This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR mhealth and uhealth, is properly cited. The complete bibliographic information, a link to the original publication on http://mhealth.jmir.org/, as well as this copyright and license information must be included.
Health care, in recent years, has made great leaps in integrating wireless technology into traditional models of care. The availability of ubiquitous devices such as wearable sensors has enabled researchers to collect voluminous datasets and harness them in a wide range of health care topics. One of the goals of using on-body wearable sensors has been to study and analyze human activity and functional patterns, thereby predicting harmful outcomes such as falls. It can also be used to track precise individual movements to form personalized behavioral patterns, to standardize the concept of frailty, well-being/independence, etc. Most wearable devices such as activity trackers and smartwatches are equipped with low-cost embedded sensors that can provide users with health statistics. In addition to wearable devices, Bluetooth low-energy sensors known as BLE beacons have gained traction among researchers in ambient intelligence domain. The low cost and durability of newer versions have made BLE beacons feasible gadgets to yield indoor localization data, an adjunct feature in human activity recognition. In the studies by Moatamed et al and the patent application by Ramezani et al, we introduced a generic framework (Sensing At-Risk Population) that draws on the classification of human movements using a 3-axial accelerometer and extracting indoor localization using BLE beacons, in concert.
The study aimed to examine the ability of combination of physical activity and indoor location features, extracted at baseline, on a cohort of 154 rehabilitation-dwelling patients to discriminate between subacute care patients who are re-admitted to the hospital versus the patients who are able to stay in a community setting.
We analyzed physical activity sensor features to assess activity time and intensity. We also analyzed activities with regard to indoor localization. Chi-square and Kruskal-Wallis tests were used to compare demographic variables and sensor feature variables in outcome groups. Random forests were used to build predictive models based on the most significant features.
Standing time percentage (
This study demonstrates that a combination of indoor localization and physical activity tracking produces a series of features at baseline, a subset of which can better distinguish between at-risk patients that can gain independence versus the patients that are rehospitalized.
According to the most recent census statistics, by 2050, the population aged 65 years and older is projected to double in size to 83.7 million in the United States [
Numerous studies have investigated the effectiveness of remote patient health monitoring, some suggesting the potential for such technologies to reduce the overall re-admission cost [
Details of the system architecture with proximity-based sensors (beacons) and a Bluetooth-enabled smartwatch as its main components can be found in the study by Moatamed et al [
Beacons broadcast their presence to Bluetooth-enabled devices. Utilizing the beacons’ Received Signal Strength Indicator (RSSI) values using smartwatches, the SARP system calculates the proximity of the watch to each beacon, thereby inferring the indoor location of the patient wearing that watch. BLE beacons (bluetooth low-energy sensors) have become popular in gathering contextual awareness because of durability and low cost. When used in health care, however, validating reliability and accuracy of their location information is paramount. Beacons are highly susceptible to diffraction, multipath propagation, angle-of-arrival, lack of line-of-sight, and absorption by the human body. In this project, because locations of interest were within close proximity, we considered RSSI values ranged between −50 dBm to −100 dBm. The average RSSI within the line-of-sight, measured by the watch at 1 feet distance, was −66 dBm. To achieve the best accuracy with respect to locations of interest, shown in
Subacute rehabilitation facility map: resident room on top and therapy room at the bottom with locations of mounted beacons shown in red.
To infer physical activity of patients in this study, 3-axis raw acceleration signal sampled at 16 Hz was extracted, and the signal magnitude (SM) was initially calculated according to
A decade has passed since the advent of commercially available low-cost, light-weight accelerometers. The enthusiasm about their potential in extracting physical patterns to usually, but not exclusively, improve health outcomes has led researchers to master the techniques of activity recognition [
Equations. MAD: mean absolute deviation.
Hierarchical Activity Recognition Pseudo Code.
