Wearables as Digital Diagnostics: Comparison
Please note this is a comparison between Version 2 by Catherine Yang and Version 1 by Nupur Biswas.

Wearables, which refer to smart consumer devices that record digital health data, are becoming an integral part of our daily lives. This reflects the growing health consciousness among people. Wearable biosensors are low-price, non-invasive, and non-irritating devices that function by continuously measuring a person’s physiological parameters in real time, which can be used for the early as well as in-depth diagnosis of several conditions. Wearable devices contain different types of sensors that collect data on step counts, heart rate, sleep duration, calories burnt, stress, and oxygen levels.

  • digital diagnostics
  • digital health
  • wearables
  • machine learning

1. Cardiovascular Diseases

As the primary data generated by wearable devices include the heartbeat rate, step count, and energy consumed, researchers have concentrated on associating cardiovascular disorders with these data. Cardiovascular diseases cause millions of deaths globally every year [46][1]. Continuous monitoring and the diagnosis of abnormalities are important for reducing fatalities. Wearable technology has made this more feasible [47][2]. A clinical trial with over 60 adults showed that wearing smartwatches with blood-pressure-monitoring features lowered the patients’ blood pressure and resting heart rate, elucidating the effect of self-monitoring [48][3]. Self-monitoring can also lead to early diagnosis [49][4]. In a study by Rens et al., cardiovascular disease patients were made to take a 6-minute walk test (6MWT) and their activity data were collected with an iPhone and an Apple Watch using the VascTrac app. The home-based 6MWT assessed frailty with 83% sensitivity and 60% specificity. Hence, functional capacity and frailty could be monitored in cardiovascular patients safely and with a higher resolution by using wearable devices [22][5]. Another study by Teo et al. tracked sleep and collected multi-modal phenotypic data and questionnaire responses from normal volunteers. The sleep data derived from the wearables and by self-reporting were compared on the basis of total sleep time (TST) and sleep efficiency (SE). From a data analysis of a multi-modal phenotype, it was found that the TST and SE derived from wearables showed an association with the markers of cardiovascular disease, such as waist circumference and body mass index. However, the self-reported data did not show such associations. A lack of sleep could lead to telomere shortening, which is a tumor suppressor mechanism (premature telomere attrition) (confidence interval [CI] = 74.573–636.538, p  =  0.016); hence, the sleep data from wearables were useful for providing insights into the cardiovascular disease risk (β  =  1.275, CI  =  0.187–2.363, p  =  0.023) [29][6]. The usage of wearables has allowed people to track their own heart rhythms for a very long period [50][7]. By using heart rate and step count data from wearable smartwatches, machine-learning algorithms have been developed by different research groups for detecting atrial fibrillation (AF), which is a leading cause of stroke worldwide. A study by Tison et al. presented a deep-learning algorithm for the detection of AF. The neural network showed a 95% CI of 0.94–1.00 (p  <  0.001) for the detection of AF compared to the AF diagnosis based on ECG results, which was used as reference. The sensitivity was observed to be 98%, with 90.2% specificity [23][8]. Similarly, another study by Inui et al. used wearables such as an Apple Watch and a FitBit and compared them with ECG data for the detection of paroxysmal AF. The correlation between the Apple Watch pulse rate data and the ECG heart rate data was found to be better than that between the FitBit data and the ECG data. The coefficient of determination for the Apple Watch was R2 = 0.685, whereas that for the FitBit was R2 = 0.057. Hence, the Apple Watch was proven to have better AF detection precision than the FitBit [51][9]. When the PPG screening app was used for AF detection, a positive predictive value of 91.6% was observed in patients who were confirmed to have AF (CI: 91.5–91.8%) [27][10]. Bashar et al. also proposed a method of AF detection that detects noise artifacts and motion by performing a time-frequency PPG signal analysis. Further, their algorithm to detect premature atrial contraction was used for AF detection with a higher accuracy. The proposed method showed a specificity, sensitivity, and accuracy of 97.43%, 98.18%, and 97.54%, respectively [28][11]. In a study by Koshy et al., the researchers monitored sinus rhythm using two different wearables (FitBit and Apple Watch) that collected heart rate data. For the detection of atrial arrhythmias, both the devices showed good results. However, the Apple Watch (r = 0.83) showed a better correlation than the FitBit (r = 0.56) [52][12]. Photoplethysmogram (PPG) signals derived from wearables or smartphones could be useful for monitoring cardiac health after signal corruptions and noise are removed. It was found that these denoised PPG signals could effectively predict coronary artery disease (CAD) [53][13]. Apart from the commercial smartwatches, smartwatches such as Kick LL are being developed for the purpose of monitoring respiration and heart rate [26][14].
Smartwatches have emerged as a new-age diagnostic tool for recording multichannel ECGs [24][15]. For this purpose, smartwatches can be attached to different body parts such as the chest or abdomen. Samol et al. have shown the possibility of an early ECG differential diagnosis of cardiac diseases [54][16]. The QT interval was also measured using a smartwatch, and the result showed a correlation of up to 0.994 with standard ECG data [25][17].

