The Promise and Perils of Wearable Physiological Sensors for Diabetes Management

Adoption of Wearable Insulin Biosensors for Diabetes Management: A Cross-Sectional Study

BACKGROUND

Wearable insulin biosensors represent a novel approach that combines the benefits of real-time glucose monitoring and automated insulin delivery, potentially revolutionizing how individuals with diabetes manage their condition.

STUDY PURPOSE

To analyze the behavioral intentions of wearable insulin biosensors among diabetes patients, the factors that drive or hinder their usage, and the implications for diabetes management and healthcare outcomes.

METHODS

A cross-sectional survey design was adopted in this study. The validated questionnaire included 10 factors (Performance expectancy, effort expectancy, social influence, facilitating conditions, behavioral intention, trust, perceived privacy risk, and personal innovativeness) affecting the acceptance of wearable insulin sensors. A total of 248 diabetic patients who had used wearable sensors participated in the study.

RESULTS

Performance expectancy was rated the highest (Mean = 3.84 out of 5), followed by effort expectancy (Mean = 3.78 out of 5), and trust (Mean = 3.53 out of 5). Statistically significant differences (p < 0.05) were observed with respect to socio-demographic variables including age and gender on various influencing factors and adoption intentions. PE, EE, and trust were positively associated with adoption intentions.

CONCLUSION

While wearable insulin sensors are positively perceived with respect to diabetes management, issues like privacy and security may affect their adoption.

The Clinical Impact of Flash Glucose Monitoring-a Digital Health App and Smartwatch Technology in Patients With Type 2 Diabetes: Scoping Review

BACKGROUND

Type 2 diabetes has a growing prevalence and confers significant cost burden to the health care system, raising the urgent need for cost-effective and easily accessible solutions. The management of type 2 diabetes requires significant commitment from the patient, caregivers, and the treating team to optimize clinical outcomes and prevent complications. Technology and its implications for the management of type 2 diabetes is a nascent area of research. The impact of some of the more recent technological innovations in this space, such as continuous glucose monitoring, flash glucose monitoring, web-based applications, as well as smartphone- and smart watch-based interactive apps has received limited attention in the research literature.

OBJECTIVE

This scoping review aims to explore the literature available on type 2 diabetes, flash glucose monitoring, and digital health technology to improve diabetic clinical outcomes and inform future research in this area.

METHODS

A scoping review was undertaken by searching Ovid MEDLINE and CINAHL databases. A second search using all identified keywords and index terms was performed on Ovid MEDLINE (January 1966 to July 2021), EMBASE (January 1980 to July 2021), Cochrane Central Register of Controlled Trials (CENTRAL; the Cochrane Library, latest issue), CINAHL (from 1982), IEEE Xplore, ACM Digital Libraries, and Web of Science databases.

RESULTS

There were very few studies that have explored the use of mobile health and flash glucose monitoring in type 2 diabetes. These studies have explored somewhat disparate and limited areas of research, and there is a distinct lack of methodological rigor in this area of research. The 3 studies that met the inclusion criteria have addressed aspects of the proposed research question.

CONCLUSIONS

This scoping review has highlighted the lack of research in this area, raising the opportunity for further research in this area, focusing on the clinical impact and feasibility of the use of multiple technologies, including flash glucose monitoring in the management of patients with type 2 diabetes.

The Effectiveness of Wearable Devices Using Artificial Intelligence for Blood Glucose Level Forecasting or Prediction: Systematic Review

BACKGROUND

In 2021 alone, diabetes mellitus, a metabolic disorder primarily characterized by abnormally high blood glucose (BG) levels, affected 537 million people globally, and over 6 million deaths were reported. The use of noninvasive technologies, such as wearable devices (WDs), to regulate and monitor BG in people with diabetes is a relatively new concept and yet in its infancy. Noninvasive WDs coupled with machine learning (ML) techniques have the potential to understand and conclude meaningful information from the gathered data and provide clinically meaningful advanced analytics for the purpose of forecasting or prediction.

