Diabetes Management Systems Research Articles

Hybrid CNN-GRU Model for Real-Time Blood Glucose Forecasting: Enhancing IoT-Based Diabetes Management with AI

For people with diabetes, controlling blood glucose level (BGL) is a significant issue since the disease affects how the body metabolizes food, which makes careful insulin regulation necessary. Patients have to manually check their blood sugar levels, which can be laborious and inaccurate. Many variables affect BGL changes, making accurate prediction challenging. To anticipate BGL many steps ahead, we propose a novel hybrid deep learning model framework based on Gated Recurrent Units (GRUs) and Convolutional Neural Networks (CNNs), which can be integrated into the Internet of Things (IoT)-enabled diabetes management systems, improving prediction accuracy and timeliness by allowing real-time data processing on edge devices. While the GRU layer records temporal relationships and sequence information, the CNN layer analyzes the incoming data to extract significant features. Using a publicly accessible type 1 diabetes dataset, the hybrid model’s performance is compared to that of the standalone Long Short-Term Memory (LSTM), CNN, and GRU models. The findings show that the hybrid CNN-GRU model performs better than the single models, indicating its potential to significantly improve real-time BGL forecasting in IoT-based diabetes management systems.

Continuous Glucose, Insulin and Lifestyle Data Augmentation in Artificial Pancreas Using Adaptive Generative and Discriminative Models.

Artificial pancreas requires data from multiple sources for accurate insulin dose estimation. These include data from continuous glucose sensors, past insulin dosage information, meal quantity and time and physical activity data. The effectiveness of closed-loop diabetes management systems might be hampered by the absence of these data caused by device error or lack of compliance by patients. In this study, we demonstrate the effect of output sequence length-driven generative and discriminative model selection in high quality data generation and augmentation. This novel generative adversarial network (GAN) based architecture automatically selects the generator and discriminator architecture based on the desired output sequence length. The proposed model is able to generate glucose, physical activity, meal information data for individual patients. The discriminative scores for Ohio T1DM (2018) dataset were 0.17 ±0.03 (Inputs: CGM, CHO, Insulin) and 0.15 ±0.02 (Inputs: CGM, CHO, Insulin, Heart Rate, Steps) and for Ohio T1D (2020) dataset was 0.16 ±0.02 (Inputs: CGM, CHO, Insulin) and 0.15 ±0.02 (Inputs: CGM, CHO, Insulin, acceleration). A mixture of generated and real data was used to test predictive scores for glucose forecasting models. The best RMSE and MARD achieved for OhioT1DM patients were 17.19 ±3.22 and 7.14 ±1.76 for PH=30 min with CGM, CHO, Insulin, heartrate and steps as inputs. Similarly, the RMSE and MARD for real+synthetic data were 15.63 ±2.57 and 5.86 ±1.69 respectively. Compared to existing generative models, we demonstrate that sequence length based architecture selection leads to better synthetic data generation for multiple output sequences (CGM, CHO, Insulin) and forecasting accuracy.

Healthcare Analysis Based on Diabetes Prediction Using a Cuckoo-Based Deep Convolutional Long-Term Memory Algorithm

In recent years, the demand for mobile medical applications utilizing the Internet of Things (IoT) for diabetes diagnosis has been progressively increasing. Diabetes is commonly known as a chronic illness that presents a significant danger to individuals, analysing when blood sugar levels surpass the typical range. If diabetes is not promptly treated, hyperosmolar conditions can lead to serious health issues like hyperglycaemia and possibly even death. Since early detection enables lifestyle changes that prevent the disease's progression, it is crucial for diabetes management and health systems. However, diabetes diagnosis has a long computational time and low prediction accuracy. To address this issue, we propose a Cuckoo-Based Deep Convolutional Long-Term Memory (CDC-LSTM) algorithm that increases accuracy by classifying diabetics or non-diabetics. Additionally, we utilize the Standardized Feature Scaler (SFS) method to normalize the variance data by removing the mean of each feature. Moreover, we select the optimal features in the diabetes dataset utilising the Filter-Based Decision Tree (FBDT) technique. Finally, the proposed CDC-LSTM method can be used to distinguish between diabetics and non-diabetics, improving the accuracy of identifying diabetic patients. Additionally, the proposed method can predict diabetes using performance assessments such as precision, recall, and F-measure. Furthermore, the method's accuracy can be improved to 95.18% compared to previous approaches.