2. Neurological Disorders and Stress

Wearable devices have allowed for the continuous monitoring of our physiology, which has made the detection and treatment of chronic diseases, such as neurological disorders and mental health problems, possible. Electrodermal activity (EDA) shows the activity of the sympathetic nervous system, and thus is a potential tool for tracking arousal and autonomic regulation. EDA data are usually collected from the fingertips, wrists, or ankles. It is known that measuring EDA consumes less power than other monitoring methods and is a simple process. There are EDA-measuring wristbands on the market with embedded EDA sensors where the wristbands are made up of electrically conductive fabric [55][18]. However, EDA values can be affected by various other factors, including the environmental, skin, and room temperatures [56][19]. These limitations become especially important when an EDA sensor is employed in a wearable device controlled by temperatures [57][20]. The EDA sensor indicates the activity of eccrine sweat glands, which varies with the psychological state [58][21]. There is a positive correlation between EDA values and skin temperature (r = 0.13, p < 0.001). A study was performed to understand the performance of a student in real-time during an exam [59][22]. It has also been found that EDA measurements from wearable sensors are useful for detecting epileptic seizures. A surge in EDA was detected during an epileptic seizure, which implies a great sympathetic discharge [15,32,60][23][24][25]. Another study showed that wearable sensors could also be used to detect social anxiety in people, and thereby improve the monitoring and treatment of social anxiety. The data used for this purpose were heart rate, EDA, and skin temperature (ST). This study also demonstrated that these sensors could distinguish among different levels of anxiety in an individual [61][26].
Wearable devices appear to be a useful tool for characterizing different parameters in different dementia-type diseases such as Parkinson’s disease (PD) and Alzheimer’s disease (AD) [62][27]. Sensors carried by the wrist-worn device StepWatch are used for the quantitative diagnosis of Parkinson’s disease and multiple sclerosis by counting the strides of the users [35][28]. Researchers are also using inertial sensors in wearables for the continuous detection of rest tremors and dyskinesia in patients suffering from PD [63,64][29][30]. The accelerometers in these watches can differentiate between postural tremors and essential tremors in PD patients by calculating the peak harmonic power and frequency. They accurately provide diagnostic information in terms of postural tremors [65,66][31][32]. Sigcha et al. also showed a high correlation (0.969) between measurements of resting tremors using smartwatch data and clinical measurements [37][33]. Based on tremor measurements using wearable devices, the classification between differential diagnoses and healthy patients reached 86.5% precision [67][34]. EchoWear, a smartwatch-based speech and voice exercise monitoring system, was implemented to detect voice and speech disorders in PD patients [36][35]. A framework called SPARK, employing wearable devices and smartphones, was developed for the detection of multiple symptoms associated with PD [68][36]. The early diagnosis of PD is also possible from activity data during sleep and sleep quality data [33][37]. Apart from the tremor detection, smartwatches are used to measure ‘plate-to-mouth’ time during eating, which reflects the intensity of the disease [34][38].
For AD patients, wearables are used as digital biomarkers [69][39]. They are used for the inference-based diagnosis of behavioral events using inertial motion data [70][40]. The early diagnosis of mild cognitive impairments (MCIs) is also possible by using wrist-worn wearables [71][41]. Apart from the diagnosis, consumer-wearable devices have a great usefulness for patient care and the monitoring of elderly AD patients [72][42]. By implementing specific sensors into wearable devices, Al-Naami et al. developed a smart wearable device for alerting AD patients to fall-down conditions [73][43].

3. Fatty Liver Diseases

Nonalcoholic fatty liver diseases (NAFLDs) are rapidly increasing in number and becoming the primary cause of most liver-associated deaths globally. The major cause of all liver diseases is physical inactivity. Wearable devices help individuals to track their physical activity at a minute level. Hence, data from wearable devices act as a wellness indicator for patients suffering with liver diseases. An improvement in physical activity leads to an improvement in cardiorespiratory fitness, and this can be measured with cardiopulmonary exercise testing (CPET). CPET is found to be useful in identifying risks in transplant hepatology [74][44]. These wearables are not only useful for detecting and identifying liver diseases, but are also useful for keeping track of physical activities that have shown to be helpful for NAFLD and hepatocellular carcinoma (HCC) patients. In a study by Kim et al., patients were monitored using Neofit (Partron Co), which recorded the calories burnt, step count, exercise duration, and heart rate. After 12 weeks of following the exercise program, the body composition and physical fitness significantly improved in the HCC patients who completed their therapy [39][45]. Similarly, a study by Schneider et al. recorded the physical activity of participants using a wrist accelerometer and detected that an increase in physical activity resulted in a dose-dependent reduction in liver disease, which appeared to be independent of adiposity [38][46].

