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 https://mhealth.jmir.org/, as well as this copyright and license information must be included.
Diabetes mellitus is a metabolic disorder that affects hundreds of millions of people worldwide and causes several million deaths every year. Such a dramatic scenario puts some pressure on administrations, care services, and the scientific community to seek novel solutions that may help control and deal effectively with this condition and its consequences.
This study aims to review the literature on the use of modern mobile and wearable technology for monitoring parameters that condition the development or evolution of diabetes mellitus.
A systematic review of articles published between January 2010 and July 2020 was performed according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Manuscripts were identified through searching the databases Web of Science, Scopus, and PubMed as well as through hand searching. Manuscripts were included if they involved the measurement of diabetes-related parameters such as blood glucose level, performed physical activity, or feet condition via wearable or mobile devices. The quality of the included studies was assessed using the Newcastle-Ottawa Scale.
The search yielded 1981 articles. A total of 26 publications met the eligibility criteria and were included in the review. Studies predominantly used wearable devices to monitor diabetes-related parameters. The accelerometer was by far the most used sensor, followed by the glucose monitor and heart rate monitor. Most studies applied some type of processing to the collected data, mainly consisting of statistical analysis or machine learning for activity recognition, finding associations among health outcomes, and diagnosing conditions related to diabetes. Few studies have focused on type 2 diabetes, even when this is the most prevalent type and the only preventable one. None of the studies focused on common diabetes complications. Clinical trials were fairly limited or nonexistent in most of the studies, with a common lack of detail about cohorts and case selection, comparability, and outcomes. Explicit endorsement by ethics committees or review boards was missing in most studies. Privacy or security issues were seldom addressed, and even if they were addressed, they were addressed at a rather insufficient level.
The use of mobile and wearable devices for the monitoring of diabetes-related parameters shows early promise. Its development can benefit patients with diabetes, health care professionals, and researchers. However, this field is still in its early stages. Future work must pay special attention to
Diabetes mellitus (DM) is a metabolic disorder primarily characterized by high blood glucose levels (GLs). People with DM are more likely to have other major health problems. Therefore, the chances for them to require special medical attention increases as the patients’ quality of life decreases [
DM is normally categorized into 3 groups: type 1 diabetes (T1D), type 2 diabetes (T2D), and gestational diabetes (GD). T1D affects between 5% and 10% of patients with DM and most often occurs in young people [
Irrespective of the type of DM, low or too high GLs in the blood for long periods can induce several complications in patients, leading to premature death in worst cases. Critical hypoglycemia can cause comatose states and induce seizures. Chronic hyperglycemia can cause vascular damage; affect the heart, kidneys, eyes, and nerves; and lead to other serious complications [
Extensive tests have proven that appropriate metabolic control in all DM types can delay the onset and evolution of its complications [
The health community uses the term
The widespread adoption of wearable and mobile technologies around the world offers new opportunities for researchers to provide medical care and information in a portable and affordable way [
Several sensors are readily available on regular smartphones, such as the accelerometer (ACC), GPS, camera, ambient light, and microphone, among others. The data collected by these sensors can be used to determine the user context [
Mobile and wearable devices generate an enormous amount of data, and their ability to process these data is beyond human skills [
Although several manuscripts have been published on the use of mobile and wearable technology for monitoring parameters that condition the development and evolution of DM, hereafter monitoring of DM-related parameters, this subject has not been systematically reviewed to the best of the authors’ knowledge. Therefore, the goal of this study is to review the published literature on the use of mobile and wearable technology for the monitoring of DM-related parameters. Three specific research questions are defined to guide this study: (1) How are DM-related parameters studied using mobile and wearable technology? (2) How are the devices and sensors used to monitor DM-related parameters? and (3) What processing is given to the collected mobile and wearable data?
The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines [
Studies were identified by searching electronic databases and scanning publications from a reference list of authors. The search was performed using 3 reference web-based citation databases: Web of Science (WoS), Scopus, and PubMed. The last search was performed on July 28, 2020. The queries used for the database search are listed in
TITLE-ABS-KEY(diabetes AND ((sensor OR sensing OR accelerometer OR gyroscope OR “proximity sensor” OR “light sensor” OR pedometer OR barometer OR gps OR camera OR “humidity sensor” OR magnetometer OR compass OR microphone OR mic OR nfc OR Bluetooth OR Wi-Fi OR fingerprint OR sms OR “phone call” OR “call log”) AND ((wearable OR “smart watch” OR smartwatch OR “fitness band” OR “flexible band” OR wristband OR “smart insole” OR bracelet) OR (mobile OR smartphone OR “smart phone” OR cellphone OR “cell phone” OR mobilephone OR “mobile phone”))))
(ts = (diabetes AND ((sensor$ OR sensing OR accelerometer$ OR gyroscope$ OR “proximity sensor$” OR “light sensor$” OR pedometer$ OR barometer$ OR gps OR camera$ OR “humidity sensor$” OR magnetometer$ OR compass OR microphone$ OR mic OR nfc OR Bluetooth OR Wi-Fi OR fingerprint OR sms OR “phone call$” OR “phone$ call” OR “call log$”) AND ( (wearable$ OR “smart watch*” OR smartwatch* OR “fitness band$” OR “flexible band$” OR wristband$ OR “smart insole$” OR bracelet$) OR (mobile$ OR smartphone$ OR “smart phone$” OR cellphone$ OR “cell phone$” OR mobilephone$ OR “mobile phone$”)))))
((diabetes AND ((sensor OR sensing OR accelerometer OR gyroscope OR “proximity sensor” OR “light sensor” OR pedometer OR barometer OR gps OR camera OR “humidity sensor” OR magnetometer OR compass OR microphone OR mic OR nfc OR Bluetooth OR Wi-Fi OR fingerprint OR sms OR “phone call” OR “call log”) AND ((wearable OR “smart watch” OR smartwatch OR “fitness band” OR “flexible band” OR wristband OR “smart insole” OR bracelet) OR (mobile OR smartphone OR “smart phone” OR cellphone OR “cell phone” OR mobilephone OR “mobile phone”))))[TitleAbstract])
Manuscripts resulting from the database search (WoS, Scopus, and PubMed) and the hand search (ResearchGate) were downloaded and merged, and duplicates were removed. A 2-stage process was applied for the analysis of the manuscripts. In the first stage, 2 of the authors (CR and OB) screened the manuscripts based on the eligibility criteria, using title and abstract. In the second stage, the same authors fully reviewed the manuscripts resulting from the first stage and selected those meeting the eligibility criteria. During both the initial screening and full-text screening for eligibility, the 2 authors processed all the papers independently and discussed their observations before making a definitive decision. In the event of disagreement, a third reviewer (CV) was assigned, and a final decision was made based on the majority vote.