Walking embodies active status, and when stationary, the classifier separates brisk (active) and idle (nonactive) movements and later classifies postures into sedentary, standing, and laying down. Both
The next stage was to find a way to quantify the difference between different activity status. Step counting is a common way that has long been used to quantify the ambulatory physical activity. However, similar to activity recognition approaches explained earlier, the accuracy of step counters is often the subject of debate among researchers. Comprehensive studies with contradictory results on the accuracy of pedometers and wearable accelerometers can be found in the studies by Crouter et al [
where xi is the SM in each 10-second window, and the xave is the average of accelerometer magnitude for 160 samples (10-second epoch×16 Hz). MAD of accelerometer magnitude represents the average magnitude of acceleration within an interval (in this case, 10 seconds) and is proportionate to force applied to the watch by patient since f=ma. This value multiplied into displacement will produce relative work and energy. Take into account that calculating displacement from acceleration, however, is not very accurate because it is the result of accelerometer’s double integration, that is, any acceleration jitter accumulates and yields big drifts in displacement. Calculating force, however, is accurate and proportionate to energy; hence, the term
Another way of quantifying activity is to integrate each acceleration channel to produce kinetic energy using e=1/2m.v2. This way, however, requires more calculations compared with MAD; for the actual speed, each channel should be considered separately so that the direction of acceleration and deceleration that are removed in SM will be taken into account.
It is worth highlighting that by using a smartwatch accelerometer, it is only possible to calculate the force, proportionate to energy, that is spent
Active/nonactive is determined in this study using an empirical threshold of 0.02 m/s2 (2 cm/s2) over the MAD value. As explained earlier, calculating displacement from the accelerometer is not highly reliable. However, for illustrative purposes, assume the initial speed of hand movement in each window of 10 seconds is zero. Using equation 3 shown in
Online watch classifier.
Class | TPa rate | FPb rate | Precision | Recall | F-measure | ROCc area |
Stationary | 0.992 | 0.015 | 0.977 | 0.992 | 0.984 | 0.954 |
Walking | 0.985 | 0.008 | 0.995 | 0.985 | 0.990 | 0.992 |
Weighted average | 0.988 | 0.011 | 0.988 | 0.988 | 0.974 | 0.929 |
aTP: true positive.
bFP: false positive.
cROC: receiver operating characteristic.
Activity recognition: positioning.
Position | Accuracy | Precision | Recall | F-measure |
Stand | 91 | 0.94 | 0.91 | 0.92 |
Sit | 93.7 | 0.87 | 0.93 | 0.90 |
Lay | 90.8 | 0.97 | 0.90 | 0.94 |
Walk | 95.1 | 0.92 | 0.95 | 0.94 |
Magnitude of accelerometer signal after filtering (direct current component removed before filtering).
From June 2016 to November 2017, we recruited patients after admission to a subacute rehabilitation center in Los Angeles. We performed a cross-sectional baseline study of this cohort to better understand data features collected by the SARP system. We investigated the prevalence of physical activity tracking features and indoor localization features at baseline for both outcome groups (hospital vs long-term care). Moreover, we assessed their efficacy in determining the outcome (hospital vs long-term care).
Participants aged older than 60 years were recruited from a subacute rehabilitation facility in Los Angeles. The study cohort contains patients who had been admitted to a subacute rehabilitation center for 21 days. After this period, patients were either re-admitted to hospital (H) or stayed in community (C; either at home or long-term care). The inclusion criteria were broad, allowing any patient to participate as long as they were aged older than 60 years, English speaking, and able to consent with the exclusion criteria including movement disorders or paralysis of the upper or lower extremity. The diversity of cohort included patients who were a postsurgical, poststroke, and postclinical decompensation because of medical illnesses. Eligible participants signed a consent form approved by the University of California, Los Angeles, Institutional Review Board.