4. Corona Virus Diseases

In the context of the pandemic caused by the 2019 coronavirus disease (COVID-19), researchers used data on heart rate, step count, and calories burnt, recorded by wearable devices, to detect COVID-19 infections in pre-symptomatic and asymptomatic conditions [75][47]. Lonini et al. have demonstrated how these consumer-grade wearables collecting data for a very long period could be useful for detecting the symptoms of such viral infections in an individual. A wearable designed to be worn on the suprasternal notch can track physical activity, cough sounds, and cardio-respiratory function [76][48]. Snyder et al. used the resting heart rate difference (RHR-diff) method and the heart-rate-over-steps anomaly detection (HROS-AD) method for the early detection of anomalies in the recorded data of COVID-19 patients, even 3 days (median value) before the onset of symptoms [16,17][49][50]. In another study, a gradient-boosting algorithm was used to detect an infection and the important symptoms [77][51]. Quer et al. provided a wearable device data model that complemented conventional virus-testing methods to detect COVID-19 infections [78][52]. In another study, Bogu and Snyder showed that using wearable data 7 days prior to COVID-19 detection and 21 days after the detection could recognize COVID-19 infections using a deep-learning-based method of a long short-term memory network-based autoencoder (LAAD). LAAD detects COVID-19 based on an abnormal resting heart rate during the period of infection. It was able to detect COVID-19 in the pre-symptomatic period as well as the symptomatic phase of the patients, with a precision score of 0.91 (CI: 0.854–0.967) [10][53]. Cho et al. proposed a one-class SVM method that can detect COVID-19 23.5–40% earlier compared to the method of Mishra et al. [16,79][49][54].

5. Metabolic Disorders

Metabolic diseases, such as diabetes, affect millions of people around the world every year. They increase the chance of multiple organ failure and result in a decreased quality of life [80][55]. Consumer wearables such as fitness trackers are also useful in diabetes patients. It has been found that physical activity (PA) has a major effect on glucose concentration. The effect of PA depends on the intensity, mode, and duration of the exercise [81][56]. Wearable smart devices are useful tools for the self-monitoring of activity by the patient and for remote monitoring by the caregivers. A clinical trial is ongoing to explore the efficacy of integrated do-it-yourself smartwatch glucose monitoring compared to scanned continuous glucose-monitoring systems [82][57]. In another study, Fitbit® data from diabetic patients were used to correlate the association of physical activity with glycemic exposure. Further, assessing PA quantitatively may show to be useful in making mealtime treatment decisions. It was also observed that participating in PA every day demonstrated an immediate or later impact on glucose control [30][58]. Akyol et al. reported a novel consumer-wearable device called Diafit that works as a customizable glucose monitor for diabetes patients [40][59]. In a study by Weatherall et al., the researchers demonstrated an association between sleep and PA data from these wearable devices (Fitbit Charge HR) and the information reported by the type 2 diabetes mellitus (T2DM) patients themselves. It was observed that the self-reported data were positively associated with both the PA data (r = 0.35, p = 0.001) and the sleep data (r = 0.24, p = 0.04) [31][60]. Hence, it is believed that monitoring patients extensively could allow them to make decisions on disease treatments. In addition, data from these wearables have the potential to improve patient-reported outcomes and their care. There is also a non-invasive method of monitoring glucose that is performed by pressing the wrist or fingertip on the thin glass behind any smart wristwatch, which consist of a chemochromic mixture that has the same function as a PPG sensor. These chemochromic components facilitate the measurement of various metabolites from sweat, which are further used to obtain the glucose concentration using neural network algorithms built into the PPG sensor. The values obtained from this showed a high correlation with invasive methods of monitoring glucose. Hence, wearables provide a non-invasive, miniaturized, easy-to-operate, and novel method for glucometry, which could be used as an alternative to invasive tools in clinical settings [83][61]. In another study reported by Lee et al., smartwatch data along with other digital data were used to enable the better prevention of metabolic syndromes by the continuous detection of several health factors [41][62].

6. Sleep Quality

Sleep is important for normal bodily functions and for good health. A lack of sleep can have physical, emotional, and mental effects and can lead to serious health conditions, especially among diseased individuals. Both PA and sleep are related to each other. Wearable technology is currently being used to track PA and sleep, which could help researchers study sleep science in-depth, resulting in the better diagnosis of sleep-related disorders [84][63]. Sathyanarayana et al. demonstrated that deep learning can be used to predict sleep quality (whether it was good or poor) by making use of an actigraph obtained from the waking hours of an individual [85][64]. In another study by Berryhill et al., it was reported that a wearable sleep tracker could improve sleep quality in healthy people and track the quality as well as quantity of sleep. They also compared the sleep quality measured by wearables and polysomnography. The wearables showed a low precision error (17.8 min) when measuring sleep duration [44][65]. Currently, there are so many sleep trackers available on the market that it is difficult to discern which one is the best. Lees et al. performed a comparison among various wearables that track sleep and time in bed by using a sleep diary (SD). The Jawbone UP3 and Fitbit Charge Heart Rate devices showed the greatest equivalence to the SD in terms of sleeping time. The SenseWear Armband, Garmin Vivosmart, and Jawbone UP3 devices showed the greatest equivalence to the SD in terms of time in bed [86][66]. Meharabadi et al. used a wearable ring and watch to measure sleep quality, and observed that for total sleep time, the correlation of the actigraphy data with the ring data was 0.86 (p < 0.001); with the watch data, the correlation was much lower, at 0.59 (p < 0.001) [42][67]. Topalidis et al. also observed that wrist-worn device data and actigraph reports that derived the wake-up time and sleep time had high correlations (0.96 and 0.84, respectively; p < 0.001) with subjective reports [87][68]. In a study conducted by Chen at al., a PPG smartwatch outperformed the polysomnography method for detecting obstructive sleep apnea. An accuracy of 81.1% was achieved [43][69]. Papini et al. also observed that a wrist-worn PPG-integrated smartwatch could complement the standard apnea diagnostic techniques with a relatively lower correlation of 0.61 [88][70]. Ko et al. conducted a study on sleep quantification in PD patients using smartwatches, and detected abnormal rapid eye movements. They also observed that the percentage of the deep-sleep stage differs between healthy (38.1) and PD (22.0) patients [89][71].

