Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Monday, March 11, 2019 at 4:00 PM to 4:30 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Advertisement

Journal Description

JMIR Diabetes (JD, Editor-in-Chief: Caroline Richardson) is a Pubmed journal of JMIR the leading open-access journal in health informatics. JMIR Diabetes focuses on technologies, medical devices, apps, engineering, informatics and patient education for diabetes prevention, self-management, care, and cure, to help people with diabetes.

As open access journal JD is read by clinicians and patients alike and have (as all JMIR journals) a focus on readable and applied science reporting the design and evaluation of health innovations and emerging technologies, as well as on diabetes prevention and epidemiology.

We publish original research, viewpoints, and reviews (both literature reviews and medical device/technology/app reviews) covering for example wearable devices and trackers, mobile apps, glucose monitoring (including emerging technologies such as Google contact lens), medical devices for insulin and metabolic peptide delivery, closed loop systems and artificial pancreas, telemedicine, web-based diabetes education and elearning, innovations for patient self-management and "quantified self", diabetes-specific EHR improvements, clinical or consumer-focused software, diabetes epidemiology and surveillance, crowdsourcing and quantified self-based research data, new sensors and actuators to be applied to diabetes.

 

Recent Articles:

  • Source: Freepik; Copyright: Tongcom; URL: https://www.freepik.com/premium-photo/woman-hands-using-mobile-smart-phone_3678796.htm; License: Licensed by the authors.

    Health App Use and Its Correlates Among Individuals With and Without Type 2 Diabetes: Nationwide Population-Based Survey

    Abstract:

    Background: Evidence suggests that mobile health app use is beneficial for the prevention and management of type 2 diabetes (T2D) and its associated complications; however, population-based research on specific determinants of health app use in people with and without T2D is scarce. Objective: This cross-sectional study aimed to provide population-based evidence on rates and determinants of health app use among adults with and without T2D, thereby covering a prevention perspective and a diabetes management perspective, respectively. Methods: The study population included 2327 adults without a known diabetes diagnosis and 1149 adults with known T2D from a nationwide telephone survey in Germany conducted in 2017. Rates of smartphone ownership and health app use were estimated based on weighted sample proportions. Among smartphone owners, determinants of health app use were identified for both groups separately in multivariable logistic regression models. Sociodemographic factors, diabetes-related factors or indicators, psychological and health-related factors, and physician-provided information were selected as potential determinants. Results: Among participants without known diabetes, 74.72% (1690/2327) were smartphone owners. Of those, 49.27% (717/1690) used health apps, most often to improve regular physical activity. Among participants with T2D, 42.26% (481/1149) were smartphone owners. Of those, 41.1% (171/481) used health apps, most commonly to target a healthy diet. Among people without known diabetes, determinants significantly (all P values <.05) associated with an increased likelihood of health app use compared with their reference group were as follows: younger and middle age of 18 to 44 or 45 to 64 years (odds ratios [ORs] 3.89; P<.001 and 1.76; P=.004, respectively), overweight or obesity (ORs 1.58; P<.001 and 2.07; P<.001, respectively), hypertension diagnosis (OR 1.31; P=.045), former or current smoking (ORs 1.51; P=.002 and 1.58; P<.001, respectively), perceiving health as very good (OR 2.21; P<.001), other chronic diseases (OR 1.48; P=.002), and having received health advice from a physician (OR 1.48; P<.001). A slight or high perceived diabetes risk (ORs 0.78; P=.04 and 0.23; P<.001, respectively) was significantly associated with a decreased likelihood of health app use. Among people with T2D, younger and middle age (18-64 years; OR 1.84; P=.007), female gender (OR 1.61; P=.02), and using a glucose sensor in addition or instead of a glucose meter (OR 2.74; P=.04) were significantly positively associated with health app use. Conclusions: In terms of T2D prevention, age, diabetes-related risk factors, psychological and health-related factors, and medical health advice may inform app development for specific target groups. In addition, health professionals may encourage health app use when giving advice on health behaviors. Concerning T2D management, only a few determinants seem relevant for explaining health app use among people with T2D, indicating a need for more future research on which people with T2D use health apps and why.

  • Source: Image created by the Authors; Copyright: The Authors; URL: http://diabetes.jmir.org/2020/2/e19581/; License: Creative Commons Attribution (CC-BY).