OBJECTIVE

The purpose of this study is to provide a systematic review complete with a quality assessment looking at diabetes effectiveness of using artificial intelligence (AI) in WDs for forecasting or predicting BG levels.

METHODS

We searched 7 of the most popular bibliographic databases. Two reviewers performed study selection and data extraction independently before cross-checking the extracted data. A narrative approach was used to synthesize the data. Quality assessment was performed using an adapted version of the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.

RESULTS

From the initial 3872 studies, the features from 12 studies were reported after filtering according to our predefined inclusion criteria. The reference standard in all studies overall (n=11, 92%) was classified as low, as all ground truths were easily replicable. Since the data input to AI technology was highly standardized and there was no effect of flow or time frame on the final output, both factors were categorized in a low-risk group (n=11, 92%). It was observed that classical ML approaches were deployed by half of the studies, the most popular being ensemble-boosted trees (random forest). The most common evaluation metric used was Clarke grid error (n=7, 58%), followed by root mean square error (n=5, 42%). The wide usage of photoplethysmogram and near-infrared sensors was observed on wrist-worn devices.

CONCLUSIONS

This review has provided the most extensive work to date summarizing WDs that use ML for diabetic-related BG level forecasting or prediction. Although current studies are few, this study suggests that the general quality of the studies was considered high, as revealed by the QUADAS-2 assessment tool. Further validation is needed for commercially available devices, but we envisage that WDs in general have the potential to remove the need for invasive devices completely for glucose monitoring in the not-too-distant future.

TRIAL REGISTRATION

PROSPERO CRD42022303175; https://tinyurl.com/3n9jaayc.

Investigating the prevalence of diabetic complications in overweight/obese patients: a study in a tertiary hospital in Malaysia

Background

In Malaysia, although diabetes accounts for more than 70% of all deaths, it is unclear how it relates to BMI and diabetic complications. This study aimed to investigate the prevalence of obesity and diabetic complications among diabetic patients in Malaysia.

Materials and methods

A cross-sectional study using an existing clinical registry was performed from 1 January 2020 to 31 December 2020 at Hospital Serdang, Malaysia. Adult patients with type 2 diabetes mellitus had their medical records examined for disease complications, as reported by the patient at first contact with the DMTAC pharmacist.

Results

The study comprised a total of 495 participants with an average HbA1c of 10.5%. About 91% (n = 451) of the 495 patients were obese/overweight. Around 37.8% (n = 187) of diabetic patients are between the ages of 50 and 59, and 59% (n = 292) have had diabetes for less than 10 years. A total of 8.5% (n = 42) and 9.7% (n = 48) consume alcohol and smoke, respectively. Around 29.9% (n = 148) had one other comorbidity (hypertension or dyslipidemia), and 63.4% (n = 314) had two comorbidities. Regarding the prevalence of complications, there were 18.9% (n = 94) who had myocardial infarction, 11.1% (n = 55) who had stroke, and 9% (n = 45) who had CKD. Age (adjusted OR = 1.03; 95% CI 1.00 to 1.07; p = 0.041) and hypertension (adjusted OR = 4.06; 95% CI 1.21 to 13.60; p = 0.023) were significantly related with the prevalence of complications in patients with diabetes.

Conclusion

In our study, a BMI of more than 23 kg/m2 (obese/overweight) does not seem to be associated with the prevalence of complications. Age and hypertension, on the other hand, appear to be strong risk predictors of the incidence of complications. With the understanding of the recent outlook on diabetes, it is recommended that public education on the targeted population should be encouraged to negate these complications.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13410-022-01131-x.

