Javascript is currently disabled in your browser. When javascript is disabled, some functions of this website will not work.

Open access for scientific and medical research

From submission to the first editing decision.

From editor acceptance to publication.

Open access to peer-reviewed scientific and medical journals.

Dove Medical Press is a member of OAI.

Batch reprints for the pharmaceutical industry.

We provide real benefits for authors, including fast processing of papers.

Register your specific details and specific drugs of interest, and we will match the information you provide with articles in our extensive database and send you a PDF copy via email in a timely manner.

Back to Journal »Medical Devices: Evidence and Research» Volume 14

Author Al-Naami B, Abu Owida H, Abu Mallouh M, Al-Naimat F, Agha M, Al-Hinnawi AR 

Published on December 2, 2021, Volume 2021: 14 pages, pages 423-433

DOI https://doi.org/10.2147/MDER.S339855

Single anonymous peer review

Editor approved for publication: Dr. Scott Fraser

Supplementary video of "Smart Wearable Monitoring System for Alzheimer's Disease Patients" [ID 339855].

Bassam Al-Naami,1 Hamza Abu Owida,2 Mohammed Abu Mallouh,3 Feras Al-Naimat,2 Moh'd Agha,2 Abdel-Razzak Al-Hinnawi4 1 Department of Biomedical Engineering, Zarqha Hashem University, Jordan; 2 Medicine Department of Engineering, Al-Ahliyya University of Amman, Amman, Jordan; 3 Department of Electromechanical Engineering, Zarqah Hashem University, Jordan; 4 Faculty of Science, Al-Isra University, Amman, Jordan Mailing address: Bassam Al-Naami, Department of Biomedical Engineering, Hash University College of Engineering, P.O. Box 330127, Zarqa, 13133, Jordan Fax +962 5 3826348 E-mail [email protected] Purpose: The daily life management of patients with Alzheimer’s disease (AD) constitutes an important and rapidly expanding Health care responsibilities. In this research, an innovative prototype of a wireless sensing smart wearable medical device (SWMD) is proposed as a multifunctional solution for patients with Alzheimer's disease. SWMD aims to integrate three major biomedical engineering advancements: 1) the use of Wi-Fi microcontrollers, 2) simultaneous monitoring of a set of important biomarkers, and 3) warnings of falls in addition to GPS position indicators. Method: SWMD uses a Wi-Fi controller combined with an electronic circuit to monitor three important signals (temperature, heart rate, and oxygen saturation), three directions (X, Y, and Z axis) drop conditions and GPS location. SWMD connects to the Firebase service (a database hosted on the Internet cloud). The proposed device was tested on 13 normal volunteers. Evaluate left, right, forward, and backward fall conditions. The prototype's functions in daily activities such as raising hands, sitting or standing, and walking conditions were also evaluated. Result: The three assembled functions were successfully combined to construct a SWDM device, as a suggested solution, to provide real-time alerts to AD patients in daily activities. The Bland-Altman statistical test showed that there was no significant difference between the collection of SWMD biomarkers and the reference method (p value> 0.05). The sensitivity of the gyroscope/accelerator sensor in fall detection is 93%, and the specificity in daily activities is 95%. GPS generates the correct location of SWDM holders, while the Internet cloud allows all important biomarkers to be stored and managed every day. Conclusion: SWMD is a possible solution for daily life support for AD patients. It integrates the three functions of GPS positioning indicator, biomarker monitoring group and fall alert into one device, all of which are controlled online via a Wi-Fi microcontroller connected to the Internet cloud. It successfully allows the management of daily records and real-time alerts to remote personnel. Keywords: Alzheimer's disease, smart wearable medical devices, fall warning, Internet cloud access, healthcare assistance, Wi-Fi microcontroller