Patients were given a smartwatch by a clinical coordinator every morning at 9 am. Patients were asked to wear their watches at all times until the coordinator collected the watch at around 6 pm every day. Watch batteries were expected to last longer than the protocol period (>9 hours). Patients normally stayed in the
Locations of interest. For sensor-based feature assessment throughout the paper, shower, toilet, and sink are considered as bathroom; walls 1, 2, and 3 as wall; beds 1 to 4 inside the therapy room and beds 1 and 2 inside the resident room as beds.
Location | Sublocations |
Resident room | Bed, chair, shower, toilet |
Therapy room | Bed, resband, bike, endorphine, strip, table, small table, hallway, seats, wall, hallway doors, sink, bath |
For this baseline analysis, we included study participants who satisfied the following constraints: (1) patients with 4 hours or more of watch wear time data in at least 1 day within the first 3 days of admission (
The hours when the watch was not worn were excluded from the study; therefore, baseline hours may not be
We collected the demographic characteristics of patients such as age, race, gender, and ethnicity. We also translated the clinical coordinator’s assessments including usage of assistive devices and their type, measures of activity of daily living (ADL), pain (yes/no), and number of active diagnosis (more or less than 10). We investigated the significance of such characteristics in distinguishing the outcome (community vs hospital).
Sensor-based features are combination of 3 groups of parameters that are achieved by harnessing smartwatch and BLE beacons. The features are based on (1) activity recognition such as sitting time and standing time; (2) indoor localization, for example, time in bed, time in bathroom, or therapy room; and (3) row acceleration quantification, MAD (energy; see section Sensing At-Risk Population System Overview). By combining these attributes, we achieved features such as sitting time in bed or energy spent in walking or in bed.
To perform a fair comparison among patients with different watch wear time, we
We investigated the significance of sensor-based features with respect to the outcomes: hospital versus community. All measurements are at baseline, that is, the day that satisfies inclusion criteria from 9 am to 6 pm. We calculated “time spent in percentage,” “energy intensity (E),” and “energy spent in percentages,” as shown in equations 4, 5, and 6 in
To recap, for each individual,
We explored the capability of baseline sensor-based and demographic features to distinguish between subacute rehabilitation patients based on their outcomes (ie, re-admitted to hospital (H) vs staying in the community (C) either long-term care or home). Chi-squared tests were used to compare categorical demographic variables between outcome groups. We compared quantitative demographic variables and sensor-based metrics (physical activity derived from watch accelerometer and indoor localization inferred from BLE beacons RSSI) between groups using the Kruskal-Wallis test. Cohen
We investigated the capability of features at baseline to triage and predict patients who were re-admitted to the hospital or who stayed in community. We built random forest models (maximum depth=2, random state=40, and class_weight=balanced), with hospital patients as positive group. We used single or combination of features with highest statistical significance in distinguishing outcomes according to Kruskal-Wallis tests. Model generation and evaluating performance characteristics (3-fold cross-validation) including sensitivity, specificity, accuracy, and area under the curve (AUC) estimation were performed using Python Programming Language libraries Pandas (version 0.21.0) and Numpy (version 1.14.5), Scipy (version 1.0.0), and Scikit-learn (version 0.19.1) [
From 184 consented subjects, 30 were excluded because of not satisfying the analysis inclusion criteria. A total of 154 patients were included in this study in which 145 (94.2%) of subjects discharged home/community (C), and 9 (5.8%) re-admitted to hospital (H) at the end of their rehabilitation process.
Sociodemographic and clinical characteristics of the cohort of 154 patients.