Overview of Artificial Intelligence-Driven Wearable Devices for Diabetes: Scoping Review

Background

Prevalence of diabetes has steadily increased over the last few decades with 1.5 million deaths reported in 2012 alone. Traditionally, analyzing patients with diabetes has remained a largely invasive approach. Wearable devices (WDs) make use of sensors historically reserved for hospital settings. WDs coupled with artificial intelligence (AI) algorithms show promise to help understand and conclude meaningful information from the gathered data and provide advanced and clinically meaningful analytics.

Objective

This review aimed to provide an overview of AI-driven WD features for diabetes and their use in monitoring diabetes-related parameters.

Methods

We searched 7 of the most popular bibliographic databases using 3 groups of search terms related to diabetes, WDs, and AI. A 2-stage process was followed for study selection: reading abstracts and titles followed by full-text screening. Two reviewers independently performed study selection and data extraction, and disagreements were resolved by consensus. A narrative approach was used to synthesize the data.

Results

From an initial 3872 studies, we report the features from 37 studies post filtering according to our predefined inclusion criteria. Most of the studies targeted type 1 diabetes, type 2 diabetes, or both (21/37, 57%). Many studies (15/37, 41%) reported blood glucose as their main measurement. More than half of the studies (21/37, 57%) had the aim of estimation and prediction of glucose or glucose level monitoring. Over half of the reviewed studies looked at wrist-worn devices. Only 41% of the study devices were commercially available. We observed the use of multiple sensors with photoplethysmography sensors being most prevalent in 32% (12/37) of studies. Studies reported and compared >1 machine learning (ML) model with high levels of accuracy. Support vector machine was the most reported (13/37, 35%), followed by random forest (12/37, 32%).

Conclusions

This review is the most extensive work, to date, summarizing WDs that use ML for people with diabetes, and provides research direction to those wanting to further contribute to this emerging field. Given the advancements in WD technologies replacing the need for invasive hospital setting devices, we see great advancement potential in this domain. Further work is needed to validate the ML approaches on clinical data from WDs and provide meaningful analytics that could serve as data gathering, monitoring, prediction, classification, and recommendation devices in the context of diabetes.

The Effectiveness of Wearable Devices Using Artificial Intelligence for Blood Glucose Level Forecasting or Prediction: Systematic Review (Preprint).. [DOI: 10.2196/preprints.40259] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

In 2021 alone, diabetes mellitus, a metabolic disorder primarily characterized by abnormally high blood glucose (BG) levels, affected 537 million people globally, and over 6 million deaths were reported. The use of noninvasive technologies, such as wearable devices (WDs), to regulate and monitor BG in people with diabetes is a relatively new concept and yet in its infancy. Noninvasive WDs coupled with machine learning (ML) techniques have the potential to understand and conclude meaningful information from the gathered data and provide clinically meaningful advanced analytics for the purpose of forecasting or prediction.

OBJECTIVE

The purpose of this study is to provide a systematic review complete with a quality assessment looking at diabetes effectiveness of using artificial intelligence (AI) in WDs for forecasting or predicting BG levels.

METHODS

We searched 7 of the most popular bibliographic databases. Two reviewers performed study selection and data extraction independently before cross-checking the extracted data. A narrative approach was used to synthesize the data. Quality assessment was performed using an adapted version of the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool.

RESULTS

From the initial 3872 studies, the features from 12 studies were reported after filtering according to our predefined inclusion criteria. The reference standard in all studies overall (n=11, 92%) was classified as low, as all ground truths were easily replicable. Since the data input to AI technology was highly standardized and there was no effect of flow or time frame on the final output, both factors were categorized in a low-risk group (n=11, 92%). It was observed that classical ML approaches were deployed by half of the studies, the most popular being ensemble-boosted trees (random forest). The most common evaluation metric used was Clarke grid error (n=7, 58%), followed by root mean square error (n=5, 42%). The wide usage of photoplethysmogram and near-infrared sensors was observed on wrist-worn devices.