There is still no cure for Alzheimer's disease (AD). 1 Emotional and psychological effects are painful for patients and relatives. According to reports, the progress of AD takes 12 years and is divided into three stages. 1,2 The first phase lasts 1 to 3 years, starting with signs of abnormal biomarkers and recurring mild to moderate cognitive problems. In the second stage (three to ten years), AD patients will experience temporary memory loss, repetitive moderate cognitive impairment, and the presence of pathophysiological biomarkers. Finally, the third stage, also called dementia, lasts eight to twelve years. Unfortunately, AD patients may experience significant memory loss, significant cognitive decline, and frequent unexpected abnormal biomarkers. 1-3 Further studies have shown that changes in cognition, behavior, sensory, and movement may begin to appear several years before the clinical symptoms of AD appear. 4,5 Unfortunately, by 2030, the AD epidemic is expected to affect approximately 74.7 million people. 2,6,7

Therefore, there is a strong demand for life support equipment for AD patients, which is an ongoing research topic. 1,2,8 Biomedical Engineering (BME) health care technology for AD patients is gradually entering our daily lives. 9 Currently, BME technology provides solutions for AD's medical care support equipment, allowing AD patients to safely perform various daily tasks. 6 One of them is a voice assistant device. Voice recording helps AD patients with daily medications, appointments, date and time by playing time sound notifications; these are simple sound "reminder" devices. 10 Other devices use Internet Wi-Fi technology and geographic location system (GPS) applications; these are telemetry medical aids (TMAD). 11-15 They are currently used in homes and nursing homes to manage people's health and have a considerable degree of reliability. 11,12 GPS trackers (for example, Smartsole) sealed under the insole are recommended. 14 It can monitor the location of people wandering around, such as AD patients. GPS is also used in smart watches with life-saving functions. 13 In addition to tracking the current location of the caregiver, the smart watch can also monitor heart rate, receive text and voice messages, and vibration alerts. They are equipped with a help button (ie emergency SOS button). However, these GPS devices face some difficulties. 11-14 Antennas installed on AD patients may cause some complexity and discomfort. They require specialized sensors and vendor-specific software, leading to high price expectations. The most important disadvantage is that these GPS devices do not have a fall warning sensor, which may be impractical for people with dexterous hands.

On the other hand, some people suggest using deep learning and face recognition to improve the quality of life of AD patients. 16,17 It is designed as a "smart hat" that can help AD patients detect people they know (for example, family members) and even people who might harm them have been investigated. 16 This is an expensive technology limited to machine learning knowledge. Although it helps to recognize people using previously trained models, it can neither monitor important parameters nor provide alerts for falls, which is a common event for AD patients.

However, some researchers studied the prototype to detect only the drop condition. Among the work of Ramachandran and Karuppiah, 25 investigated recent work. Using different methods, such as environmental sensing-based systems, wearable sensor-based systems, and vision-based systems, their accuracy is between 79% and 100%.

Therefore, it is expected that healthcare BME technology will continue to advance, replacing old equipment with smarter equipment, and propose solutions to unresolved problems. 1 This paper presents a prototype of a new type of multi-functional sensing smart wearable monitoring device (SWMD). Design, build and test. SWMD is worn on the wrist and has three advantages compared with existing equipment. First, SWMD is equipped with a fall alert using gyroscope and accelerometer sensors. Second, SWMD uses Wi-Fi microcontrollers that can access Firebase services (databases hosted on the Internet cloud) to enable healthcare professionals and family members to connect with AD patients in real time. As far as we know, the latter two specifications are neither mentioned in the literature nor equipped in existing equipment. In addition, the third technical feature, the prototype proposes a new configuration that can simultaneously monitor a set of important biological signals (ie, biomarkers), such as temperature, heart pulse, and oxygen level.

Figure 1 shows a block diagram of the proposed SWMD for AD patients. It consists of six input sensors, microcontroller, battery and two output devices. The InvenSense MPU-6050 gyroscope and accelerometer sensor is one of the six input sensors used in the proposed SWMD. Figure 2 shows the MPU-6050, which can measure acceleration along the x, y, and z axes and angular velocity around the x, y, and z axes. When the MPU-6050 sensor reads the normal values ​​of acceleration and angular velocity, it can detect the fall of the AD patient. Use MAX30100 to measure heart rate and blood oxygen saturation (SpO2). Figure 3 shows the MAX30100, which is an integrated pulse oximetry and heart rate sensor. It consists of two LEDs, a photodetector, optimized optics and low-noise signal processing to detect pulse oximetry and heart rate signals. 18 The sensor emits light of two wavelengths (red and infrared) from two LEDs. The reflected light is then measured and processed to estimate two biomarkers, pulse rate and SpO2. Patient temperature is another biomarker measured using Texas Instruments LM35 temperature measurement IC. The accuracy of the temperature sensor is ± 0.5 C°. The fifth input signal of SWMD comes from GPS GPS6MV2 module. It is used to determine the latitude and longitude coordinates of SWMD. Finally, the contact sensor is used to detect whether the patient is wearing the SWMD correctly. Figure 1 Block diagram of the proposed SWMD prototype to help AD patients. Figure 2 Gyroscope and accelerometer sensor module. Figure 3 MAX30100 pulse oximeter and heart rate sensor integrated circuit.