Studies were included if related to DM and if data were collected using sensors from wearable devices or smartphones and transmitted wirelessly. Hence, studies that were not related to DM were directly excluded. Those related to DM but where data were not collected using wearables or smartphones or where data were not transmitted wirelessly were also excluded. The inclusion criteria for both disease and technology are explained below.
According to the considered disease, a manuscript was included if it focused exclusively on DM, meaning that the main clinical topic of the study was DM; it was related to DM complications, that is, the main clinical topic of the study was a complication (or several) resulting from DM; it studied DM in combination with another disease, in other words, the main clinical topic of the study was the relation between DM and another condition such as cardiovascular disease; and patients with DM were used as a case study, namely, a clinical solution for multiple conditions was proposed, but the evaluation was performed on patients with DM.
According to the technology, the definition of
Studies meeting the disease and technology inclusion criteria were also excluded if they were oriented to the intervention without an actual monitoring of DM-related parameters; they were technology centered, namely, the solution was not applied to a clinical case study; the proposed solution was not tested; similar studies under a different title were already considered; and the manuscript was not available.
Only English manuscripts in engineering and computer science areas, of article or proceedings type, and published between January 2010 and July 2020 (both inclusive) were included.
The 9-point NOS was used to score the included manuscripts. Nonrandomized studies, including case-control and cohort studies, were independently scored by 2 authors (CR and JRR). Disagreements were discussed and resolved.
The query used in the Scopus, WoS, and PubMed databases resulted in 960, 627, and 323 references, respectively. A total of 71 manuscripts were identified through other sources. After applying the PRISMA guidelines (
Search and selection of manuscripts using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.
The process used to achieve the 26 publications included in this review is as follows. A total of 590 original studies were obtained after merging the results from the databases and eliminating duplicates. Up to 79.5% (469/590) of the manuscripts were excluded after screening the title and abstract. Of the 469 manuscripts, 243 (51.8%) were not focused on DM, with a majority of papers where the term
The 121 manuscripts resulting from the previous screening were fully analyzed. A total of 78.5% (95/121) of the manuscripts were excluded following the same criteria mentioned above: 5% (5/95) studies were not focused on DM; in 22% (21/95) of the studies, no sensing was performed; in 27% (26/95) of the studies, the sensing device was not considered mobile or wearable; in 3% (3/95) of the studies, the data were not sent wirelessly; 5% (5/95) of the studies were centered on technology; 25% (24/95) of the studies were not properly tested, that is, some studies did not show enough scientific maturity in their tests and others did not involve patients with DM; 6% (6/95) of the manuscripts were not available; 4% (4/95) of the manuscripts were reviews or surveys; and finally, 1% (1/95) of the manuscript was a magazine. As a result, 21.5% (26/121) of the manuscripts were selected to be reviewed in this study.
Of the 26 selected studies, 22 (85%) studies were assessed in terms of quality (
Some general statistics and quality indicators were obtained from the selected studies. Overall, 62% (16/26) manuscripts were published in journals, whereas (10/26) manuscripts were included in conference proceedings. Moreover, 23% (6/26) of the articles were published in journals ranked in quartile 1, 4% (1/26) in quartile 2, 8% (2/26) in quartile 3, and 4% (1/26) in quartile 4% (1/26) according to the Journal Citation Reports (WoS). In addition, 19% (5/26) of the articles were published in journals ranked in quartile 1, 23% (6/26) in quartile 2, 4% (1/26) in quartile 3, and 4% (1/26) in quartile 4 according to the SCImago Journal Rank (Scopus). It was observed that cross-national research teams were present on many occasions. These teams had a European member 14 times, had a member from the Unites States 11 times, and had an Asian member 8 times. The majority of the studies (21/26, 81%) were published between 2017 and 2019, as shown in
Close to half of the manuscripts (12/26, 46%) did not focus on a specific type of DM, almost a third of the studies (8/26, 31%) were related to T1D, 5 were associated with T2D (5/26, 19%), and 1 study dealt with GD (1/26, 4%). The majority of the studies (25/26, 96%) were some type of trial or longitudinal study, with sample sizes ranging from 1 to 100 participants with an approximate duration of up to 140 days. Patients with DM were involved in approximately two-third of these trials (17/26, 65%). More than half of the studies used only wearables to carry out their objectives (15/26, 58%), approximately one-fifth of the studies used only smartphones (5/26, 19%), and 6 studies used both wearables and smartphones in combination (6/26, 23%). The most common sensor used in the studies was the ACC (19/26, 73%).