Parameter | Community | Hospital | Community vs hospital ( |
|
Subjects, n (%) | 145 (94.2) | 9 (5.8) | —a | |
Age (years), mean (SD) | 82.16 (9.55) | 84.22 (13.87) | .24 | |
.56 | ||||
Female | 104 (71.7) | 4 (44.4) | ||
Male | 41 (28.3) | 5 (55.6) | ||
>.99 | ||||
Asian | 5 (3.4) | 0 (0.0) | ||
Black/African American | 14 (9.7) | 0 (0.0) | ||
Hispanic/Latino | 4 (2.7) | 0 (0.0) | ||
Native/Hawaiian Pacific Islander | 3 (2.1) | 0 (0.0) | ||
White | 119 (82.1) | 9 (100) | ||
.92 | ||||
No | 44 (31.7) | 1 (14.3) | ||
Yes | 95 (68.3) | 6 (85.7) | ||
>.99 | ||||
<10 | 22 (15.2) | 1 (11.1) | ||
≥10 | 123 (84.8) | 8 (88.9) | ||
.77 | ||||
Limited assistance | 65 (45.1) | 2 (22.2) | ||
Extensive assistance | 79 (54.9) | 7 (77.8) | ||
.96 | ||||
Limited assistance | 32 (22.2) | 1 (11.1) | ||
Extensive assistance | 112 (77.8) | 8 (88.9) | ||
.91 | ||||
Independent | 128 (88.9) | 7 (77.8) | ||
Supervision | 4 (2.8) | 0 (0.0) | ||
Limited assistance | 9 (6.2) | 1 (11.1) | ||
Extensive assistance | 3 (2.1) | 1 (11.1) | ||
.007 | ||||
Limited assistance | 50 (34.7) | 1 (11.1) | ||
Extensive assistance | 94 (65.3) | 7 (77.8) | ||
Total dependence | 0 (0.0) | 1 (11.1) | ||
.73 | ||||
Limited assistance | 73 (50.7) | 2 (22.2) | ||
Extensive assistance | 59 (41.0) | 5 (55.6) | ||
Activity did not occur | 12 (8.3) | 2 (22.2) | ||
.88 | ||||
Limited assistance | 73 (50.7) | 2 (22.2) | ||
Extensive assistance | 64 (44.4) | 6 (66.7) | ||
Activity occurred only once or twice | 2 (1.4) | 0 (0.0) | ||
Activity did not occur | 5 (3.5) | 1 (11.1) | ||
.85 | ||||
Supervision | 1 (0.7) | 0 (0.0) | ||
Limited assistance | 71 (49.3) | 2 (22.2) | ||
Extensive assistance | 72 (50.0) | 7 (77.8) | ||
.84 | ||||
Supervision | 2 (1.4) | 0 (0.0) | ||
Limited assistance | 71 (49.3) | 2 (22.2) | ||
Extensive assistance | 71 (49.3) | 7 (77.8) | ||
.61 | ||||
Supervision | 1 (0.7) | 0 (0.0) | ||
Limited assistance | 83 (57.6) | 2 (22.2) | ||
Extensive assistance | 60 (41.7) | 7 (77.8) | ||
.09 | ||||
Always continent | 117 (81.2) | 4 (44.4) | ||
Occasionally incontinent | 4 (2.8) | 0 (0.0) | ||
Frequently incontinent | 8 (5.6) | 2 (22.2) | ||
Always incontinent | 7 (4.8) | 3 (33.3) | ||
Not rated | 8 (5.6) | 0 (0.0) | ||
.08 | ||||
Always continent | 128 (88.9) | 5 (55.6) | ||
Occasionally incontinent | 3 (2.1) | 0 (0.0) | ||
Frequently incontinent | 7 (4.8) | 1 (11.1) | ||
Always incontinent | 6 (4.2) | 3 (33.3) | ||
.97 | ||||
Walker | 1 (0.7) | 0 (0.0) | ||
Wheelchair | 5 (4.0) | 1 (14.3) | ||
Walker and wheelchair | 123 (94.6) | 6 (85.7) | ||
Cane and wheelchair | 1 (0.7) | 0 (0.0) |
aNot applicable.
bADL: activity daily living.
cParameters with
Amongst sensory-based features shown in
Sensor-based (activity and indoor localization) features: assessment according to outcomes.