Figure 1 Block diagram of the proposed SWMD prototype to help AD patients.

Figure 2 Gyroscope and accelerometer sensor module.

Figure 3 MAX30100 pulse oximeter and heart rate sensor integrated circuit.

The output of SWMD is divided into three types: visual output through LCD, sound output through buzzer and data output through Firebase real-time database. The LCD displays patient information and biomarkers. Its screen size is 1.8 inches, and it has an SD card slot of up to 2 GB to store information. A buzzer has been added to the system, and an audible alarm will sound when the sensor reads an abnormal value. The alarm will draw the attention of the patient and the surrounding environment, indicating an emergency situation that needs to be dealt with. Firebase Real-time Database is a database hosted in the cloud, used to share SWMD readings with other people (that is, patients' doctors and relatives) through the cloud. Data is stored and synchronized in real time with each connected client. SWMD is connected to the Internet through the SIM800L module. The SWMD is powered by a 3.7 V lithium-ion battery with a capacity of 2000 mAh. The energy in the battery is enough to run the device continuously for about 10 hours, and it can be charged through the charger port.

In terms of controller hardware, ESPRESSIF's ESP32-WROOM-32 microcontroller module is used. The microcontroller has two independently controllable CPU cores, the CPU clock is up to 240 MHz, and the RAM is 4 MB. It also integrates a wealth of peripherals (ie capacitive touch sensor, Hall sensor, SD card interface, Ethernet, Bluetooth, Wi-Fi). Figure 4 shows the SWMD components and connection diagram. All sensors are defined on the microcontroller using Arduino as the programming language. Figure 5 (AD) shows the top (A), bottom (B), right and left sides (C and D) of the assembled SWMD. Figure 4 Components and connections of a smart wearable monitoring device. Figure 5 SWMD after assembly. (A) top view, (B) bottom view, (C) right side view, and (D) left side view.

Figure 4 Components and connections of a smart wearable monitoring device.

Figure 5 SWMD after assembly. (A) top view, (B) bottom view, (C) right side view, and (D) left side view.

Figure 6 shows the operation flow chart of SWMD. First, open SWMD. Then, it starts to search and connect to the Wi-Fi network. If it is not connected to the Wi-Fi network, SWMD will be turned off. If it is connected to a Wi-Fi network, the touch sensor will be checked to ensure that the user is wearing the SWMD correctly. After confirming the correct internet connection and SWMD wearing, the sensor will start to run and send the measured value to the LCD and Firebase via the microcontroller. SWMD is set to measure the body temperature, pulse rate, SpO2, acceleration, angular velocity, and GPS position of AD patients every 10 seconds, and share the readings with healthcare providers via Firebase. If any measured value exceeds the normal reading, SWMD will turn on the alarm buzzer and send a warning message to relatives or healthcare providers via the Internet cloud. Figure 6 SWMD operation flow chart.

Figure 6 SWMD operation flow chart.

The proposed SWMD tested 13 normal volunteers between 22 and 33 years old. The results of these tests are presented using descriptive statistics. One-way analysis of variance was used in the analysis, followed by Tukey's post-test; significance was approved as p-value <0.05. In addition, the Bland Altman method was used to evaluate the agreement between the proposed and existing reference measurements. 19 The study was approved by the Research Ethics Committee of Al-Ahliyya Amman University and was carried out in accordance with Helsinki's statement. All volunteers (normal) were assigned their informed consent before participating in the study. It is difficult to get the consent of AD patients. Supervising patients like AD patients requires medical preventive measures, which scientists cannot do (the author is a biomedical engineer). In our institution, it is against research ethics to conduct investigation experiments on people with AD who may be at risk of falling, or to ask them to try a fall experiment without doctor intervention.