In the following sections, we report the findings extracted from the analysis of all the reviewed studies. The dimensions for characterization are medical classification, DM type, research goals, devices, sensors, data processing,
More than half of the selected studies, namely, 62% (16/26) of manuscripts were exclusively focused on DM [
According to the DM type, 4% (1/26) of studies were related to GD [
As for the research goals of the selected studies, 15% (4/26) of manuscripts aimed to detect physical activity patterns relevant to patients with DM, such as walking, running, or sleeping [
Overall, 23% (6/26) of manuscripts [
A total of 38% (10/26) of studies were aimed at finding an association between variables or diseases related to DM [
Finally, 23% (6/26) of manuscripts had the principal goal of simply measuring data relevant to DM [
All details about medical classification, DM type, and research goals of the reviewed manuscripts are provided in
Summary of medical topics, diabetes types, and research goals, ordered by the year of publication.
Manuscript | Medical classification | Diabetes type | Research goals |
Najafi et al (2010) [ |
Patients with DMa used as case study | Not specified | Find association between posture and balance control among patients with different DM complications |
Grewal et al (2013) [ |
DM complication: DPNb and DPN with diabetic foot | Not specified | Find association between DPN and DFUc for gait |
Luštrek et al (2014) [ |
Focused on DM | Not specified | Activity recognition of walking, running, cycling, lying, sitting, and standing |
Luštrek et al (2015) [ |
Focused on DM | Not specified | Activity recognition of sleeping, home chores, home leisure, eating, and exercising |
Cvetković et al (2016) [ |
Focused on DM | Not specified | Activity recognition of working, eating, exercising, and home activities |
Calbimonte et al (2017) [ |
Focused on DM | T1Dd | Predict glycemic events |
Fraiwan et al (2017) [ |
DM complication: diabetic foot | Not specified | Diagnose development of DFU |
McLean et al (2017) [ |
Patients with DM used as case study | GDe | Measure physical proximity, physical activity, and magnetic field strength |
Razjouyan et al (2017) [ |
DM complication: diabetic foot | Not specified | Find association between physiological stress response and healing speed among outpatients with active DFU |
Reddy et al (2017) [ |
Focused on DM | T2Df | Diagnose individual’s diabetic status |
Turksoy et al (2017) [ |
Focused on DM | T1D | Find association between biometric variables and changes in glucose concentration |
Bartolic et al (2018) [ |
Focused on DM | Not specified | Measure GLg, insulin dosage, physical activity, daily movement, and sleep duration and quality |
Faccioli et al (2018) [ |
Focused on DM | T1D | Find association between glucose prediction models’ performance |
Groat et al (2018) [ |
Focused on DM | T1D | Find association between exercise behavior data with the rate of change in GL |
McMillan et al (2018) [ |
Focused on DM | T2D | Measure combined GL data, physical activity, and sedentary behavior |
Merickel et al (2018) [ |
Focused on DM | T1D | Find association between pattern of glucose and at-risk pattern of vehicle acceleration behavior |
Nguyen Gia et al (2019) [ |
DM in conjunction with other diseases: DM+cardiovascular disease | Not specified | Activity recognition of fall detection and remote health monitoring |
Rescio et al (2019) [ |
DM complication: diabetic foot | Not specified | Measure temperature and pressure of the plantar foot |
Sarda et al (2019) [ |
DM in conjunction with other diseases: DM+depression | Not specified | Find association between smartphone-sensing parameters and symptoms of depression |
Ramazi et al (2019) [ |
Focused on DM | T2D | Predict the progression of T2D |
Garcia et al (2019) [ |
Focused on DM | Not specified | Diagnose DM from facial images |
Sevil et al (2019) [ |
DM in conjunction with other diseases: DM+acute psychological stress | T1D | Find the association between acute psychological stress and the glucose dynamics |
Zherebtsov et al (2019) [ |
Patients with DM used as case study | T2D | Measure the changes in the microcirculatory blood flow of healthy patients and patients with T2D |
Rodriguez-Rodriguez et al (2019) [ |
Focused on DM | T1D | Predict blood GL for T1D with limited computational and storage capabilities using only CGMh data |
Sanz et al (2019) [ |
Focused on DM | T1D | Find the association between different signals provided by 3 different wearables devices and the accuracy of a CGM device during aerobic exercises |
Whelan et al (2019) [ |
Focused on DM | T2D | Measure the use, feasibility, and acceptability of behavioral and physiological self-monitoring technologies in individuals at risk of developing T2D |
aDM: diabetes mellitus.
bDPN: diabetic peripheral neuropathy.
cDFU: diabetic foot ulcer.
dT1D: type 1 diabetes.
eGD: gestational diabetes.
fT2D: type 2 diabetes.
gGL: glucose level.
hCGM: continuous glucose monitor.
A total of 58% (15/26) of studies used wearable devices for monitoring tasks [
Smartphones were used in 19% (5/26) of studies for sensing purposes: a Samsung Galaxy S6 Edge Plus (Samsung) [
A total of 30 different types of sensors were used to acquire data from the reviewed studies. The ACC stands out as the sensor most widely used across studies, namely, in 73% (19/26) of studies [
All details about the devices and sensors used in the reviewed manuscripts are provided in
Summary of devices used, ordered by the year of publication.