    The Challenges of COVID-19 for People Living With Diabetes: Considerations for Digital Health

    Abstract:

    The coronavirus disease (COVID-19) is a global pandemic that significantly impacts people living with diabetes. Diabetes-related factors of glycemic control, medication pharmacodynamics, and insulin access can impact the severity of a COVID-19 infection. In this commentary, we explore how digital health can support the diabetes community through the pandemic. For those living with diabetes, digital health presents the opportunity to access care with greater convenience while not having to expose themselves to infection in an in-person clinic. Digital diabetes apps can increase agency in self-care and produce clinically significant improvement in glycemic control through facilitating the capture of diabetes device data. However, the ability to share these data back to the clinic to inform virtual care and enhance diabetes coaching and guidance remains a challenge. In the end, it requires an unnecessarily high level of technical sophistication on the clinic’s part and on those living with diabetes to routinely use their diabetes device data in clinic visits, virtual or otherwise. As the world comes together to fight the COVID-19 pandemic, close collaboration among the global diabetes community is critical to understand and manage the sustained impact of the pandemic on people living with diabetes.

  • Reader at telescreening platform. Source: The Authors; Copyright: The Authors; URL: https://diabetes.jmir.org/2020/2/e17309; License: Creative Commons Attribution (CC-BY).

    Assessment of Training Outcomes of Nurse Readers for Diabetic Retinopathy Telescreening: Validation Study

    Abstract:

    Background: With the high prevalence of diabetic retinopathy and its significant visual consequences if untreated, timely identification and management of diabetic retinopathy is essential. Teleophthalmology programs have assisted in screening a large number of individuals at risk for vision loss from diabetic retinopathy. Training nonophthalmological readers to assess remote fundus images for diabetic retinopathy may further improve the efficiency of such programs. Objective: This study aimed to evaluate the performance, safety implications, and progress of 2 ophthalmology nurses trained to read and assess diabetic retinopathy fundus images within a hospital diabetic retinopathy telescreening program. Methods: In this retrospective interobserver study, 2 ophthalmology nurses followed a specific training program within a hospital diabetic retinopathy telescreening program and were trained to assess diabetic retinopathy images at 2 levels of intervention: detection of diabetic retinopathy (level 1) and identification of referable disease (level 2). The reliability of the assessment by level 1−trained readers in 266 patients and of the identification of patients at risk of vision loss from diabetic retinopathy by level 2−trained readers in 559 more patients were measured. The learning curve, sensitivity, and specificity of the readings were evaluated using a group consensus gold standard. Results: An almost perfect agreement was measured in identifying the presence of diabetic retinopathy in both level 1 readers (κ=0.86 and 0.80) and in identifying referable diabetic retinopathy by level 2 readers (κ=0.80 and 0.83). At least substantial agreement was measured in the level 2 readers for macular edema (κ=0.79 and 0.88) for all eyes. Good screening threshold sensitivities and specificities were obtained for all level readers, with sensitivities of 90.6% and 96.9% and specificities of 95.1% and 85.1% for level 1 readers (readers A and B) and with sensitivities of 86.8% and 91.2% and specificities of 91.7% and 97.0% for level 2 readers (readers A and B). This performance was achieved immediately after training and remained stable throughout the study. Conclusions: Notwithstanding the small number of trained readers, this study validates the screening performance of level 1 and level 2 diabetic retinopathy readers within this training program, emphasizing practical experience, and allows the establishment of an ongoing assessment clinic. This highlights the importance of supervised, hands-on experience and may help set parameters to further calibrate the training of diabetic retinopathy readers for safe screening programs.

  • Low Carb Program. Source: https://www.lowcarbprogram.com; Copyright: Low Carb Program; License: Licensed by the authors.

    Novel Digital Architecture of a “Low Carb Program” for Initiating and Maintaining Long-Term Sustainable Health-Promoting Behavior Change in Patients with...

    Abstract:

    Globally, the burden of noncommunicable diseases such as type 2 diabetes is crippling health care systems. Type 2 diabetes, a disease linked with obesity, affects 1 in every 30 people today and is expected to affect 1 in 10 people by 2030. Current provisions are struggling to manage the trajectory of type 2 diabetes prevalence. Offline, face-to-face education for patients with type 2 diabetes has shown to lack long-term impact or the capacity for widespread democratized adoption. Digitally delivered interventions have been developed for patients with type 2 diabetes, and the evidence shows that some interventions provide the capacity to support hyperpersonalization and real-time continuous support to patients, which can result in significant engagement and health outcomes. However, digital health app engagement is notoriously difficult to achieve. This paper reviews the digital behavior change architecture of the Low Carb Program and the application of health behavioral theory underpinning its development and use in scaling novel methods of engaging the population with type 2 diabetes and supporting long-term behavior change.