Is Raman the best strategy towards the development of non-invasive continuous glucose monitoring devices for diabetes management?

Diabetes has no well-established cure; thus, its management is critical for avoiding severe health complications involving multiple organs. This requires frequent glycaemia monitoring, and the gold standards for this are fingerstick tests. During the last decades, several blood-withdrawal-free platforms have been being studied to replace this test and to improve significantly the quality of life of people with diabetes (PWD). Devices estimating glycaemia level targeting blood or biofluids such as tears, saliva, breath and sweat, are gaining attention; however, most are not reliable, user-friendly and/or cheap. Given the complexity of the topic and the rise of diabetes, a careful analysis is essential to track scientific and industrial progresses in developing diabetes management systems. Here, we summarize the emerging blood glucose level (BGL) measurement methods and report some examples of devices which have been under development in the last decades, discussing the reasons for them not reaching the market or not being really non-invasive and continuous. After discussing more in depth the history of Raman spectroscopy-based researches and devices for BGL measurements, we will examine if this technique could have the potential for the development of a user-friendly, miniaturized, non-invasive and continuous blood glucose-monitoring device, which can operate reliably, without inter-patient variability, over sustained periods.

Nanohybrid electrocatalyst based on cobalt phthalocyanine-carbon nanotube-reduced graphene oxide for ultrasensitive detection of glucose in human saliva

The current diabetes management systems require collecting blood samples via an invasive and painful finger pricking leading to the formation of callus, scarring and loss of sensibility to patients due to continuous monitoring. Therefore, a non-invasive and painless method of determining glucose levels would be desirable to diabetes patients who need constant monitoring. Saliva glucose measurement is a non-invasive alternative for diabetes management. A highly sensitive, stable, and selective non-enzymatic electrochemical sensor that can accurately quantify saliva glucose is required. A single-walled carbon nanotube/reduced graphene oxide/cobalt phthalocyanines nanohybrid modified glassy carbon electrode (GCE-SWCNT/rGO/CoPc) has been fabricated for the non-enzymatic determination of glucose in human saliva. The SWCNT/rGO/CoPc was characterized using various spectroscopic, microscopic, and electrochemical techniques. The synergistic effect between SWCNT, rGO, and CoPc facilitated excellent electron transfer process that improved the sensor sensitivity. The GCE-SWCNT/rGO/CoPc sensor exhibited two linear responses in the 0.30 μM to 0.50 mM and 0.50–5.0 mM glucose concentration ranges, and the detection limit was 0.12 μM. The sensor had an excellent saliva glucose detection sensitivity of 992.4 μA·mM−1·cm−2 and high specificity for glucose in the presence of other coexisting analytes. In addition, it showed good storage stability, reusability, and a fast response time of about 1.2 s. The GCE-SWCNT/rGO/CoPc nanohybrid electrode showed excellent potential for developing accurate, non-invasive, and painless glucose sensing.

Assessment of Systems and Services for Management of Diabetes and Diabetic Retinopathy in Cameroon