7. Psychological Illness

Apart from detecting physiological illnesses, wearable devices play an important role in addressing psychological characteristics that are often neglected due to a lack of symptomatic evidence. Wearable device data equipped with ML algorithms are helpful for extracting the highly personalized nature of psychological conditions such as depression and mood swings. A recent study on 14 young people using EEG data, neurocognitive assessments, and lifestyle data from wearable devices revealed that each person had distinct depression determinants [90][72]. Hence, highly personalized diagnoses and treatments are required. In another interesting study, pictures were shown to the participants of the study. A machine-learning analysis further identified important features, and classifiers were used to predict the valence and arousal. Although the accuracy was not significantly high (69.9%), it showed the possibility of identifying emotional states using wearable devices [91,92,93][73][74][75]. Apart from the emotional state, the supervised machine-learning and gradient-boosting algorithm DART (dropouts meet multiple additive regression trees) [94][76] has been used for the detection of depression in a group of working young people wearing a Fitbit wristband. This was further evaluated by performing a k-fold cross-validation on the test sets. The study showed that the severity of depression symptoms was associated with nighttime heart rate variation [45][77]. Anxiety and depression have also been diagnosed in children with the help of wearable data devices and a machine-learning method such as k-nearest neighbor (kNN). A diagnosis accuracy of 75% was achieved by using the kNN method [95][78]. Stress is another mental health issue that has become very prevalent among adults. 