The block diagram, electronic components and flow chart of the proposed SWMD (i.e., Figures 1, 4 and 6) have been successfully assembled, and the prototype of the wearable device is shown in Figure 5. The supplementary video shows a demonstration of SWMD operation. This video demonstrates the different outputs and alarms produced by SWMD.

Thirteen participants were asked to wear SWMD on their wrists (Figure 5). Although the participants do not have medical conditions, these tests will allow the various functions of the proposed SWMD to be checked. The body temperature, pulse rate, and SpO2 of each volunteer were recorded, and then compared with the same parameters recorded by standard medical equipment. These measured values ​​are expressed as mean ± standard deviation (SD) for statistical analysis. The results are shown in Table 1. Use one-way analysis of variance to determine statistical significance, and then perform Tukey's post-test. Significance was confirmed at p-value<0.05. The average value ± SD of the reference temperature measurement is 35.2 ± 0.77 C°, and the recommended SWMD temperature measurement value is 35.3 ± 0.84 C°. The pulse rate measurement results were 80.7 ± 5.6 BPM and 80.4 ± 6.5 BPM, respectively, as reference and SWMD. The measurement results of oxygen concentration (ie SpO2) are 95% ± 0.022 and 94% ± 0.017, respectively, for reference and SWMD use. The results showed that there was no statistically significant difference between the reference test method and the recommended SWMD (p value <0.05). Table 1 Results of biomarkers from the proposed SWMD and references

Table 1 Results of biomarkers from the proposed SWMD and references

Perform a Bland Altman statistical test to evaluate the agreement between the proposed SWMD and the measured value of the standard medical device. Calculate the arithmetic difference between each measurement of SWMD and the standard device. Infer the mean and standard deviation of the difference. Table 2 shows the results, illustrating the mean of the difference and the mean ±1.96 SD. The upper and lower differences of the reference measurement values ​​of the three biomarkers of temperature, pulse rate, and oxygen concentration were 0.71 to -0.51 C°, 6.24 to -5.47 BPM, and 4.18% to -5.18%, respectively. Table 2 Differences in biomarker results between SWMD and references

Table 2 Differences in biomarker results between SWMD and references

Figure 7 shows the Bland Altman diagram. It shows that all measurements from SWMD are clustered around the mean ± 1.96 SD. Since the difference between the SWMD measurement value and the standard medical device measurement value is within the mean ± 1.96 SD and has no clinical significance, the two measurement methods can be used interchangeably. In addition, the average value of all characteristics is close to zero, which means that the measured value of the developed device is quite consistent with the measured value obtained using standard medical equipment. Therefore, the proposed SWMD can provide correct biomarker measurement as a standard method. Figure 7 Bland-Altman diagram of SWMD and reference reading: (A) temperature test, (B) pulse test and (C) oxygen concentration test.

Figure 7 Bland-Altman diagram of SWMD and reference reading: (A) temperature test, (B) pulse test and (C) oxygen concentration test.

The GPS in SWMD determines the global location of the person wearing the device. It is tested and compared with the result of the same location selected from the smartphone. Table 3 lists GPS in three different locations using SWMD and smartphones. Someone pointed out that the results of SWMD and smartphones are very close. Table 3 GPS results of three locations using SWMD and smartphone