ABSTRACT Aim To evaluate systems and services for management of diabetes and diabetic retinopathy. Methodology The National Program for Blindness Control conducted a nationwide descriptive study from 1st February to 31st October 2016. Data was collected using WHO’s:“Tool Assessment of Diabetic Retinopathy and Diabetes Management Systems” adapted to the context. Using direct interviews, all previously identified stakeholders, were involved from all levels of management and throughout the territory. The IBM version 20 software permitted analysis. Results Out of the 48 individuals selected, 46 agreed to participate in the survey. Four participants (8.7%) worked at the central level of the Ministry of Public Health, 2 (4.4%) were NGOs partners, 6 (13%) diabetic patients, and 34 (73.9%) health staff. According to the answers of participants, diabetes stands among priorities in the national health policy. Diabetic care services have been integrated into the National action plan for Chronic Non-Communicable Diseases, but a specific program for control of diabetes has not been created neither are national guidelines recommended by the Ministry available. Some health facilities provide care for diabetes and its complications. Modern technologies for evaluation and follow-up of diabetes of its complications are available only in tertiary level hospitals and in some private clinics. The cost of care obtained is the responsibility of the patients and families. Conclusion The political will to manage diabetes and diabetic retinopathy is recognized by stakeholders and beneficiaries but not translated into an effective program. A suitable implementation strategy is necessary.

Time spent in target range assessed by self-monitoring blood glucose associates with glycated hemoglobin in insulin treated patients with diabetes

Background and aimsSelf-monitoring blood glucose (SMBG) remains a widespread tool to monitor blood glucose. The development of diabetes management systems (DMS) allows SMBG to provide additional information as time spent in target range (TIR). This study evaluates the association between HbA1c and TIR, evaluated through DMS, over 2 months, and 2 weeks. Methods and resultsType 1 (T1D) and Type 2 (T2D) insulin-treated patients with diabetes were enrolled. We used the term PIR (Points in Range) instead of TIR, since SMBG provides point-in-time glucose values rather than a continuous trend over time. PIR was calculated in 2-month and 2-week time ranges before available HbA1c measurement.One-hundred ninety-seven patients with T1D and 36 with T2D were recruited. HbA1c and PIR were inversely associated (2 months: R -0.72, 2 weeks R -0.70; p < 0.0001) in all subjects. The relationship did not change when T1D and T2D patients were analyzed separately. For every 10% change of PIR, there was a change of HbA1c by 0.4%. ConclusionsOur study, for the first time, demonstrates a significant correlation between HbA1c and PIR calculated by DMS. DMS offers additional information useful in disease management of patients with T1D and T2D performing SMBG.

SAT-636 The Fast-Evolving Connected Diabetes Care Landscape: Transforming Diabetes Care with Telehealth and Technology

Background and AimsRecent years have brought about a new form of “connected diabetes care,” defined as digital diabetes management systems based around (1) smartphone apps, (2) devices with built-in connectivity, and (3) remote human and automated coaching and support. Given their potential to help improve health outcomes, the rapid pace of innovation, and the dearth of information about them to guide patients, providers, and payers, we provide an update on the landscape of and trends in connected diabetes care offerings.MethodsProminent connected diabetes care providers that have published results are categorized and characterized. Similarities and differences are identified and the state of available evidence is evaluated.ResultsConnected diabetes care offerings were analyzed for items including: health conditions managed, care team composition, connected medical devices, and evidence. We expect these players will further expand offerings across chronic conditions, strive to integrate more deeply with the traditional healthcare system, deploy greater automation to promote scalability, and find clever ways to promote and support the use of continuous glucose monitoring in type 2 diabetes. Future evidence generation for this field should have more standardized methodology.ConclusionsThe field of connected diabetes care has tremendous potential to improve outcomes, but it is in its infancy in terms of awareness, uptake, and effectiveness. Further, questions regarding offerings’ abilities to support most people with diabetes sustainably remain. However, existing evidence is sufficient to support further exploration and refinement of the model as the next step in team-based diabetes care.

Effect of a Mobile Phone-Based Glucose-Monitoring and Feedback System for Type 2 Diabetes Management in Multiple Primary Care Clinic Settings: Cluster Randomized Controlled Trial.