References

  1. WHO. Fact Sheets on Cardiovascular Diseases . 11 May 2022. Available online: https://www.who.int/en/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds) (accessed on 15 June 2022).
  2. Bayoumy, K.; Gaber, M.; Elshafeey, A.; Mhaimeed, O.; Dineen, E.H.; Marvel, F.A.; Martin, S.S.; Muse, E.D.; Turakhia, M.P.; Tarakji, K.G.; et al. Smart wearable devices in cardiovascular care: Where we are and how to move forward. Nat. Rev. Cardiol. 2021, 18, 581–599.
  3. Yen, H.Y.; Huang, W.H. The efficacy of commercial smartwatches with a blood pressure-monitoring feature: A pilot randomized controlled trial. J. Nurs. Scholarsh. 2022, 54, 324–331.
  4. Gkikopoulos, N.; Wenger, M.; Distler, O.; Becker, M. Self-monitoring of the resting heart rate using a fitness tracker smartwatch application leads to an early diagnosis of large vessel vasculitis. BMJ Case Rep. 2022, 15, e245021.
  5. Rens, N.; Gandhi, N.; Mak, J.; Paul, J.; Bent, D.; Liu, S.; Savage, D.; Nielsen-Bowles, H.; Triggs, D.; Ata, G.; et al. Activity data from wearables as an indicator of functional capacity in patients with cardiovascular disease. PLoS ONE 2021, 16, e0247834.
  6. Teo, J.X.; Davila, S.; Yang, C.; Hii, A.A.; Pua, C.J.; Yap, J.; Tan, S.Y.; Sahlén, A.; Chin, C.W.L.; Teh, B.T.; et al. Digital phenotyping by consumer wearables identifies sleep-associated markers of cardiovascular disease risk and biological aging. Commun. Biol. 2019, 2, 361.
  7. Kalla, M.; Fabritz, L.; Kirchhof, P. SMART About Watches: We Need Technical and Biological Validation of Atrial Fibrillation Screening. JACC Clin. Electrophysiol. 2019, 5, 209–211.
  8. Tison, G.H.; Sanchez, J.M.; Ballinger, B.; Singh, A.; Olgin, J.E.; Pletcher, M.J.; Vittinghoff, E.; Lee, E.S.; Fan, S.M.; Gladstone, R.A.; et al. Passive Detection of Atrial Fibrillation Using a Commercially Available Smartwatch. JAMA Cardiol. 2018, 3, 409–416.
  9. Inui, T.; Kohno, H.; Kawasaki, Y.; Matsuura, K.; Ueda, H.; Tamura, Y.; Watanabe, M.; Inage, Y.; Yakita, Y.; Wakabayashi, Y.; et al. Use of a Smart Watch for Early Detection of Paroxysmal Atrial Fibrillation: Validation Study. JMIR Cardio 2020, 4, e14857.
  10. Guo, Y.; Wang, H.; Zhang, H.; Liu, T.; Liang, Z.; Xia, Y.; Yan, L.; Xing, Y.; Shi, H.; Li, S.; et al. Mobile Photoplethysmographic Technology to Detect Atrial Fibrillation. J. Am. Coll. Cardiol. 2019, 74, 2365–2375.
  11. Bashar, S.K.; Han, D.; Hajeb-Mohammadalipour, S.; Ding, E.; Whitcomb, C.; McManus, D.D.; Chon, K.H. Atrial Fibrillation Detection from Wrist Photoplethysmography Signals Using Smartwatches. Sci. Rep. 2019, 9, 15054.
  12. Koshy, A.N.; Sajeev, J.K.; Nerlekar, N.; Brown, A.J.; Rajakariar, K.; Zureik, M.; Wong, M.C.; Roberts, L.; Street, M.; Cooke, J.; et al. Smart watches for heart rate assessment in atrial arrhythmias. Int. J. Cardiol. 2018, 266, 124–127.
  13. Ukil, A.; Bandyopadhyay, S.; Puri, C.; Pal, A.; Mandana, K. Cardiac condition monitoring through photoplethysmogram signal denoising using wearables: Can we detect coronary artery disease with higher performance efficacy? In Proceedings of the IEEE Computing in Cardiology Conference, Vancouver, BC, Canada, 11–14 September 2016.
  14. Hoilett, O.S.; Twibell, A.M.; Srivastava, R.; Linnes, J.C. Kick LL: A Smartwatch for Monitoring Respiration and Heart Rate using Photoplethysmography. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Honolulu, HI, USA, 18–21 July 2018; Volume 2018, p. 3824.
  15. Samol, A.; Bischoff, K.; Luani, B.; Pascut, D.; Wiemer, M.; Kaese, S. Recording of Bipolar Multichannel ECGs by a Smartwatch: Modern ECG Diagnostic 100 Years after Einthoven. Sensors 2019, 19, 2894.
  16. Samol, A.; Bischof, K.; Luani, B.; Pascut, D.; Wiemer, M.; Kaese, S. Single-Lead ECG Recordings Including Einthoven and Wilson Leads by a Smartwatch: A New Era of Patient Directed Early ECG Differential Diagnosis of Cardiac Diseases? Sensors 2019, 19, 4377.
  17. Spaccarotella, C.A.M.; Migliarino, S.; Mongiardo, A.; Sabatino, J.; Santarpia, G.; De Rosa, S.; Curcio, A.; Indolfi, C. Measurement of the QT interval using the Apple Watch. Sci. Rep. 2021, 11, 10817.
  18. Fletcher, R.R.; Poh, M.Z.; Eydgahi, H. Wearable sensors: Opportunities and challenges for low-cost health care. In Proceedings of the 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, Buenos Aires, Argentina, 31 August–4 September 2010; pp. 1763–1766.
  19. Turpin, G.; Shine, P.; Lader, M. Ambulatory Electrodermal Monitoring: Effects of Ambient Temperature, General Activity, Electrolyte Media, and Length of Recording. Psychophysiology 1983, 20, 219–224.
  20. Qasim, M.S.; Bari, D.; Martinsen, O.G. Influence of ambient temperature on tonic and phasic electrodermal activity components. Physiol. Meas. 2022, 43, 065001.