Table 3 GPS results of three locations using SWMD and smartphone

A gyroscope/accelerometer sensor (ie MPU-6050) is used to detect falls of emergency patients. The sensor provides acceleration and angular velocity readings on the x, y, and z axes. These measurements are continuously monitored by a Wi-Fi microcontroller, and when a normal reading is detected, a fall alarm will be turned on. Fall alarms can be automatically sent to remote personnel, such as caregivers and family members, via the Internet cloud. The microcontroller can adjust the threshold for loss of balance on the x, y, and z axes. The supplementary video shows an example of how the buzzer works in the event of loss of balance. In this experiment, 10 of 13 volunteers underwent 4 tests to evaluate fall alerts in one of four different directions: forward, backward, left, and right fall conditions. The volunteers were asked to repeat the test 4 times. Therefore, for each drop direction, we conducted 40 tests. Table 4 shows the sensitivity of correctly detecting fall conditions. On the other hand, volunteers were also asked to test the prototype (SWDM) in some normal activities of daily living (ADL). For each ADL normal exercise, walking, sitting, standing, and raising hands, the test is also repeated four times. Table 4 illustrates the success in avoiding false positives (ie, specificity). False positive (FP), true positive (TP), false negative (FN) and true negative (TN) are described according to the following conditions: Table 4 Experiment results of 7 different sudden movements using fall detection sensors. Action description

Table 4 uses the fall detection sensor to carry out the experiment result of 7 kinds of different sudden movements. Action description

TP: Indicates a fall detection alarm.

FP: Indicates that there is an alarm but no fall has occurred (that is, ADL is moving normally but is detected as a fall).

TN: Indicates that there is no alarm when ADL is in normal motion.

FN: Represents an undetected fall (that is, there is no alarm for a fall).

Subsequently, the sensitivity (the accuracy of detecting a true fall) and specificity (the accuracy of avoiding false positives) are derived from the equation:

Alzheimer's disease constitutes an important and rapidly expanding healthcare responsibility. 1 Although the current AD life assist devices (such as recording, 10 text messages, 1 GPS positioning, 9,11-14,20-22 and facial recognition devices16,17,23) have harvested advances in healthcare and communication technology, There are technical imperfections, such as combining the assessment of several biomarkers with several generations of alarms to prevent falls, which is crucial in daily life with AD. 1

This article shows a prototype of a smart wearable life support device with four innovative aspects involving AD patients and caregivers. First, it proposes a new prototype that can simultaneously monitor three biomarkers (temperature, pulse rate, and SpO2) and provide alerts. Secondly, it is also a major development. It also proposes a solution to provide alerts in the event that AD patients suddenly encounter any lack of balance due to competition, rollover, or fall. Third, the system can save the daily information of all AD patients in the Internet cloud. Fourth, all the information in SWMD can be monitored by telemedicine observers, including the sudden fall of AD patients. GPS services can also be used to indicate the location of AD patients.

In monitoring the biological signals of AD patients, the proposed SWMD uses well-known commercial temperature, pulse rate and SpO2 sensors. Measurements of 13 participants showed that there was no significant statistical difference between calculations using SWMD (Figures 1, 4-6) and standard methods. Figure 7 shows the Bland Altman diagram. The statistical chart provides two key indicators, deviation and consistency range, which are used to evaluate the accuracy of the model or prototype. 18,19,24 The graph in Figure 7 shows that the measured value in SWMD is within the standard deviation of the mean ±1.96, so it has no clinical significance. In addition, the average difference of all three biomarkers is close to zero, indicating that the measured value of the developed device is quite consistent with the measured value of the reference test method. Therefore, the proposed smart system SWMD can be regarded as a reliable substitute for the current standard measurement.

In terms of fall warning, when the microcontroller detects the normal reading of the gyroscope/accelerometer sensor, the warning will turn on, as shown in the supplementary video. It proposes an effective solution that can alert caregivers in the event of a fall, and other AD life support devices have not yet solved this problem. It proposes a major improvement that can be acted upon immediately in the event of an emergency. Table 4 shows that the prototype initially reached 93.7% in correct detection of fall conditions, and the specificity of avoiding false alarms in some daily activities reached 95%. On the one hand, these results depend on the preset of the accelerometer threshold, but on the other hand, it indicates that it is possible to adjust (preset) to suit the conditions of different holders. This will be a prospective study conducted under the supervision of a doctor.

Finally, Internet cloud access allows management of all daily data about AD health status (ie data from three biomarkers). This data can be saved, checked, and managed by the healthcare provider (for example, printed or deleted). In the case of medical conditions and fall conditions related to the three biomarkers, the microcontroller alerts the AD patient. Although there is no SOS button that can be added, the microcontroller can be programmed to send a "loud" recording to people around when an AD patient encounters an abnormal biomarker or falls.