Feature | Community, mean (SD) | Hospital, mean (SD) | Effect sizea | Frequency (n) | ||||
Community | Hospital | |||||||
Activeb | 2.37 (3.84) | 1.00 (1.29) | .001 | 1.24 | 145 | 9 | ||
Walking | 2.37 (3.84) | 1.00 (1.29) | .08 | 0.50 | 145 | 9 | ||
Standingb | 59.70 (8.70) | 57.92 (6.39) | .002 | 1.24 | 145 | 9 | ||
Sittingb | 17.83 (9.69) | 13.33 (8.90) | .02 | 0.86 | 145 | 9 | ||
Laying downb | 20.10 (6.43) | 27.73 (9.94) | .04 | 0.54 | 145 | 9 | ||
Total energyb | 52.61 (18.23) | 35.85 (16.53) | .003 | 0.87 | 145 | 9 | ||
Active | 11.94 (18.27) | 6.05 (8.02) | .30 | 0.42 | 145 | 9 | ||
Walking | 450.47 (253.08) | 366.45 (218.66) | .44 | 0.34 | 145 | 9 | ||
Standing | 85.93 (26.92) | 82.27 (36.12) | .32 | 0.11 | 145 | 9 | ||
Sitting | 184.33 (97.58) | 156.19 (104.74) | .31 | 0.28 | 145 | 9 | ||
Laying downb | 26.23 (8.68) | 19.54 (7.35) | .02 | 0.418 | 145 | 9 | ||
Energy therapy room | 70.75 (43.11) | 68.49 (63.56) | .36 | 0.04 | 145 | 9 | ||
Bathroomb | 74.84 (49.02) | 62.35 (83.54) | .02 | 0.17 | 114 | 8 | ||
Strip | 57.84 (42.33) | 13.03 (8.30) | .06 | 1.43 | 88 | 2 | ||
Bed | 60.22 (40.27) | 39.09 (7.15) | .27 | 0.72 | 97 | 4 | ||
Resband | 61.06 (43.10) | 75.73 (85.49) | .57 | 0.20 | 100 | 6 | ||
Bike | 91.80 (76.82) | 120.58 (38.41) | .31 | 0.43 | 36 | 2 | ||
Scifit | 98.39 (55.04) | 0.0 (0.0) | —c | — | 14 | 0 | ||
Endor | 41.38 (6.74) | 0.0 (0.0) | — | — | 3 | 0 | ||
Midstrip | 56.46 (48.92) | 65.46 (24.53) | .38 | 0.22 | 45 | 3 | ||
Small table | 61.07 (40.37) | 148.47 (138.78) | .53 | 0.71 | 57 | 3 | ||
Table | 93.49 (66.75) | 0.0 (0.0) | — | — | 56 | 0 | ||
Hallway seats | 42.58 (43.13) | 32.52 (7.89) | .87 | 0.32 | 43 | 3 | ||
Stairs | 133.48 (128.07) | 0.0 (0.0) | — | — | 8 | 0 | ||
Wall | 57.07 (28.49) | 25.61 (0.0) | .17 | — | 73 | 1 | ||
Energy resident roomb | 43.32 (17.44) | 26.99 (6.05) | <.001 | 1.25 | 145 | 9 | ||
Bedb | 43.93 (19.01) | 25.76 (4.37) | <.001 | 1.23 | 144 | 9 | ||
Bathroomb | 55.89 (27.95) | 32.50 (9.30) | .004 | 1.18 | 141 | 9 | ||
Chair | 42.45 (20.61) | 0.0 (0.0) | — | — | 5 | 0 | ||
Activeb | 12.92 (6.52) | 6.94 (4.01) | .001 | 1.10 | 145 | 9 | ||
Walking | 0.35 (0.51) | 0.15 (0.27) | .09 | 0.44 | 145 | 9 | ||
Standingb | 44.22 (7.94) | 32.68 (7.30) | <.001 | 1.51 | 145 | 9 | ||
Sittingb | 8.60 (8.36) | 6.16 (7.36) | .04 | 0.31 | 145 | 9 | ||
Laying downb | 46.83 (9.83) | 60.99 (11.11) | <.001 | 1.35 | 145 | 9 | ||