Studies and devices | Devices, sensors, measurement | Purpose |
Najafi et al (2010) [ |
Wearable: hip-worn strap ( Triaxial ACCb (quaternions) Triaxial gyroscope (quaternions) Triaxial magnetometer (quaternions) Pressure sensor (area of sway) |
Recognize the motion of ankle and hip joints in 3 dimensions |
Grewal et al (2013) [ |
Wearable: lower limb band ( ACC (acceleration) Gyroscope (angular velocity) |
Gait detection |
Luštrek et al (2014) [ |
Smartphone ( ACC (acceleration) ACC (acceleration) HRMc (HRd) |
Smartphone location detection; activity recognition: walking, running, cycling, lying, sitting, and standing; and energy expenditure estimation |
Luštrek et al (2015) [ |
Smartphone ( ACC (acceleration, location, HR, and RRe) Microphone (sound) GPS (location and velocity) Wi-Fi (location) ACC (acceleration) ECGf (HR and RR) |
Activity recognition: sleep, exercise, work, transport, eating, home, and outdoor |
Cvetković et al (2016) [ |
Smartphone ( ACC (acceleration) Microphone (sound) GPS (location and velocity) Wi-Fi (location) ACC (acceleration) ECG (HR and RR) |
Activity recognition: sleep, exercise, work, transport, eating, home, and out |
Calbimonte et al (2017) [ |
Wearable: chest strap ( ACC (acceleration) ECG (HBg fiducial points location, STh segment shape, QTci interval, HR, and RR) |
Generate 2 semantic models: physiological and energy expenditure for classifying hypoglycemic events |
Fraiwan et al (2017) [ |
Smartphone ( Infrared sensor (thermal images) Camera (standard image) |
Recognize change of temperature on the feet |
McLean et al (2017) [ |
Smartphone ( ACCs (acceleration) GPS (location) Wi-Fi (location) Camera (photo) Magnetometer (magnetic field strength) Bluetooth (physical proximity) |
Quantify physical proximity, sedentary behavior, vehicle use, and location |
Razjouyan et al (2017) [ |
Wearable: chest strap ( ACC (acceleration) ECG (HR, RR, and core body temperature) |
Detection of physiological stress of the patient |
Reddy et al (2017) [ |
Smartphone ( Camera and flash (PPGj) Pulse oximeter (PPG) |
Discriminate between diabetic and healthy individuals |
Turksoy et al (2017) [ |
Wearable: armband ( ACC (acceleration) Thermometer (skin temperature and near-body temperature) Galvanometer (galvanic skin response) Heat flux (rate of heat dissipating from the body) GMk (GLl) GM (GL) ACC (acceleration) ECG (HR) HRM (HR) Expired gases (O2 and CO2) |
Find a correlation between biometric changes and glucose concentrations during exercise |
Bartolic et al (2018) [ |
Smartphone ( App (insulin doses) ACC (acceleration) HRM (HR) GM (GL) |
Quantify physical activity, daily movement, sleep duration and quality, calorie consumption, insulin dosages, and continuous GL |
Faccioli et al (2018) [ |
Smartphone ( App (carbohydrates count) ACC (acceleration) GM (continuous GL) |
Quantify step count, continuous GL, and carbohydrate intake |
Groat et al (2018) [ |
Smartphone ( App (exercise behavior) HRM (HR) GM (continuous GL) |
Quantify exercise behavior measured via a wristband and an app to compare with the rate of change in GL recorded by a CGM |
McMillan et al (2018) [ |
Wearable: thigh-worn ( ACC (acceleration) Inclinometer (acceleration) GM (continuous GL) |
Quantify step count, cadence and postural transitions and energy expenditure estimates, and continuous GL |
Merickel et al (2018) [ |
Wearable: wristwatch ( ACC (acceleration) HRM (HR) GM (continuous GL) Camera (video) GPS (vehicle acceleration and speed) OBDm sensor (vehicle acceleration and speed) |
Compare the driving behavior from drivers with and without T1Dn |
Nguyen Gia et al (2019) [ |
Wearable: chest strap ( ACC (acceleration) Gyroscope (angular velocity) Magnetometer (magnetic field) ECG (QTo intervals and HR) GM (continuous GL) Thermometer (body temperature) Ambient sensor (room temperature, humidity, and air quality) |
Monitor DMp and ECG, and report abnormalities: fall, very low or high GL, and abnormal HR in real time without interfering with the patient’s daily activities |
Rescio et al (2019) [ |
Wearable: smart insole ( Infrared thermometer (plantar temperature) Pressure sensor (pressure) |
Monitor temperature and pressure of the plantar foot |
Sarda et al (2019) [ |
Smartphone ( ACC (acceleration) Call logs (communication) GPS (location) Ambient light sensor (ambient light) |
Activity recognition: mobility, sleep, and social interaction |
Ramazi et al (2019) [ |
Wearable: CGM ( GM (continuous GL) ACC (acceleration) |
Quantify GL, traveled steps, and physical activity: sitting, standing, and lying |
Garcia et al (2019) [ |
Smartphone ( Camera (standard image) |
Capture facial images |
Sevil et al (2019) [ |
Wearable: wristband ( ACC (acceleration) PPG (blood volume pulse) Galvanometer (galvanic skin response) Infrared thermopile (skin temperature) GM (continuous GL) |
Estimate acute psychological stress effect index and GL |
Zherebtsov et al (2019) [ |
Wearable: wristband ( Laser Doppler flowmetry (Doppler shift) |
Quantify changes in the microcirculatory blood flow in tissues |
Rodriguez-Rodriguez et al (2019) [ |
Wearable: FGM ( GM (continuous GL) |
Quantify GL for the creation of a database for further processing by the prediction models |
Sanz et al (2019) [ |
Wearable: wristband ( ACC (acceleration) HRM (HR) Altimeter (altitude) HRM (HR) Skin temperature (skin temperature) Galvanometer (galvanic skin response) ACC (acceleration) HRM (HR) GM (continuous GL) GM (GL) |
Quantify number of steps walked, number of floors of stairs climbed, exercise intensity, calories burned, and skin electrodermal activity |
Whelan et al (2019) [ |
Wearable: wristband ( ACC (acceleration) Altimeter (altitude) HRM (HR) ACC (acceleration) GM (continuous GL) |
Quantify number of steps walked, distance traveled, HR, calories expended, flights of stairs climbed, and GL |
aText in italic represents model and company of each devices in that order. In the cases of no specification on the correspondent manuscript “Model not specified” it is stated.