Various solutions to evaluate fall detection accidents are reported in the literature. They always try to distinguish falls from common ADL activities. However, the solution differs in some aspects, such as sensor type and sensor placement. Table 5 illustrates examples from these reports. Some reports use only microelectromechanical systems 31 (MEMS) or accelerometers, 27, 30 and other reports use accelerometers integrated into gyroscopes, with or without magnetometers. 26,29,33 Some researchers prefer to use accelerometers with heart rate variability (HRV) sensors derived from ECG signals (ie pressure indicators)28 or infrared sensors (ie position indicators). 31 Other researchers use artificial intelligence techniques based on acceleration measurements during a fall accident (for example, machine learning programs)32. On the other hand, there is no agreement on the placement of the fall detection device. The sensor is installed on the head, 32 chest, 26, 32 thigh, 26, 32 waist, 27, 29, 31, 32 shoulder, 29 wrist, 32 or foot. 29 Some researchers prefer the smartphone style, so the fall detection device can be placed in the trouser pocket, 30 while other researchers prefer to design special vests. 33 Table 5 shows that there is no evidence of agreement among the researcher groups. Most reports in the literature use accelerometers of different types and brands. This shows that they use different 3D acceleration thresholds. However, they all report excellent sensitivity and specificity values ​​higher than 90%, and may reach 100%. These records were from healthy subjects who were asked to repeat simulated fall detection or ADL activities. Therefore, Table 5 shows that the proposed SWDM produces results similar to other reports in the literature. However, in this article, SWDM is a multifunctional prototype worn only on the wrist. We believe that, as shown in Reference 1, placing many fall detection devices on various parts of the body will put a burden on the holder. SWDM was applied to healthy people and produced relatively sensitive and specific results. As the report in Table 5 shows, it is difficult to test prototypes on abnormal or elderly subjects and ask them to follow the simulation of the fall accident. SWDM showed the preliminary results of a device designed for the elderly. The device detects fall accidents on the one hand, and observes multiple biomarkers (not only HRV) through GPS and WiFi microcontrollers and online Internet cloud access. Table 5 Fall detection system using gyroscope/accelerometer

Table 5 Fall detection system using gyroscope/accelerometer

The future work of this article will be to minimize the size of the proposed prototype to make it more comfortable. This can be achieved by using smaller electronic devices (such as micro or nano embedded systems). In addition, the accuracy (sensitivity and specificity) of fall detection needs to be improved. SWDM testing needs to be performed on elderly or AD patients of different ages and different disease stages, but this should require medical precautions because it implies fall testing and risks.

The purpose of this research is to develop an auxiliary wearable prototype that can be used as a solution to locate patients with Alzheimer's disease, while also monitoring other important parameters such as temperature, heart rate and oxygen level. If the patient suddenly falls down due to any health complications, the prototype can also send an alert. It contains a Wi-Fi microcontroller that can save daily information and monitor the GPS location of AD patients. The system was tested on 13 volunteers, with a sensitivity of 93% in correctly detecting falls and a specificity of 95% in avoiding false alarms. Wi-Fi microcontroller, GPS, biometric acquisition and fall alarm circuits are successfully operating. The prototype is a trusted device that provides daily life support for AD patients.

The author is very grateful to the staff and participants of the Department of Biomedical Engineering for their contributions to the goals of this study.

The authors did not receive any financial support to conduct this research.

The authors report no conflicts of interest in this work.