BackgroundRecent evidence of the effectiveness of mobile phone–based diabetes management systems is generally based on studies conducted in tertiary hospitals or professional diabetes clinics.ObjectiveThis study aimed to evaluate the clinical efficacy and applicability of a mobile phone–based glucose-monitoring and feedback system for the management of type 2 diabetes mellitus (T2DM) in multiple primary care clinic settings.MethodsIn this multicenter, cluster-randomized controlled, open trial, 13 primary care clinics in Seoul and other large cities in South Korea were voluntarily recruited. Overall, 150 (9 clinics) and 97 (4 clinics) participants with T2DM were assigned to the intervention and control groups, respectively (2:1 allocation). Every month, participants in both groups attended face-to-face physicians’ consultation for the management of diabetes in the clinic. For the intervention group, participants were required to upload their daily self-monitoring of blood glucose (SMBG) results using the mobile phone app in addition to outpatient care for 3 months. The results were automatically transmitted to the main server. Physicians had to check their patients’ SMBG results through an administrator’s website and send a short feedback message at least once a week. At baseline and 3 months, both groups had anthropometry and blood tests, including hemoglobin A1c (HbA1c), and responded to questionnaires about treatment satisfaction and compliance.ResultsAt 3 months, participants in the intervention group showed significantly more improvement in HbA1c (adjusted mean difference to control −0.30%, 95% CI −0.50 to −0.11; P=.003) and fasting plasma glucose (−17.29 mg/dL, 95% CI −29.33 to −5.26; P=.005) than those in the control group. In addition, there was significantly more reduction in blood pressure, and the score regarding treatment satisfaction and motivation for medication adherence increased more in the intervention group than in the control group. In the subgroup analyses, the effect on glycemic control was more significant among younger patients and higher baseline HbA1c levels.ConclusionsThe mobile phone–based glucose-monitoring and feedback system was effective in glycemic control when applied in primary care clinic settings. This system could be utilized effectively with diverse institutions and patients.Trial RegistrationClinical Research Information Service (CRIS) https://tinyurl.com/tgqawbz

Assessment of diabetic retinopathy and diabetes management systems in Pakistan using a WHO tool.

Using WHO questionnaire known as TADDS(Tool for Assessment of Diabetic Retinopathy and Diabetes Management System), a country wide survey was conducted to assess the health care system for diabetes mellitus (DM) and diabetic retinopathy (DR). This would also provide any evidence of the presence and usefulness of links between the two. A total of 190 key informants for DR and DM services from 47 districts were interviewed. The answers were reviewed and any disagreement was resolved through discussion with stakeholders'. The final results were disseminated. The results showed that diabetes is listed as a priority; national plan exists but programme has not been implemented. Health professionals are unaware about Ministry of Health guidelines. There is infrequent networking between DM and DR care providers. Transport and cost are the main barriers for accessing these services. Out of pocket expenses provide 55% of health care financing.

Reviewing U.S. Connected Diabetes Care: The Newest Member of the Team.

Recent years have brought about an explosion in the number of companies offering connected diabetes care products, defined as digital diabetes management systems based around (1) smartphone apps, (2) devices with built-in connectivity, and (3) remote human and automated coaching and support. These nascent models aim to provide more continuous and on-demand care, aligning with the 24/7 demands of chronic disease. It has been enabled by multiple factors, including the rising use of connected devices and apps to help people manage their chronic conditions, growing appreciation for the importance of outcomes beyond A1c, and the lofty and growing cost of health care. Despite the potential of these programs to improve the outcomes and well-being of people with diabetes and reduce the burdens on health care providers and systems, awareness and use of these programs and approaches remain low in the medical community. In this article, we present a snapshot of this dynamic field, including a taxonomy of various connected diabetes care products available to employers, health plans, health systems, and people with diabetes in the United States, and we identify meaningful distinctions among them: (1) health conditions managed, (2) peer support interactions, (3) prescribing providers on the care team, (4) provision of connected medical devices and/or continuous glucose monitors, (5) degree of treatment personalization, and (6) clinical and real-world evidence. We also discuss broad trends in connected diabetes care. Given the urgency and scale of the diabetes epidemic, it is vital that a range of medical and clinical communities find meaningful ways to scale individualized, timely care under reimbursement models that better align incentives for various stakeholders, particularly health care providers themselves. This would not only address deficiencies in care but could also make diabetes care more attractive to future clinicians.