bACC: accelerometer.
cHRM: heart rate monitor.
dHR: heart rate.
eRR: respiration rate.
fECG: electrocardiogram.
gHB: heartbeat.
hST: electrocardiogram measurement ST interval.
iQTc: corrected electrocardiogram measurement QT interval.
jPPG: photoplethysmogram.
kGM: glucose monitor.
lGL: glucose level.
mOBD: on-board diagnostics device.
nT1D: type 1 diabetes.
oQT: electrocardiogram measurement QT interval.
pDM: diabetes mellitus.
Except for 12% (3/26) of studies [
The studies without specific data processing were rather oriented to simply collect data. ML was primarily used in the reviewed investigations for activity recognition and diagnosis tasks. Statistical analyses were predominantly aimed at finding associations between behavioral and physiological variables with DM conditions.
Some authors created their own algorithm to attain the study objective. Cvetković et al [
Some studies used additional data, not collected passively from mobile or wearable devices, to achieve their goal. One example is the study by Razjouyan et al [
All details about data processing for the reviewed manuscripts are provided in
Summary of processing techniques, privacy, and security ordered by the year of publication.
Manuscript | Statistical methods | Machine learning methods | Privacy | Security |
Najafi et al (2010) [ |
Pearson correlation coefficient, paired |
None | Study approved by the local ethics committee | Not described |
Grewal et al (2013) [ |
Statistical fluctuation, SD, and coefficient of variation | None | Study approved by the local ethics committee. All participants signed an informed consent form before participating in the study | Not described |
Luštrek et al (2014) [ |
None | RFa and support vector regression algorithm | Not described | Not described |
Luštrek et al (2015) [ |
None | Spectral centroid, zerocrossing, mel frequency cepstral coefficient, linear predictive coding, and method of moments values of the sound signals; clustering of Wi-Fi and GPS data; new algorithm of acceleration data; naive bayes, logistic regression, SVMb, RF, RIPPERc, adaboost, and bagging for activity recognition tasks; and event calculus for interpreting recognized activities | Sound from the smartphone microphone is recorded in fractions of 100 ms per second | Not described |
Cvetković et al (2016) [ |
None | Spectral centroid, zerocrossing, mel frequency cepstral coefficient, linear predictive coding, and method of moments values of the sound signals; clustering of Wi-Fi and GPS data; new algorithm of acceleration data; 5 new algorithms for activity recognition task; and symbolic rules to refine confused predictions | Sound from the smartphone microphone is recorded in fractions of 100 ms per second | Not described |
Calbimonte et al (2017) [ |
None | Normalized least mean squares, ontology, and RDFd stream processing engine (CQELSe continuous evaluation) | Not described | Not described |
Fraiwan et al (2017) [ |
None | Otsu thresholding technique and point-to-point mean difference technique | Authors referred to “Ethics approval and consent to participate” as “Not applicable” | Not described |
McLean et al (2017) [ |
None | None | Not described | Data are stored on the phone and uploaded in an encrypted form |
Razjouyan et al (2017) [ |
Analysis of variance, root mean square of successive R-wave to R-wave intervals, power spectrum density of time series representing R-wave to-R-wave intervals, receiver operating characteristic, and area under the curve | None | Not described | Not described |
Reddy et al (2017) [ |
None | SVM, artificial neural network, and classification and regression trees | Not described | Not described |
Turksoy et al (2017) [ |
Partial least squares, regression, and variable importance in projection | None | Not described | Not described |
Bartolic et al (2018) [ |
Trading view and minimum and maximum values | None | Not described | Not described |
Faccioli et al (2018) [ |
Black-box linear model, prediction error method, coefficient of determination, and RMSEf | None | The trial study and all experimental procedures were approved by the institution’s ethical review board | Not described |
Groat et al (2018) [ |
Cohen κ | None | Study approved by the local institutional review board | Not described |
McMillan et al (2018) [ |
None | None | Not described | Not described |
Merickel et al (2018) [ |
Their own procedures and β regression model | None | All subjects gave informed consent to study participation according to the University of Nebraska Medical Center’s institutional review board’s protocols | Not described |
Nguyen Gia et al (2019) [ |
None | Heart rate and the QTg interval extraction, activity status categorization, and fall detection | Not described | Lightweight cryptography |
Rescio et al (2019) [ |
None | None | Not described | Not described |
Sarda et al (2019) [ |
Descriptive analysis and univariate analysis | SVM, RF, adaboost, extreme gradient boosting, and cross-validation | Not described | All transmissions were in an encrypted form using the HTTPSh secure sockets layer protocol |
Ramazi et al (2019) [ |
RMSE | New algorithm for different sensor signal synchronization and long short-term memory deep neural network | Study approved by the local institutional review board | Not described |
Garcia et al (2019) [ |
None | KNNi and SVM | Not described | Not described |
Sevil et al (2019) [ |
Mean, SD, kurtosis, and mean absolute error | SVM, KNN, linear discriminant, decision tree, and logistic regression | Study approved by the local institutional review board | Not described |
Zherebtsov et al (2019) [ |
Statistical significance | None | Study approved by the local institutional review board. Each volunteer gave a voluntary informed written consent to participate in the experiment | Not described |
Rodriguez-Rodriguez et al (2019) [ |
RMSE | Autoregressive integrated moving average, RF, and SVM | Study conducted in accordance with the Helsinki Declaration. Study approved by the local ethics committee. Data storage complied with the stricter data protection rules for protecting personal information. All participants were fully informed about the purpose of the experiment and provided written informed consent and assent according to the national regulations | Not described |
Sanz et al (2019) [ |
Median, linear regression, and cross-validation | None | Study approved by the local ethics committee | Not described |
Whelan et al (2019) [ |
Mean, SD, and frequency | None | All participants provided written informed consent. Study approved by the local ethics advisory committee | Not described |
aRF: random forest.