CONCLUSIONS

This review has provided the most extensive work to date summarizing WDs that use ML for diabetic-related BG level forecasting or prediction. Although current studies are few, this study suggests that the general quality of the studies was considered high, as revealed by the QUADAS-2 assessment tool. Further validation is needed for commercially available devices, but we envisage that WDs in general have the potential to remove the need for invasive devices completely for glucose monitoring in the not-too-distant future.

CLINICALTRIAL

PROSPERO CRD42022303175; https://tinyurl.com/3n9jaayc

Exercise and Self-Management in Adults with Type 1 Diabetes

PURPOSE OF REVIEW

The purpose of this review paper is to examine the most recent evidence of exercise-related self-management in adults with type 1 diabetes (T1D).

RECENT FINDINGS

This paper reviews the benefits and barriers to exercise, diabetes self-management education, the role of the healthcare provider in assessment and counseling, the use of technology, and concerns for special populations with T1D. Adults with T1D may not exercise at sufficient levels. Assessing current levels of exercise, counseling during a clinical visit, and the use of technology may improve exercise in this population.

A Brief Review on the Evolution of Technology in Exercise and Sport in Type 1 Diabetes: Past, Present, and Future

One hundred years ago, insulin was first used to successfully lower blood glucose levels in young people living with what was then called juvenile diabetes. While insulin was not a cure for diabetes, it allowed individuals to resume a near normal life and have some freedom to eat more liberally and gain the strength they needed to live a more active lifestyle. Since then, a number of therapeutic and technical advances have arisen to further improve the health and wellbeing of individuals living with type 1 diabetes, allowing many to participate in sport at the local, regional, national or international level of competition. This review and commentary highlights some of the key advances in diabetes management in sport over the last 100 years since the discovery of insulin.

Sensor-Based Prediction of Mental Effort during Learning from Physiological Data: A Longitudinal Case Study

Trackers for activity and physical fitness have become ubiquitous. Although recent work has demonstrated significant relationships between mental effort and physiological data such as skin temperature, heart rate, and electrodermal activity, we have yet to demonstrate their efficacy for the forecasting of mental effort such that a useful mental effort tracker can be developed. Given prior difficulty in extracting relationships between mental effort and physiological responses that are repeatable across individuals, we make the case that fusing self-report measures with physiological data within an internet or smartphone application may provide an effective method for training a useful mental effort tracking system. In this case study, we utilized over 90 h of data from a single participant over the course of a college semester. By fusing the participant’s self-reported mental effort in different activities over the course of the semester with concurrent physiological data collected with the Empatica E4 wearable sensor, we explored questions around how much data were needed to train such a device, and which types of machine-learning algorithms worked best. We concluded that although baseline models such as logistic regression and Markov models provided useful explanatory information on how the student’s physiology changed with mental effort, deep-learning algorithms were able to generate accurate predictions using the first 28 h of data for training. A system that combines long short-term memory and convolutional neural networks is recommended in order to generate smooth predictions while also being able to capture transitions in mental effort when they occur in the individual using the device.

Deep Learning for Diabetes: A Systematic Review

Diabetes is a chronic metabolic disorder that affects an estimated 463 million people worldwide. Aiming to improve the treatment of people with diabetes, digital health has been widely adopted in recent years and generated a huge amount of data that could be used for further management of this chronic disease. Taking advantage of this, approaches that use artificial intelligence and specifically deep learning, an emerging type of machine learning, have been widely adopted with promising results. In this paper, we present a comprehensive review of the applications of deep learning within the field of diabetes. We conducted a systematic literature search and identified three main areas that use this approach: diagnosis of diabetes, glucose management, and diagnosis of diabetes-related complications. The search resulted in the selection of 40 original research articles, of which we have summarized the key information about the employed learning models, development process, main outcomes, and baseline methods for performance evaluation. Among the analyzed literature, it is to be noted that various deep learning techniques and frameworks have achieved state-of-the-art performance in many diabetes-related tasks by outperforming conventional machine learning approaches. Meanwhile, we identify some limitations in the current literature, such as a lack of data availability and model interpretability. The rapid developments in deep learning and the increase in available data offer the possibility to meet these challenges in the near future and allow the widespread deployment of this technology in clinical settings.