“Diabetes Just Tends to Take Over Everything”: Experiences of Support and Barriers to Diabetes Management for Pregnancy in Women With Type 1 Diabetes

To optimize clinical outcomes, women with type 1 diabetes are advised to consistently achieve blood glucose levels in their target range before becoming pregnant. However, following this recommendation can be clinically and psychologically challenging for patients. We explored women’s experiences of pregnancy-related diabetes management and any barriers and support systems affecting their self-management. Fifteen semi-structured telephone interviews were conducted with a nationwide sample. Interviews focused on women’s perceptions of barriers hindering pregnancy-related diabetes management and support systems facilitating their self-management. Audio recordings were analyzed using inductive thematic analysis. Results indicated significant impairment of psychological health and overall quality of life in women with type 1 diabetes who were pregnant or planning pregnancy. Most participants reported a lack of support and empathetic engagement from their health care team, which affected their clinical management. Guilt and concerns about high blood glucose levels, constant pressure to meet glucose targets, and difficult interactions with health care professionals were a few of the primary themes with regard to barriers to optimal management. Patient-centered programs that provide effective clinical and psychosocial support for women who are preparing for pregnancy with preexisting diabetes are urgently needed so that these women feel adequately supported and empowered to undertake pregnancy.

Impact of errors in paper-based and computerized diabetes management with decision support for hospitalized patients with type 2 diabetes. A post-hoc analysis of a before and after study

ObjectiveMost preventable adverse drug events and medication errors occur during medication ordering. Medication order entry and clinical decision support are available on paper or as computerized systems. In this post-hoc analysis we investigated frequency and clinical impact of blood glucose (BG) documentation- and user-related calculation errors as well as workflow deviations in diabetes management. We aimed to compare a paper-based protocol to a computerized medication management system combined with clinical workflow and decision support. MethodsSeventy-nine hospitalized patients with type 2 diabetes mellitus were treated with an algorithm driven basal-bolus insulin regimen. BG measurements, which were the basis for insulin dose calculations, were manually entered either into the paper-based workflow protocol (PaperG: 37 patients) or into GlucoTab®—a mobile tablet PC based system (CompG: 42 patients). We used BG values from the laboratory information system as a reference. A workflow simulator was used to determine user calculation errors as well as workflow deviations and to estimate the effect of errors on insulin doses. The clinical impact of insulin dosing errors and workflow deviations on hypo- and hyperglycemia was investigated. ResultsThe BG documentation error rate was similar for PaperG (4.9%) and CompG group (4.0%). In PaperG group, 11.1% of manual insulin dose calculations were erroneous and the odds ratio (OR) of a hypoglycemic event following an insulin dosing error was 3.1 (95% CI: 1.4–6.8). The number of BG values influenced by insulin dosing errors was eightfold higher than in the CompG group. In the CompG group, workflow deviations occurred in 5.0% of the tasks which led to an increased likelihood of hyperglycemia, OR 2.2 (95% CI: 1.1–4.6). DiscussionManual insulin dose calculations were the major source of error and had a particularly strong influence on hypoglycemia. By using GlucoTab®, user calculation errors were entirely excluded. The immediate availability and automated handling of BG values from medical devices directly at the point of care has a high potential to reduce errors. Computerized systems facilitate the safe use of more complex insulin dosing algorithms without compromising usability. In CompG group, missed or delayed tasks had a significant effect on hyperglycemia, while in PaperG group insufficient precision of documentation times limited analysis. The use of old BG measurements was clinically less relevant. ConclusionInsulin dosing errors and workflow deviations led to measurable changes in clinical outcome. Diabetes management systems including decision support should address nurses as well as physicians in a computerized way. Our analysis shows that such systems reduce the frequency of errors and therefore decrease the probability of hypo- and hyperglycemia.