1. World Parkinson League. Summary of the Fifth World Parkinson Conference, Kyoto, Japan, June 4-7, 2019. J Parkinsons Dis. 2019;9(s1):1-278. doi:10.3233/jpd-199900

2. Wang T. Acupuncture for Brain.Springer, Cham; 2021.doi:10.1007/978-3-030-54666-3

3. Reisberg B, Prichep L, Mosconi L, etc. Alzheimer's disease is the early stage of mild cognitive impairment and the stage of subjective cognitive impairment. Alzheimer's disease. 2008; 4 (1 supplement. 1). doi:10.1016/j.jalz.2007.11.017

4. Kourtis LC, Regele OB, Wright JM, Jones GB. Digital biomarkers of Alzheimer's disease: opportunities for mobile/wearable devices. Npj Digital Medicine. 2019; 2(1). doi:10.1038/s41746-019-0084-2

5. Eshkoor SA, Hamid TA, Nudin SS, Adiah H, Mun CY. The association between dentures and fall rates in dementia. Medical equipment Evid Res. 2014; 7(1). doi:10.2147/MDER.S63220

6. Srivastava S, Ahmad R, Khare SK. Alzheimer's disease and its different methods of treatment: a review. Eur J Med Chem. 2021;216. doi:10.1016/j.ejmech.2021.113320

7. Guarino A, Favieri F, Boncompagni I, Agostini F, Cantone M, Casagrande M. Executive function in Alzheimer's disease: a systematic review. Pre-aging neuroscience. 2019; 10. doi:10.3389/fnagi.2018.00437

8. Nogueira MML, Neto JPS, Dourado MCN. The quality of life of patients with Alzheimer's disease: a comparison of binary kinship. J Geriatr Psychiatry Neurol. 2021;34(2):119-127. doi:10.1177/0891988720915521

9. Furht B, Agarwal A. Handbook of Medical and Healthcare Technologies. New York, NY: Springer; 2013. doi: 10.1007/978-1-4614-8495-0

10. Chen S, Jin X, Zhang L, Wan J. Comprehensive review of IoT technology and healthcare applications. Communication in computer and information science. roll. 1424; 2021. doi:10.1007/978-3-030-78621-2_29.

11. Abbate S, Avvenuti M, Light J. MIMS: minimally invasive monitoring sensor platform. IEEE Sens J. 2012;12(3):677-684. doi:10.1109/JSEN.2011.2149515

12. Abbate S, Avvenuti M, Light J. Research on the availability of wireless monitoring systems in the elderly with Alzheimer's disease. International J telemedicine application. 2014; 2014. doi:10.1155/2014/617495

13. Caring.com. Freedom Guardian Observation Review; 2021. Available from the following URL: https://www.caring.com/best-medical-alert-systems/freedom-guardian-watch/. Visited on July 14, 2021.

14. SafeTracks GPS Canada Inc. GPS-SmartSole™; 2021. Available from: https://www.iloctech.com/. Visited on November 23, 2021.

15. Mehrabian S, Extra J, Wu YH, Pino M, Traykov L, Rigaud AS. Cognitively impaired patients and their nursing staff's views on the home remote care system. Medical equipment Evid Res. 2014; 8. doi:10.2147/MDER.S70520

16. Boppana L, Kumari P, Chidrewar R, Gadde PK. Use deep learning to provide the upper limit of intelligence for patients with Alzheimer's disease. IEEE Region 10 Annual International Conference, Proceedings/TENCON. roll. 2019; October 2019. doi:10.1109/TENCON.2019.8929412.

17. Lee G, Nho K, Kang B, etc. Use multimodal deep learning methods to predict the progression of Alzheimer's disease. Sci Rep. 2019; 9(1). doi:10.1038/s41598-018-37769-z

18. Analog equipment company. Pulse oximeter and heart rate sensor IC for wearable health; 2014. Available from: https://www.maximintegrated.com/en/products/sensors/MAX30100.html#tech-docs. Visited on November 17, 2021.

19. Altman DG, Bland JM. Assess the consistency between measurement methods. Clinical Chemistry 2017;63(10):1653–1654. doi:10.1373/clinchem.2016.268870

20. Wojtusiak J, Mogharab Nia R. Using GPS trackers for location prediction: Can machine learning help find separated patients with dementia? Internet things. 2021;13:100035. doi:10.1016/j.iot.2019.01.002

21. Bal D, Islam Tusher MM, Rahman M, Rahman Saymon MS. NAVIX: A wearable navigation system for the visually impaired. The 2nd International Conference on Industry 4.0 Sustainable Technologies in 2020, STI 2020; 2020.doi:10.1109/STI50764.2020.9350480.