bSVM: support vector machine.
cRIPPER: repeated incremental pruning to produce error reduction.
dRDF: resource description framework.
eCQELS: continuous query evaluation over linked stream.
fRMSE: root mean square error.
gQT: electrocardiogram measurement QT interval.
hHTTPS: Hypertext Transfer Protocol Secure.
iKNN: k-nearest neighbors.
A total of 62% (16/26) of studies addressed privacy or security issues [
Overall, 19% (3/16) of studies considered security aspects. McLean et al [
The remaining 35% (19/26) of studies did not mention anything about privacy or security [
All details about
The number of participants involved differed significantly among the studies. The average number of participants was 29 (SD 28.2), calculated from 88% (23/26) of studies that indicated the number of participants [
As for the health status distribution for the 26 studies, 11 (42%) studies involved patients with DM [
A total of 31% (8/26) of studies involved subjects of both genders [
All details about the
Summary of study topic ordered by the year of publication.
Manuscript | Sample size | Sample type | Duration |
Najafi et al (2010) [ |
38 | 17 diabetic and 21 healthy; gender undefined; and age undefined | Not described |
Grewal et al (2013) [ |
39 | 31 diabetic and 8 healthy; gender undefined; and aged 56.9 (SD 8.2) years | Not described |
Luštrek et al (2014) [ |
10 | 0 diabetic and 10 healthy; gender undefined; and age undefined | Not described |
Luštrek et al (2015) [ |
5 | Health status undefined; 1 female and 4 males; and age undefined | 14 days |
Cvetković et al (2016) [ |
9 | 0 diabetic and 9 healthy; 1 female and 8 males; and aged 24-36 years | 14 days |
Calbimonte et al (2017) [ |
Not described | External data set | Not described |
Fraiwan et al (2017) [ |
Not described | Healthy; gender undefined; and age undefined | Not described |
McLean et al (2017) [ |
22 | 22 diabetic and 0 healthy; gender undefined; and age undefined | Not described |
Razjouyan et al (2017) [ |
25 | 25 diabetic and 0 healthy; gender undefined; aged 59.3 (SD 8.3) years | 21 (SD 4) days |
Reddy et al (2017) [ |
100 | 50 diabetic and 50 healthy; gender undefined; and aged 34 (SD 10) years (diabetic) and 41 (SD 13) years (healthy) | 5 mnin |
Turksoy et al (2017) [ |
26 | 26 diabetic and 0 healthy; 14 females and 12 males; and aged 24.2 (SD 5.41) years | 6 days |
Bartolic et al (2018) [ |
Not described | Health status undefined; gender undefined; and age undefined | Not described |
Faccioli et al (2018) [ |
6 | 6 diabetic and 0 healthy; gender undefined; and age undefined | 5 days |
Groat et al (2018) [ |
12 | 12 diabetic and 0 healthy; 8 females and 4 males; and aged 48 (SD 13.4) years | 30 days |
McMillan et al (2018) [ |
1 | 1 diabetic and 0 healthy; 0 female and 1 male; and aged 68 years | 1 day |
Merickel et al (2018) [ |
36 | 20 diabetic and 16 healthy; gender undefined; and aged 21-59 years | 28 days |
Nguyen Gia et al (2019) [ |
4 | 0 diabetic and 4 healthy; gender undefined; aged 30 years | Not described |
Rescio et al (2019) [ |
5 | Health status undefined; gender undefined; and aged 47.2 (SD 12.3) years | Not described |
Sarda et al (2019) [ |
46 | 46 diabetic and 0 healthy; 17 females and 29 males; and aged 35 (SD 12) years | 140 days |
Ramazi et al (2019) [ |
50 | 50 diabetic and 0 healthy; gender undefined; and aged 33-78 years | 7 days |
Garcia et al (2019) [ |
100 | 50 diabetic and 50 healthy; 58 females and 42 males; and aged 20-87 years | Not described |
Sevil et al (2019) [ |
2 | 2 diabetic and 0 healthy; gender undefined; and age undefined | 1 day |
Zherebtsov et al (2019) [ |
55 | 18 diabetic and 37 healthy; gender undefined; and aged 53.2 (SD 11.4) years (diabetic), 19.6 (SD 0.6) years (16 healthy), and 53.2 (SD 11.4) years (21 healthy) | 10 min |
Rodriguez-Rodriguez et al (2019) [ |
25 | 25 diabetic and 0 healthy; 11 females and 14 males; and aged 18-56 years | 14 days |
Sanz et al (2019) [ |
6 | 6 diabetic and 0 healthy; gender undefined; and aged 36.7 (SD 8.9) years | Not described |
Whelan et al (2019) [ |
45 | 0 diabetic and 45 healthy; 27 females and 18 males; and aged 56 (SD 9) years | 42 days |
The reviewed studies revealed the potential of mobile and wearable technologies in health areas. These technologies can significantly improve the management of conditions for both patients and clinicians for a variety of diseases. DM is not an exception, and growing attention has been paid to the use of these technologies in the recent years. Obtaining objective and continuous measurements is an important advantage of using this technology for patient monitoring. Data are sensed automatically by electronic sensors when the subject is interacting with the mobile or wearable devices both explicitly and implicitly, such as phone calls or step counts, respectively. These technologies most often enable the seamless collection of data, even when the patient is out of the clinic. This is a relevant feature to overcome the drawbacks of classical clinical trials in which subjects are required to stay in labs or clinics, set specific appointments, commute to the doctor’s office, etc. This technology adds a level of objectivity in the monitoring of patients with DM and people in general with respect to traditional clinical questionnaires, which are more dependent on users’ willingness and capacity to answer correctly. In addition, the patient may not remember everything accurately in between doctor visits and hospitalization times. In view of such limitations, the opportunities for the monitoring of DM-related parameters are unprecedented. Nonetheless, it is clear from this review that mobile and wearable technologies have been scarcely exploited for this purpose.