DAS: Personal Diabetes Management System

In this study we have presented the design and implementation of a Diabetes Assistant System (DAS) which is able to store and manage the diabetic patient's medical data. DAS (Diabetes Assistance System) is developed after studying several well-known existing diabetes management systems and includes many features that were not available in past. In addition to this many features of existing systems are redesigned for more productivity and effective disease management. DAS not only facilitates diabetic patients to manage their lifestyles but it also provides functionalities for medical practitioners and support staff for disease management features. DAS supports core features of user management, disease management, visit management and extended features for socialization. DAS is developed by focusing users' needs of mobility and ease of access hence available as web-based and mobile-based diabetes management system. DAS enables doctors to support patients remotely and view their disease history. Moreover, a doctor can manage his/her personal profile and daily schedule of online availability. Patients can manage their profiles, daily activities, test results, medications, foods intakes and appointments. In addition to this, patients can view their disease history, doctor's schedule and health tips. The support staff manages disease related information like medicines, manufacturers, tests, foods and exercises data. In addition they can view/manage doctor's schedule and appointments.

Expansion of Electronic Health Record-Based Screening, Prevention, and Management of Diabetes in New York City

To address the increasing burden of diabetes in New York City, we designed 2 electronic health records (EHRs)-facilitated diabetes management systems to be implemented in 6 primary care practices on the West Side of Manhattan, a standard system and an enhanced system. The standard system includes screening for diabetes. The enhanced system includes screening and ensures close patient follow-up; it applies principles of the chronic care model, including community–clinic linkages, to the management of patients newly diagnosed with diabetes and prediabetes through screening. We will stagger implementation of the enhanced system across the 6 clinics allowing comparison, through a quasi-experimental design (pre–post difference with a control group), of patients treated in the enhanced system with similar patients treated in the standard system. The findings could inform health system practices at multiple levels and influence the integration of community resources into routine diabetes care.

Are information technology-based systems the way forward for diabetes management in Asia?

Are information technology-based systems the way forward for diabetes management in Asia?

Could mobile diabetes management systems revolutionize patient care?

181 ISSN 1758-1907 10.2217/DMT.12.14 © 2012 Future Medicine Ltd Diabetes Manage. (2012) 2(3), 181–183 Living healthily with diabetes often means following a strict regime of frequent blood glucose measurements, diet control and regular physical activity. Most people living with diabetes know this, however, in one’s busy everyday life it is hard to meet this best practice standard for diabetes self-management. Some key elements for diabetes management are:

Self-monitoring of blood glucose

Self-monitoring of blood glucose

Designing mobile support for glycemic control in patients with diabetes

We assessed the feasibility and acceptability of using mobile phones as part of an existing Web-based system for collaboration between patients with diabetes and a primary care team. In design sessions, we tested mobile wireless glucose meter uploads and two approaches to mobile phone-based feedback on glycemic control. Mobile glucose meter uploads combined with graphical and tabular data feedback were the most desirable system features tested. Participants had a mixture of positive and negative reactions to an automated and tailored messaging feedback system for self-management support. Participants saw value in the mobile system as an adjunct to the Web-based program and traditional office-based care. Mobile diabetes management systems may represent one strategy to improve the quality of diabetes care.

Ubiquitous Diabetes Management System via Interactive Communication Based on Information Technologies: Clinical Effects and Perspectives.

New diabetes management systems based on interactive communication have been introduced recently, accompanying rapid advances in information technology; these systems are referred to as "ubiquitous diabetes management systems." In such ubiquitous systems, patients and medical teams can communicate via Internet or telecommunications, with patients uploading their glucose data and personal information, and medical teams sending optimal feedback. Clinical evidence from both long-term and short-term trials has been reported by some researchers. Such systems appear to be effective not only in reducing the levels of HbA1c but also in stabilizing glucose control. However, most notably, evidence for the cost-effectiveness of such a system should be demonstrated before it can be propagated out to the general population in actual clinical practice. To establish a cost-effective model, various types of clinical decision supporting software designed to reduce the labor time of physicians must first be developed. A number of sensors and devices for monitoring patients' data are expected to be available in the near future; thus, methods for automatic interconnections between devices and web charts were also developed. Further investigations to demonstrate the clinical outcomes of such a system should be conducted, hopefully leading to a new paradigm of diabetes management.