Bathroom | 0.03 (0.04) | 0.06 (0.08) | .16 | 0.27 | 114 | 8 | ||
Strip | 0.01 (0.03) | 0.005 (0.002) | .62 | 0.48 | 88 | 2 | ||
Bed | 0.62 (0.19) | 0.55 (0.23) | .64 | 0.43 | 97 | 4 | ||
Resbandb | 0.02 (0.02) | 0.05 (0.03) | .03 | 0.74 | 100 | 6 | ||
Bike | 0.03 (0.03) | 0.01 (0.002) | .51 | 0.80 | 36 | 2 | ||
Scifit | 0.03 (0.02) | 0.0 (0.0) | — | — | 14 | 0 | ||
Endor | 0.009 (0.01) | 0.0 (0.0) | — | — | 3 | 0 | ||
Midstrip | 0.02 (0.02) | 0.02 (0.02) | .31 | 0.49 | 45 | 3 | ||
Small tableb | 0.02 (0.03) | 0.04 (0.02) | .04 | 0.50 | 57 | 3 | ||
Table | 0.06 (0.05) | 0.0 (0.0) | — | — | 56 | 0 | ||
Hallway seats | 0.006 (0.004) | 0.01 (0.16) | .64 | 0.78 | 43 | 3 | ||
Stairs | 0.02 (0.04) | 0.0 (0.0) | — | — | 8 | 0 | ||
Wall | 0.01 (0.02) | 0.01 (0.0) | .98 | — | 73 | 1 | ||
Bed | 0.62 (0.19) | 0.55 (0.23) | .16 | 0.12 | 144 | 9 | ||
Bathroom | 0.21 (0.17) | 0.25 (0.20) | .92 | 0.52 | 141 | 9 | ||
Chair | 0.007 (0.03) | 0.0 (0.0) | — | — | 5 | 0 |
aEffect sizes have been calculated as Cohen
bParameters with
cNot applicable (the
Kernel density estimation (KDE) distributions are shown in
Energy intensity distribution.
Gauging energy intensity in community versus hospital.
Distribution of patients spending energy in therapy room compared with resident room. X-axis indicates the ratio of energy in therapy to resident room.
Time and energy intensity details of therapy room.
Average time spent and energy intensity at each therapy location stratified by groups are shown in
Frequency of therapy room location/facility usage by group.
Location/facility | Frequency of facility usage | |
Community, n (%) | Hospital, n (%) | |
Scifit | 14 (9.6) | 0 (0.0) |
Endor | 3 (2.1) | 0 (0.0) |
Table | 56 (38.6) | 0 (0.0) |
Stairs | 8 (5.5) | 0 (0.0) |
Bed | 118 (81.4) | 7 (77.8) |
Bike | 36 (24.8) | 2 (22.2) |
Midstrip | 45 (31.0) | 3 (33.3) |
Small table | 57 (39.3) | 3 (33.3) |
Bathrooma | 114 (78.6) | 9 (100.0) |
Resband | 100 (69.0) | 7 (77.8) |
Hallway seat | 43 (29.7) | 3 (33.3) |
Strip | 88 (60.7) | 3 (33.3) |
aParameters with
Energy percentage feature, as mentioned in
According to
Random forest models were built based on the most statistically significant features. In reviewing
Correlations among sensor-based features. Asterisk indicates parameters with
Predictive models: 3-fold cross-validation (community, n=48; hospital, n=3).