  21. Christie, M.J. Electrodermal activity in the 1980s: A review. J. R. Soc. Med. 1981, 74, 616–622.
  22. Khan, T.H.; Villanueva, I.; Vicioso, P.; Husman, J. Exploring relationships between electrodermal activity, skin temperature, and performance during. In Proceedings of the 2019 IEEE Frontiers in Education Conference (FIE), Covington, KY, USA, 16–19 October 2019.
  23. Tang, J.; El Atrache, R.; Yu, S.; Asif, U.; Jackson, M.; Roy, S.; Mirmomeni, M.; Cantley, S.; Sheehan, T.; Schubach, S.; et al. Seizure detection using wearable sensors and machine learning: Setting a benchmark. Epilepsia 2021, 62, 1807–1819.
  24. Poh, M.Z.; Loddenkemper, T.; Swenson, N.C.; Goyal, S.; Madsen, J.R.; Picard, R.W. Continuous monitoring of electrodermal activity during epileptic seizures using a wearable sensor. In Proceedings of the 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, Buenos Aires, Argentina, 31 August–4 September 2010; pp. 4415–4418.
  25. Onorati, F.; Regalia, G.; Caborni, C.; Migliorini, M.; Bender, D.; Poh, M.Z.; Frazier, C.; Kovitch Thropp, E.; Mynatt, E.D.; Bidwell, J.; et al. Multicenter clinical assessment of improved wearable multimodal convulsive seizure detectors. Epilepsia 2017, 58, 1870–1879.
  26. Shaukat-Jali, R.; van Zalk, N.; Boyle, D.E. Detecting Subclinical Social Anxiety Using Physiological Data from a Wrist-Worn Wearable: Small-Scale Feasibility Study. JMIR Form. Res. 2021, 5, e32656.
  27. Mc Ardle, R.; Del Din, S.; Galna, B.; Thomas, A.; Rochester, L. Differentiating dementia disease subtypes with gait analysis: Feasibility of wearable sensors? Gait Posture 2020, 76, 372–376.
  28. Schmidt, A.L.; Pennypacker, M.L.; Thrush, A.H.; Leiper, C.I.; Craik, R.L. Validity of the stepwatch step activity monitor: Preliminary findings for use in persons with parkinson disease and multiple sclerosis. J. Geriatr. Phys. Ther. 2011, 34, 41–45.
  29. Powers, R.; Etezadi-Amoli, M.; Arnold, E.M.; Kianian, S.; Mance, I.; Gibiansky, M.; Trietsch, D.; Alvarado, A.S.; Kretlow, J.D.; Herrington, T.M.; et al. Smartwatch inertial sensors continuously monitor real-world motor fluctuations in Parkinson’s disease. Sci. Transl. Med. 2021, 13, abd7865.
  30. López-Blanco, R.; Velasco, M.A.; Méndez-Guerrero, A.; Romero, J.P.; del Castillo, M.D.; Serrano, J.I.; Rocon, E.; Benito-León, J. Smartwatch for the analysis of rest tremor in patients with Parkinson’s disease. J. Neurol. Sci. 2019, 401, 37–42.
  31. Wile, D.J.; Ranawaya, R.; Kiss, Z.H.T. Smart watch accelerometry for analysis and diagnosis of tremor. J. Neurosci. Methods 2014, 230, 1–4.
  32. Khwaounjoo, P.; Singh, G.; Grenfell, S.; Özsoy, B.; MacAskill, M.R.; Anderson, T.J.; Çakmak, Y.O. Non-Contact Hand Movement Analysis for Optimal Configuration of Smart Sensors to Capture Parkinson’s Disease Hand Tremor. Sensors 2022, 22, 4613.
  33. Sigcha, L.; Pavón, I.; Costa, N.; Costa, S.; Gago, M.; Arezes, P.; López, J.M.; Arcas, G. De Automatic Resting Tremor Assessment in Parkinson’s Disease Using Smartwatches and Multitask Convolutional Neural Networks. Sensors 2021, 21, 291.
  34. Varghese, J.; van Alen, C.M.; Fujarski, M.; Schlake, G.S.; Sucker, J.; Warnecke, T.; Thomas, C. Sensor validation and diagnostic potential of smartwatches in movement disorders. Sensors 2021, 21, 3139.
  35. Dubey, H.; Goldberg, J.C.; Abtahi, M.; Mahler, L.; Mankodiya, K. EchoWear: Smartwatch technology for voice and speech treatments of patients with Parkinson’s disease. In Proceedings of the Proceedings of the conference on Wireless Health, New York, NY, USA, 14–16 October 2015; pp. 1–8.
  36. Sharma, V.; Mankodiya, K.; De La Torre, F.; Zhang, A.; Ryan, N.; Ton, T.G.N.; Gandhi, R.; Jain, S. Spark: Personalized parkinson disease interventions through synergy between a smartphone and a smartwatch. In Design, User Experience, and Usability. User Experience Design for Everyday Life Applications and Services; Springer: Cham, Switzerland, 2014; Volume 8519, pp. 103–114.
  37. Iakovakis, D.; Mastoras, R.E.; Hadjidimitriou, S.; Charisis, V.; Bostanjopoulou, S.; Katsarou, Z.; Klingelhoefer, L.; Reichmann, H.; Trivedi, D.; Chaudhuri, R.K.; et al. Smartwatch-based Activity Analysis During Sleep for Early Parkinson’s Disease Detection. In Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 20–24 July 2020; pp. 4326–4329.
  38. Kyritsis, K.; Fagerberg, P.; Ioakimidis, I.; Chaudhuri, K.R.; Reichmann, H.; Klingelhoefer, L.; Delopoulos, A. Assessment of real life eating difficulties in Parkinson’s disease patients by measuring plate to mouth movement elongation with inertial sensors. Sci. Rep. 2021, 11, 1632.