Several studies have not indicated the type of DM. In such studies, the authors refer to the condition simply as
Clinical trials were quite limited or even nonexistent in many of the reviewed studies. In fact, the majority of analyzed contributions had a predominant technological focus, prioritizing systems’ performance or robustness over the impact or applicability of potential clinical outcomes. This explains the remarkably low scores achieved by most of the selected studies in the NOS quality assessment. Most of the reviewed cohort studies did not have a sufficiently representative cohort. Most often, a distinction between exposed and nonexposed cohorts was not clearly made, or even worse, no description of the derivation of the cohort was provided. This lack of detail was also observed for cases and controls. Comparability was also found to be quite limited, as exposed and nonexposed individuals, if any, were not matched in the design, and confounders were either missing or not adjusted for in the analysis. Although outcomes were assessed in a majority of studies, follow-ups were mostly nonexistent or no information was provided whatsoever. Therefore, one of the major weaknesses detected in the reviewed studies is the limited dedication to the clinical validation of the proposed technical solutions.
Mobile and wearable data can shed new light on behavioral and physiological aspects that are difficult to approach in a continuous and unobtrusive manner via standard clinical tests. However, ignoring clinical data is certainly a big mistake. Therefore, combining passive mobile data with clinical data, such as laboratory test results, drug information, or patient demographics, is key for a holistic understanding of the patient’s current and future health status. Thus, it is recommended to perform more extensive clinical tests and validations involving the collection of new data sets. Existing data sets in this area show important flaws such as noninclusion of patients with DM, noninclusion of complementary clinical data, lack of gender diversity, or age variety. Moreover, public sharing of data sets is also considered essential to facilitate the replicability and reproducibility of the studies. Hence, data transparency and openness are encouraged, as in other similar disciplines.
None of the reviewed studies focused on the prevention of DM. This matter is especially important in the case of T2D, the only type of DM that can be prevented. Therefore, developing studies with outcomes that help to detect the disease in the early stages or even before it occurs can result in great progress. Approaching this subject from a holistic perspective could also be key for making new successful findings. This is closely related to the idea of using different data sources to generate more powerful medical models. Combining demographics, nutrition data, medication data, and passive sensor data among other heterogeneous data types can certainly help to realize more impactful and personalized solutions.
Activity recognition is one of the most important areas from which the monitoring of DM-related parameters could benefit. Thus, the research conducted in this new field may not only leverage the results from previous studies but also help in developing and testing new activity detection models. For example, improvements in the recognition of eating activities are needed to calculate food intake automatically.
Most of the studies had technological test phases, but in some cases, their quality was rather questionable. The description was often incomplete, lacked characteristics of the subjects, and did not mention the duration of the tests in several cases. These seem to be characteristics deemed in studies in the early stages. However, many of these studies stated that improvements would be made regarding this aspect in future research.
The studies analyzed in this review applied a variety of devices and sensors. Some case studies only used smartphones, others used only wearables, and others used a combination of them. This shows the ways in which these devices can be used to improve DM control and its complications. However, there is generally a poor description of the devices used in terms of their brand, model, manufacturer, main features, operating system, etc. This is an especially sensitive barrier for the replication of studies and development of follow-up research. Likewise, on some occasions, the sensors embedded in these devices were not explicitly described. Some studies included complementary devices such as a pressure platform, a glucometer, or an ambient sensor, not necessarily wearables, which helped to obtain more complete data and better characterize the patient’s environment. Most often, all devices were merely used to collect data for creating ML models and to find an association among variables or diseases, but in very few cases, the proposed solution was implemented in a realistic use case with long-lasting clinical applications.
The predominant sensor was the ACC, possibly because it is one of the most common sensors available on both wearables and mobile devices. In addition, its applications are closely related to energy expenditure and activity recognition tasks, which are very useful in DM problems. Other sensors such as GPS, thermometer, microphone, and ambient light are less commonly used in the reviewed studies. This may be because some of these sensors, such as GPS and microphone, are considered to be more privacy-intrusive by users. Nonetheless, these sensors were shown to be helpful as complements to other sensors for the monitoring of DM-related parameters. Furthermore, it is worth noting that none of the studies used commercial smart insoles but one prototype, especially given the fact that most important complications of DM translate into foot issues.
Diabetes technology has grown in the recent years, with CGM being at the forefront of the devices used. CGM is primarily used to monitor patients with T1D, with increasing use for patients with T2D. However, the use of CGM does not replace the traditional finger-stick test because patients still need to do a meter reading for accuracy, and in most cases, insurance companies do not cover the use of CGM. The fact that mobile and wearable technologies are at the reach of a majority of the population makes the reviewed solutions particularly cost-effective.
