M.

, Abd Al-Jabbar

E. Y.

, Alkhaled

W. H.

, & Al-Sawaff

Z. H.

(2023). Using IoT technology for monitoring Alzheimer’s and elderly patients. Indonesian Journal of Electrical Engineering and Computer Science , 31(2), 986–994.

13.

Gao

(2023). Preliminary design and research of wearable devices for Parkinson’s disease. Highlights in Science, Engineering and Technology , 39, 575–580.

14.

Gaubert

, & Chainay

(2021). Decision-making competence in patients with Alzheimer’s disease: A review of the literature. Neuropsychology Review , 31(2), 267–287.

15.

Gill

S. S.

, Arya

R. C.

, Wander

G. S.

, & Buyya

(2019). Fog-based smart healthcare as a big data and cloud service for heart patients using IoT . International Conference on Intelligent Data Communication Technologies and Internet of Things (ICICI) 2018 (pp. 1376–1383). Springer.

16.

Haque

, Soliman

, & Chowdhury

M. N. U. R.

(2023). Wireless sensor networks data anomaly detection: A smart approach . 2023 3rd International Conference on Intelligent Technologies (CONIT) (pp. 1–8). IEEE.

17.

Küçükönder

, & Görçün

Ö. F.

(2023). Healthcare 4.0 and decision-making techniques in the health industry: A systematic literature review. In İyigün

İ.

& Görçün

Ö. F.

(Eds.), Health 4.0 and medical supply chain (pp. 121– 134). Springer.

18.

, Chai

, Khan

, Jan

S. R. U.

, Verma

, Menon

V. G.

, Kavita

, & Li

(2021). A comprehensive survey on machine learning-based big data analytics for IoT-enabled smart healthcare system. Mobile Networks and Applications , 26, 234–252.

19.

Masood

J. A. I. S.

, Jeyaselvi

, Senthamarai

, Koteswari

, Sathya

, & Chakravarthy

N. K.

(2023). Privacy preservation in wireless sensor network using energy efficient multipath routing for healthcare data. Measurement: Sensors , 29, 100867.

20.

Mehmood

, Ullah

, Ahmad

, & Kim

(2019). Object detection mechanism based on deep learning algorithm using embedded IoT devices for smart home appliances control in CoT. Journal of Ambient Intelligence and Humanized Computing , 1–17.

21.

Ntehelang

, Isong

, Lugayizi

, & Dladlu

(2019). IoT-based big data analytics issues in healthcare . Proceedings of the 3rd International Conference on Telecommunications and Communication Engineering (pp. 16–21).

22.

Poornima

M. G.

, Prabhu

M S.

, Rahman

, Vurukonda

, Sade

, & Biswas

(2022). Machine learning for IoT health care applications. Journal of Positive School Psychology , 6(8), 4025–4037.

23.

Rajagopal

S. M.

, Supriya

, & Buyya

(2023). Fedsdm: Federated learning based smart decision making module for ECG data in IoT integrated Edge-Fog-Cloud computing environments. Internet of Things , 22, 100784.

24.

Rather

M. A.

, Khan

, Alshahrani

, Rashid

, Qadri

, Rashid

, Alsaffar

R. M.

, Kamal

M. A.

, & Rehman

M. U.

(2021). Inflammation and Alzheimer’s disease mechanisms and therapeutic implications by natural products. Mediators of Inflammation , 2021, 1–21.

25.

Rodrigues

, Petersen

R. B.

, & Perry

(2014). Parallels between major depressive disorder and Alzheimer’s disease: Role of oxidative stress and genetic vulnerability. Cellular and Molecular Neurobiology , 34(7), 925–949.

26.

Troncone

, Luciani

, Coggins

, Wilker

E. H.

, Ho

C. Y.

, Codispoti

K. E.

, Frosch

M. P.

, Kayed

, & Del Monte

(2016). Aβ amyloid pathology affects the hearts of patients with Alzheimer’s disease: Mind the heart. Journal of the American College of Cardiology , 68(22), 2395–2407.

27.

Tunc

M. A.

, Gures

, & Shayea

(2021). A survey on IoT smart healthcare: Emerging technologies, applications, challenges, and future trends. arXiv preprint arXiv:2109.02042 .

28.

Venkatraman

, Parvin

, Mansoor

, & Gawanmeh

(2023). Big data analytics and internet of things for personalised healthcare: Opportunities and challenges. International Journal of Electrical & Computer Engineering (2088-8708) , 13(4).

29.

Wang

, Talavera

, Karastoyanova

, & Azzopardi

(2023). Fall detection with a non-intrusive and first-person vision approach. IEEE Sensors Journal , 23(22), 28304–28317.

30.

Yang

, Wang

, Li

, Gu

, Liang

, Li

, Zhang

, & Zhong

(2020). Exploring emerging IoT technologies in smart health research: A knowledge graph analysis. BMC Medical Informatics and Decision Making , 20, 1–12.

31.

Zamolodchikov

, Renné

, & Strickland

(2016) The Alzheimer’s disease peptide β-amyloid promotes thrombin generation through activation of coagulation factor XII. Journal of Thrombosis and Haemostasis , 14(5), 995–1007.

32.

Zeadally

, Siddiqui

, Baig

, & Ibrahim

(2020). Smart healthcare: Challenges and potential solutions using internet of things (IoT) and big data analytics. PSU Research Review , 4(2), 149–168.