  39. Kourtis, L.C.; Regele, O.B.; Wright, J.M.; Jones, G.B. Digital biomarkers for Alzheimer’s disease: The mobile/wearable devices opportunity. NPJ Digit. Med. 2019, 2, 9.
  40. Alam, R.; Anderson, M.; Bankole, A.; Lach, J. Inferring physical agitation in dementia using smartwatch and sequential behavior models. In Proceedings of the IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2018, Las Vegas, NV, USA, 4–7 March 2018; Volume 2018-January, pp. 170–173.
  41. Gwak, M.; Woo, E.; Sarrafzadeh, M. The role of accelerometer and gyroscope sensors in identification of mild cognitive impairment. In Proceedings of the IEEE Global Conference on Signal and Information Processing, Anaheim, CA, USA, 26–29 November 2018; pp. 434–438.
  42. Maresova, P.; Tomsone, S.; Lameski, P.; Madureira, J.; Mendes, A.; Zdravevski, E.; Chorbev, I.; Trajkovik, V.; Ellen, M.; Rodile, K. Technological Solutions for Older People with Alzheimer’s Disease: Review. Curr. Alzheimer Res. 2018, 15, 975–983.
  43. Al-Naami, B.; Owida, H.A.; Mallouh, M.A.; Al-Naimat, F.; Agha, M.; Al-Hinnawi, A.R. A New Prototype of Smart Wearable Monitoring System Solution for Alzheimer’s Patients. Med. Devices Evid. Res. 2021, 14, 423–433.
  44. Dunn, M.A.; Kappus, M.R.; Bloomer, P.M.; Duarte-Rojo, A.; Josbeno, D.A.; Jakicic, J.M. Wearables, Physical Activity, and Exercise Testing in Liver Disease. Semin. Liver Dis. 2021, 41, 128–135.
  45. Kim, Y.; Seo, J.; An, S.Y.; Sinn, D.H.; Hwang, J.H. Efficacy and Safety of an mHealth App and Wearable Device in Physical Performance for Patients With Hepatocellular Carcinoma: Development and Usability Study. JMIR mHealth uHealth 2020, 8, e14435.
  46. Schneider, C.V.; Zandvakili, I.; Thaiss, C.A.; Schneider, K.M. Physical activity is associated with reduced risk of liver disease in the prospective UK Biobank cohort. JHEP Reports 2021, 3, 100263.
  47. Zhu, T.; Watkinson, P.; Clifton, D.A. Smartwatch data help detect COVID-19. Nat. Biomed. Eng. 2020, 4, 1125–1127.
  48. Lonini, L.; Shawen, N.; Botonis, O.; Fanton, M.; Jayaraman, C.; Mummidisetty, C.K.; Shin, S.Y.; Rushin, C.; Jenz, S.; Xu, S.; et al. Rapid Screening of Physiological Changes Associated with COVID-19 Using Soft-Wearables and Structured Activities: A Pilot Study. IEEE J. Transl. Eng. Health Med. 2021, 9, 4900311.
  49. Mishra, T.; Wang, M.; Metwally, A.A.; Bogu, G.K.; Brooks, A.W.; Bahmani, A.; Alavi, A.; Celli, A.; Higgs, E.; Dagan-Rosenfeld, O.; et al. Pre-symptomatic detection of COVID-19 from smartwatch data. Nat. Biomed. Eng. 2020, 4, 1208–1220.
  50. Alavi, A.; Bogu, G.K.; Wang, M.; Rangan, E.S.; Brooks, A.W.; Wang, Q.; Higgs, E.; Celli, A.; Mishra, T.; Metwally, A.A.; et al. Real-time alerting system for COVID-19 and other stress events using wearable data. Nat. Med. 2022, 28, 175–184.
  51. Gadaleta, M.; Radin, J.M.; Baca-Motes, K.; Ramos, E.; Kheterpal, V.; Topol, E.J.; Steinhubl, S.R.; Quer, G. Passive detection of COVID-19 with wearable sensors and explainable machine learning algorithms. NPJ Digit. Med. 2021, 4, 166.
  52. Quer, G.; Radin, J.M.; Gadaleta, M.; Baca-Motes, K.; Ariniello, L.; Ramos, E.; Kheterpal, V.; Topol, E.J.; Steinhubl, S.R. Wearable sensor data and self-reported symptoms for COVID-19 detection. Nat. Med. 2021, 27, 73–77.
  53. Bogu, G.K.; Snyder, M.P. Deep learning-based detection of COVID-19 using wearables data. MedRxiv 2021.
  54. Cho, H.R.; Kim, J.H.; Yoon, H.R.; Han, Y.S.; Kang, T.S.; Choi, H.; Lee, S. Machine learning-based optimization of pre-symptomatic COVID-19 detection through smartwatch. Sci. Rep. 2022, 12, 7886.
  55. Ramesh, J.; Aburukba, R.; Sagahyroon, A. A remote healthcare monitoring framework for diabetes prediction using machine learning. Healthc. Technol. Lett. 2021, 8, 45.
  56. Yavelberg, L.; Zaharieva, D.; Cinar, A.; Riddell, M.C.; Jamnik, V. A Pilot Study Validating Select Research-Grade and Consumer-Based Wearables throughout a Range of Dynamic Exercise Intensities in Persons with and without Type 1 Diabetes: A Novel Approach. J. Diabetes Sci. Technol. 2018, 12, 569–576.
  57. Sehgal, S.; De Bock, M.; Williman, J.; Taylor, B.; Elbalshy, M.; Galland, B.; Hall, R.; Paul, R.; Boucsein, A.; Jones, S.; et al. Study protocol: Safety and efficacy of smart watch integrated do-it-yourself continuous glucose monitoring in adults with Type 1 diabetes, a randomised controlled trial. J. Diabetes Metab. Disord. 2021, 20, 2103–2113.
  58. Ozaslan, B.; Patek, S.D.; Breton, M.D. Impact of Daily Physical Activity as Measured by Commonly Available Wearables on Mealtime Glucose Control in Type 1 Diabetes. Diabetes Technol. Ther. 2020, 22, 742–748.
  59. Akyol, E.; Cabral Ramos Mota, R.C.; Somanath, S. DiaFit: Designing Customizable Wearables for Type 1 Diabetes Monitoring. In Conference on Human Factors in Computing Systems—Proceedings; Association for Computing Machinery: Yokohama, Japan, 2021; p. 437.