The power consumption of the hardware available in both mobiles and wearables has decreased with the latest advances. However, there is still much to be done to reduce it even further. The 5G technology promises to do so by lowering network energy use by almost 90% and increasing battery life, especially for low-power devices [
Data collected using mobile and wearable devices for continuous monitoring can be mined using AI techniques such as ML. As shown in this review, some authors used ML to extract information from the collected data, where large and heterogeneous data sets generally improve the performance of these techniques. Data from mobile and wearable sensors can, in principle, be used in combination with conventional clinical data to develop more relevant knowledge outcomes. The time and effort required to collect a data set that can be used to apply ML techniques is reduced by the use of mobile and wearable devices. Classical approaches are generally constrained by the number of samples or data points, as these are measured during clinic appointments, thus leading to lengthier collection phases.
The most common ML techniques used in these studies were decision trees and support vector machines, whereas other popular algorithms such as k-nearest neighbors, artificial neural networks, ensemble methods, and deep learning techniques are used less frequently. These techniques, especially when it comes to deep learning, can significantly boost the performance of the results, normally at the expense of having large data sets, a condition that is normally attained when using passive sensing. In general, experimentation with ML algorithms was performed using a small number of methods, whereas the use of a large variety of these techniques normally leads to higher robustness. Very few studies have used complementary clinical data in addition to sensor data, resulting in better models and more relevant outcomes.
Many manuscripts did not mention the endorsement of their studies from an ethics committee or review board. This is especially important because in several cases, people were used to test the proposed solutions. It is even more important to highlight that in very few occasions, the studies described that informed consent was requested from the participants in the trials. This occurs even when sensitive information is recorded from users during monitoring, such as location, video, or call logs. A reason for this could be linked to the rather emerging nature of this field or the lack of realistic clinical studies around which technical solutions have been developed.
Privacy and security issues were weak aspects of the reviewed studies. Researchers should devote more attention to both realizing and explaining proper procedures to ensure that security and privacy are properly addressed in clinical studies. Otherwise, the quality and applicability of the results are compromised. An effort must be made to put into practice the protocols in the trial involving the ethics committee or review boards in the authorization of the studies. Creating proper informed consents forms and using them in the trials should be a major concern for research in this area, especially in lieu of regulations such as the European General Data Protection Regulation. Similarly, information on data management plans can provide further details on how the research has been undertaken.
A summary of the principal findings described previously is provided in
Summary of the principal findings of the reviewed manuscripts. DM: diabetes mellitus; ECG: electrocardiogram; GL: glucose level; HR: heart rate; ML: machine learning; RR: respiration rate; T2D: type 2 diabetes.
The monitoring of DM-related parameters using mobile and wearable technology is an emerging field of study. As for any other review, despite having listed a wide variety of terms referring to sensors, wearable devices, and smartphones, new keywords emerge quite often in this rather dynamic technological area, which may have left out some interesting studies from our analysis. Although the search areas of this systematic review (computer science and engineering) are quite large, it is also possible that some relevant studies indexed in other related categories may have been filtered out. We conducted a preliminary check for other domains such as endocrinology metabolism, general internal medicine, or health care sciences services, and we did not find relevant studies that would meet the defined criteria. Other sources of digital data, such as social network interactions, have not been considered in this study, as they can be realized via different technologies besides mobiles and wearables. Nevertheless, it could be interesting to explore the potential of these interactions to explain some relevant behaviors of the patient, such as their mood. The lack of details in some studies also made it difficult to judge whether the authors were using commercial devices or their own prototype. Thus, it is possible that some relevant studies were excluded, although this is in line with the PRISMA guidelines followed in this systematic review.
As demonstrated in this systematic review, the field of mobile and wearable monitoring of DM-related parameters shows early promise, despite its recent development. Several actors may benefit at the maturation of this field: (1) patients with DM, who may have a better quality of life while improving the management and self-control of the disease or its complications in a continuous, passive, and unobtrusive way; (2) health care professionals and institutions, who may develop the ability to provide medical care and information in a portable and affordable way; and (3) researchers, who may have access to a large and varied amount of data sets to extract relevant information. The aforementioned 3 actors may work in synergy, which motivates a greater and faster evolution of the field. However, some gaps remain to accomplish this view, such as the creation or modification of relevant sensors to be less privacy-intrusive; decreasing the devices’ power consumption; using the advantages of the 5G technology; and, perhaps the most important one, combining passive mobile data with clinical data for a holistic understanding of the patient’s health status. Accomplishing these challenges requires interdisciplinary teams’ collaboration and the appropriate funding of governments and institutions to design and develop the required technologies for sensing the data, designing new and better processing techniques, and creating realistic solutions with long-lasting clinical applications.
Newcastle-Ottawa Scale quality assessment of the selected studies.
Reviewed manuscripts by the year of publication (up to July 28, 2020).
Sensor use for each study.
accelerometer
artificial intelligence
continuous glucose monitor
diabetic foot ulcer
diabetes mellitus
diabetic peripheral neuropathy
electrocardiogram
flash glucose monitor
gestational diabetes
glucose level
glucose monitor
heart rate
machine learning
Newcastle-Ottawa Scale
Preferred Reporting Items for Systematic Reviews and Meta-Analyses
respiration rate
type 1 diabetes
type 2 diabetes
Web of Science
This study was funded by the University of Granada within the framework of the Development Cooperation Fund. The study was also partially funded by the Spanish Project Advanced Computing Architectures and Machine Learning-Based Solutions for Complex Problems in Bioinformatics, Biotechnology, and Biomedicine (RTI2018-101674-B-I00).
CR and OB conceptualized the work. OB and CV defined the review methodology. CR and OB conducted screening at all levels and data extraction with the help of CV. CR, CV, and OB developed the analysis protocol and conducted the systematic analysis. CR and JRR conducted the quality assessment. CR, CV, MM, JRR and OB contributed to manuscript drafting, review and editing.
None declared.