Features | Sensitivity, mean (SD)a | Specificity, mean (SD)a | Accuracy, mean (SD)a | AUCb, mean (SD) |
Standing time (%) | 22.2 (31.4) | 74.4 (15.3) | 71.4 (12.9) | 0.62 (0.06) |
Standing time (%), laying down time (%) | 11.1 (15.7) | 91.0 (0.9) | 86.4 (1.5) | 0.70 (0.10) |
Standing time (%), laying down time (%), resident room energy intensity (%) | 44.4 (41.6) | 87.6 (4.3) | 85.1 (5.5) | 0.85 (0.09) |
Resident room energy intensity | 77.7 (15.7) | 74.5 (8.5) | 74.7 (7.3) | 0.84 (0.10) |
aMean (SD) reported for the validation datasets based on a 3-fold cross-validation. Mean and SD are calculated across all 3 folds.
bAUC: area under the curve.
To our knowledge, this is the first study that has combined indoor localization and accelerometer-based physical activity recognition to assess older patients. A subset of indoor location and physical activity features were found to be highly correlated with the outcomes (community vs hospital re-admission) at baseline. In this section, we discuss the significant highlights of the result.
Interestingly, walking, a known distinctive parameter in assessing physical functional performance in certain older populations [
One interesting aspect of this study was to investigate the activity while a patient is with a physical therapist versus activity during the other hours of the day. It did not appear that a clear distinction could be made between different outcome groups based on therapy room energy intensity. This could be because all patients during therapy sessions are engaged by the therapist in similar physical activities following set protocols. However, the energy intensity of resident room was distinctive within outcome groups.
To assess the value of indoor localization in activity tracking, it would be best to highlight some of the scenarios: according to
Both group energy intensities at bed and bath were less than 60 per min. In the study by Razjouyan et al [
None of the patients in hospital outcome group used therapy room toilet/bathroom. It is likely that those patients were not capable enough to perform such exercises or even not advised by clinicians/nurses to do so to prevent injury. Either way, the lack of performing an activity, in this case, information extracted from indoor localization data, could be an early indication of which group a patient belongs to; it could also potentially be used to identify adverse outcomes and proactively address to prevent a negative outcome.
Considering only the prediction results, we can infer that location data add value to our system. It is apparent that energy intensity in resident room is the most decisive feature in predicting the outcome.
Activity classification can best be obtained using a series of motion sensors placed on various parts of the body. Thus, a wide range of activities can be captured as most body motions are detected. However, to simplify the activity detection, using single motion sensors is quite popular. Placing an accelerometer on the hip has been one of the most popular methods because it captures almost all human motions; however, it underestimates the arm ergometry, as it cannot fully extract the arm movements [
Patients’ compliance with wearing a smartwatch was the main challenge of this study, and we expect it to be a generic obstacle in similar studies that aim to harness wearable technology for patients. Moreover, if the target population is less familiar with new forms of technology such as wearable devices, the compliance issue might become even more crucial. In this study, we recruited 184 patients, of which 30 patients were excluded for not satisfying the analysis inclusion criteria (watch wear time constraint). Our baseline analyses revealed that 50% of patients removed their watches before the study coordinator collects them at the end of the 8 hours.
Dealing with medical datasets is rather challenging in that the datasets predominantly consist of normal cases in addition to minority abnormal instances that deem to be more interesting [
Next step would be the longitudinal analysis on the same study cohort over the 21-day period they were admitted to the same rehabilitation center. This will allow us to track the trends in sensor feature values and investigate if their changes mimic the daily assessment change performed by clinicians. The result can allow development of models of early frailty detection or producing intervention alerts.
Despite the evolution of eHealth and mobile health (mHealth) and the emerging role of wearable and mobile technology in new platforms of health care, there are anecdotal claims that wearable technology may not precisely quantify patients’ health [
activity of daily living
area under the curve
bluetooth low-energy sensors
community
hospital
kernel density estimation
mean absolute deviation
mobile health
Received Signal Strength Indicator
Sensing At-Risk Population
signal magnitude
The authors would like to express their gratitude to the researchers cited here and apologize to those whose work, because of page restrictions, could not be mentioned. This research was mainly funded by an National Institutes of Health (NIH) grant, DHHS Agency for Health Care Research and Quality: RO1 HS024394.
The SARP system is protected by a patent (US Patent Application 15/736,744) [