  60. Weatherall, J.; Paprocki, Y.; Meyer, T.M.; Kudel, I.; Witt, E.A. Sleep Tracking and Exercise in Patients with Type 2 Diabetes Mellitus (Step-D): Pilot Study to Determine Correlations Between Fitbit Data and Patient-Reported Outcomes. JMIR mHealth uHealth 2018, 6, e8122.
  61. Zilberstein, G.; Zilberstein, R.; Maor, U.; Righetti, P.G. Noninvasive wearable sensor for indirect glucometry. Electrophoresis 2018, 39, 2344–2350.
  62. Lee, J.-H.; Lee, K.-H.; Kim, H.-J.; Youk, H.; Lee, H.-Y.; Lee, J.-H.; Lee, K.-H.; Kim, H.-J.; Youk, H.; Lee, H.-Y. Effective Prevention and Management Tools for Metabolic Syndrome Based on Digital Health-Based Lifestyle Interventions Using Healthcare Devices. Diagnostics 2022, 12, 1730.
  63. Rentz, L.E.; Ulman, H.K.; Galster, S.M. Deconstructing Commercial Wearable Technology: Contributions toward Accurate and Free-Living Monitoring of Sleep. Sensors 2021, 21, 5071.
  64. Sathyanarayana, A.; Joty, S.; Fernandez-Luque, L.; Ofli, F.; Srivastava, J.; Elmagarmid, A.; Arora, T.; Taheri, S. Sleep Quality Prediction From Wearable Data Using Deep Learning. JMIR mHealth uHealth 2016, 4, e6562.
  65. Berryhill, S.; Morton, C.J.; Dean, A.; Berryhill, A.; Provencio-Dean, N.; Patel, S.I.; Estep, L.; Combs, D.; Mashaqi, S.; Gerald, L.B.; et al. Effect of wearables on sleep in healthy individuals: A randomized crossover trial and validation study. J. Clin. Sleep Med. 2020, 16, 775–783.
  66. Lee, J.M.; Byun, W.; Keill, A.; Dinkel, D.; Seo, Y. Comparison of Wearable Trackers’ Ability to Estimate Sleep. Int. J. Environ. Res. Public Health 2018, 15, 1265.
  67. Mehrabadi, M.A.; Azimi, I.; Sarhaddi, F.; Axelin, A.; Niela-Vilén, H.; Myllyntausta, S.; Stenholm, S.; Dutt, N.; Liljeberg, P.; Rahmani, A.M. Sleep Tracking of a Commercially Available Smart Ring and Smartwatch Against Medical-Grade Actigraphy in Everyday Settings: Instrument Validation Study. JMIR mHealth uHealth 2020, 8, e20465.
  68. Topalidis, P.; Florea, C.; Eigl, E.S.; Kurapov, A.; Leon, C.A.B.; Schabus, M. Evaluation of a Low-Cost Commercial Actigraph and Its Potential Use in Detecting Cultural Variations in Physical Activity and Sleep. Sensors 2021, 21, 3774.
  69. Chen, Y.; Wang, W.; Guo, Y.; Zhang, H.; Chen, Y.; Xie, L. A Single-Center Validation of the Accuracy of a Photoplethysmography-Based Smartwatch for Screening Obstructive Sleep Apnea. Nat. Sci. Sleep 2021, 13, 1533–1544.
  70. Papini, G.B.; Fonseca, P.; van Gilst, M.M.; Bergmans, J.W.M.; Vullings, R.; Overeem, S. Wearable monitoring of sleep-disordered breathing: Estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography. Sci. Rep. 2020, 10, 13512.
  71. Ko, Y.F.; Kuo, P.H.; Wang, C.F.; Chen, Y.J.; Chuang, P.C.; Li, S.Z.; Chen, B.W.; Yang, F.C.; Lo, Y.C.; Yang, Y.; et al. Quantification Analysis of Sleep Based on Smartwatch Sensors for Parkinson’s Disease. Biosensors 2022, 12, 74.
  72. Shah, R.V.; Grennan, G.; Zafar-Khan, M.; Alim, F.; Dey, S.; Ramanathan, D.; Mishra, J. Personalized machine learning of depressed mood using wearables. Transl. Psychiatry 2021, 11, 338.
  73. Laureanti, R.; Bilucaglia, M.; Zito, M.; Circi, R.; Fici, A.; Rivetti, F.; Valesi, R.; Oldrini, C.; Mainardi, L.T.; Russo, V. Emotion assessment using Machine Learning and low-cost wearable devices. In Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada, 20–24 July 2020; pp. 576–579.
  74. Pollreisz, D.; Taherinejad, N. A simple algorithm for emotion recognition, using physiological signals of a smart watch. In Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Korea, 11–15 July 2017; pp. 2353–2356.
  75. Quiroz, J.C.; Geangu, E.; Yong, M.H. Emotion Recognition Using Smart Watch Sensor Data: Mixed-Design Study. JMIR Ment. Health 2018, 5, e10153.
  76. Priyadarshini, R.K.; Bazila Banu, A.; Nagamani, T. Gradient Boosted Decision Tree based Classification for Recognizing Human Behavior. In Proceedings of the 2019 International Conference on Advances in Computing and Communication Engineering (ICACCE), Sathyamangalam, India, 4–6 April 2019.
  77. Rykov, Y.; Thach, T.Q.; Bojic, I.; Christopoulos, G.; Car, J. Digital Biomarkers for Depression Screening With Wearable Devices: Cross-sectional Study With Machine Learning Modeling. JMIR mHealth uHealth 2021, 9, e24872.
  78. McGinnis, R.S.; McGinnis, E.W.; Hruschak, J.; Lopez-Duran, N.L.; Fitzgerald, K.; Rosenblum, K.L.; Muzik, M. Rapid Anxiety and Depression Diagnosis in Young Children Enabled by Wearable Sensors and Machine Learning. In Proceedings of the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA, 18–21 July 2018; pp. 3983–3986.
More
Video Production Service