Diabetes Technology and Exercise

Advances in technologies such as glucose monitors, exercise wearables, closed-loop systems, and various smartphone applications are helping many people with diabetes to be more physically active. These technologies are designed to overcome the challenges associated with exercise duration, mode, relative intensity, and absolute intensity, all of which affect glucose homeostasis in people living with diabetes. At present, optimal use of these technologies depends largely on motivation, competence, and adherence to daily diabetes care requirements. This article discusses recent technologies designed to help patients with diabetes to be more physically active, while also trying to improve glucose control around exercise.

Modern noninvasive methods for monitoring glucose levels in patients: a review

This paper presents the current state of the art of noninvasive glucose monitoring. In recent years, we can observe constant increase in the incidence of diabetes. About 40% of all performed blood tests apply to the glucose tests. Formerly, this lifestyle disease occurred mainly in rich countries, but now it is becoming more common in poorer countries. It is related to the increase in life expectancy, unhealthy diet, lack of exercise, and other factors. Untreated diabetes may cause many complications or even death. For this reason, daily control of glucose levels in people with this disorder is very important. Measurements with a traditional glucometer are connected with performing finger punctures several times a day, which is painful and uncomfortable for patients. Therefore, researches on other methods are ongoing. A method that would be fast, noninvasive and cheap could also enable testing the state of the entire population, which is necessary because of the number of people currently living with undiagnosed type 2 diabetes. Although the first glucometer was made in 1966, the first studies on glucose level measurement in tear film were documented as early as 1937. This shows how much a noninvasive method of diabetes control is needed. Since then, there have been more and more studies on alternative methods of glucose measurement, not only from tear fluid, but also from saliva, sweat, or transdermally.

Validity of a Portable Breath Analyser (AIRE) for the Assessment of Lactose Malabsorption

Hydrogen (H₂) measurement in exhaled breath is a reliable and non-invasive method to diagnose carbohydrate malabsorption. Currently, breath H₂ measurement is typically limited to clinic-based equipment. A portable breath analyser (AIRE, FoodMarble Digestive Health Limited, Dublin, Ireland) is a personalised device marketed for the detection and self-management of food intolerances, including lactose malabsorption (LM). Currently, the validity of this device for breath H₂ analysis is unknown. Individuals self-reporting dairy intolerance (six males and six females) undertook a lactose challenge and a further seven individuals (all females) underwent a milk challenge. Breath samples were collected prior to and at frequent intervals post-challenge for up to 5 h with analysis using both the AIRE and a calibrated breath hydrogen analyser (BreathTracker, QuinTron Instrument Company Inc., Milwaukee, WI, USA). A significant positive correlation (p < 0.001, r > 0.8) was demonstrated between AIRE and BreathTracker H₂ values, after both lactose and milk challenges, although 26% of the AIRE readings demonstrated the maximum score of 10.0 AU. Based on our data, the cut-off value for LM diagnosis (25 ppm H₂) using AIRE is 3.0 AU and it is effective for the identification of a response to lactose-containing foods in individuals experiencing LM, although its upper limit is only 81 ppm.

Wearables and the medical revolution

Wearable sensors are already impacting healthcare and medicine by enabling health monitoring outside of the clinic and prediction of health events. This paper reviews current and prospective wearable technologies and their progress toward clinical application. We describe technologies underlying common, commercially available wearable sensors and early-stage devices and outline research, when available, to support the use of these devices in healthcare. We cover applications in the following health areas: metabolic, cardiovascular and gastrointestinal monitoring; sleep, neurology, movement disorders and mental health; maternal, pre- and neo-natal care; and pulmonary health and environmental exposures. Finally, we discuss challenges associated with the adoption of wearable sensors in the current healthcare ecosystem and discuss areas for future research and development.