22. Daum CH, Neubauer N, Oliva C, Beleno R, Liu L. The accuracy and usability of the mobile alert system for community citizens to locate lost dementia patients. Innovative aging. 2019;3(Supplement_1):S453–S454. doi:10.1093/geroni/igz038.1698

23. Aljehani SS, Alhazmi RA, Aloufi SS, Aljehani BD, Abdulrahman R. ICare: Application of Internet of Things technology to monitor patients with Alzheimer's disease. The First International Conference on Computer Application and Information Security, ICCAIS 2018; 2018. doi:10.1109/CAIS.2018.8442010.

24. Anzalone P. Equivalence of blood glucose testing at the earlobe. Clinical Nurse Research Center. 2008;17(4):251–261. doi: 10.1177/1054773808325050

25. Ramachandran A, Karuppiah A. Survey on the latest developments in wearable fall detection systems. Biomedical Res Int. 2020; 2020: 2167160. doi:10.1155/2020/2167160

26. Li Q, Stankovic JA, Hanson MA, Barth AT, Lach J, Zhou G. Use the posture information derived from the gyroscope and accelerometer for accurate and fast fall detection. Conference Proceedings-2009 6th International Symposium on Wearable and Implantable Body Sensor Networks, BSN 2009; 2009. doi:10.1109/BSN.2009.46.

27. Wu F, Zhao H, Zhao Y, Zhong H. Development of a fall detection system based on wearable sensors. International J telemedicine application. 2015; 2015. doi:10.1155/2015/576364

28. Shahiduzzaman M. Detects falls through accelerometer and heart rate variability measurement. Glob J Comput Sci Technol. 2015;15(3-G).

29. Mao A, Ma X, He Y, Luo J. Highly portable sensor-based human fall monitoring system. Sensor (Switzerland). 2017;17(9):2096. doi:10.3390/s17092096

30. Chaitep T, Chawachat J. A three-stage threshold algorithm based on smartphone fall detection. ECTI-CON 2017-2017 The 14th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology; 2017. doi:10.1109/ECTICon.2017.8096203.

31. Chen J, Kwong K, Chang D, Luk J, Bajcsy R. Wearable sensor for reliable fall detection. IEEE Annual International Conference on Medical and Biological Engineering-Proceedings. roll. 7; 2005. doi:10.1109/iembs.2005.1617246.

32. Özdemir AT, Barshan B. Use machine learning technology to detect falls using wearable sensors. Sensor (Switzerland). 2014;14(6):10691-10708. doi:10.3390/s140610691

33. He J, Bai S, Wang X. Non-intrusive fall detection and warning system based on Kalman filter and Bayesian network classifier. Sensor (Switzerland). 2017;17(6):1393. doi:10.3390/s17061393

This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at https://www.dovepress.com/terms.php and include the Creative Commons Attribution-Non-commercial (unported, v3.0) license. By accessing the work, you hereby accept the terms. The use of the work for non-commercial purposes is permitted without any further permission from Dove Medical Press Limited, provided that the work has an appropriate attribution. For permission to use this work for commercial purposes, please refer to paragraphs 4.2 and 5 of our terms.

Contact Us• Privacy Policy• Associations and Partners• Testimonials• Terms and Conditions• Recommend this site• Top

Contact Us• Privacy Policy

© Copyright 2021 • Dove Press Ltd • Software development of maffey.com • Web design of Adhesion

The views expressed in all articles published here are those of specific authors and do not necessarily reflect the views of Dove Medical Press Ltd or any of its employees.

Dove Medical Press is part of Taylor & Francis Group, the academic publishing department of Informa PLC. Copyright 2017 Informa PLC. all rights reserved. This website is owned and operated by Informa PLC ("Informa"), and its registered office address is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 3099067. UK VAT group: GB 365 4626 36

In order to provide our website visitors and registered users with services that suit their personal preferences, we use cookies to analyze visitor traffic and personalize content. You can understand our use of cookies by reading our privacy policy. We also retain data about visitors and registered users for internal purposes and to share information with our business partners. By reading our privacy policy, you can understand which of your data we retain, how to process it, with whom to share it, and your right to delete data.

If you agree to our use of cookies and the content of our privacy policy, please click "Accept".