  • Source: freepik; Copyright: freepik; URL: https://www.freepik.com/free-photo/hands-holding-phone-with-twitter-laptop_1208839.htm#page=3&query=twitter&position=3; License: Licensed by JMIR.

    Using Social Media to Track Geographic Variability in Language About Diabetes: Infodemiology Analysis

    Abstract:

    Background: Social media posts about diabetes could reveal patients’ knowledge, attitudes, and beliefs as well as approaches for better targeting of public health messages and care management. Objective: This study aimed to characterize the language of Twitter users’ posts regarding diabetes and describe the correlation of themes with the county-level prevalence of diabetes. Methods: A retrospective study of diabetes-related tweets identified from a random sample of approximately 37 billion tweets from the United States from 2009 to 2015 was conducted. We extracted diabetes-specific tweets and used machine learning to identify statistically significant topics of related terms. Topics were combined into themes and compared with the prevalence of diabetes by US counties and further compared with geography (US Census Divisions). Pearson correlation coefficients are reported for each topic and relationship with prevalence. Results: A total of 239,989 tweets from 121,494 unique users included the term diabetes. The themes emerging from the topics included unhealthy food and drink, treatment, symptoms/diagnoses, risk factors, research, recipes, news, health care, management, fundraising, diet, communication, and supplements/remedies. The theme of unhealthy foods most positively correlated with geographic areas with high prevalence of diabetes (r=0.088), whereas tweets related to research most negatively correlated (r=−0.162) with disease prevalence. Themes and topics about diabetes differed in overall frequency across the US geographical divisions, with the East South Central and South Atlantic states having a higher frequency of topics referencing unhealthy food (r range=0.073-0.146; P<.001). Conclusions: Diabetes-related tweets originating from counties with high prevalence of diabetes have different themes than tweets originating from counties with low prevalence of diabetes. Interventions could be informed from this variation to promote healthy behaviors.

  • Source: The Authors / Placeit; Copyright: The Authors; URL: http://diabetes.jmir.org/2020/1/e15189/; License: Licensed by JMIR.

    Effectiveness of a Digital Lifestyle Change Program in Obese and Type 2 Diabetes Populations: Service Evaluation of Real-World Data

    Abstract:

    Background: The prevalence of type 2 diabetes mellitus (T2DM) and obesity is increasing, and the way people interact with health care is evolving. People traditionally access advice and support to improve their lifestyle and learn more about the self-management of T2DM in a face-to-face setting. Although these services have a strong evidence base, they have limitations for reaching specific groups of people. Digital programs could provide a new delivery model to help more people access health education and behavior change support, but long-term data supporting these programs are limited. Objective: The purpose of this service evaluation was to analyze the weight change of people who participated in OurPath (also known as Second Nature), a UK-based digital lifestyle change program, for either weight management or diabetes-related weight management and structured education at 6 and 12 months. Methods: Participants either paid to access the program privately (self-funded clients) or were referred by their general practitioner to participate in the program free of charge (funded by the National Health Service). Additional follow-up support was provided to help people to maintain lifestyle changes. To retrospectively assess potential weight loss, the analysis included data from participants who submitted weight readings at baseline and 6 and 12 months after starting the program. Changes in weight after 6 and 12 months were primary outcome measures. Results: For the 896 participants who submitted baseline and 6- and 12-month data, a significant change in mean weight of −7.12 kg (−7.50%; SD 6.37; P<.001) was observed at 6 months. Data from the same participants at 12 months showed a change in mean weight when compared with a baseline of −6.14 kg (−6.48%; SD 6.97; P<.001). Conclusions: The data presented here had several limitations, and there were too many uncertainties to make any reliable conclusions. However, these results suggest that digital lifestyle change programs could provide a new way to help people to access nutritional advice and support to achieve weight loss. Further research into digital education and coaching platforms is needed to establish their effectiveness.

  • Source: The Authors / Placeit; Copyright: JMIR Publications; URL: http://diabetes.jmir.org/2020/1/e15744/; License: Creative Commons Attribution (CC-BY).

    Feasibility, Acceptability, and Impact of a Web-Based Structured Education Program for Type 2 Diabetes: Real-World Study

    Abstract:

    Background: Structured education for people with type 2 diabetes improves outcomes, but uptake is low globally. In the United Kingdom in 2016, only 8.3% of people who were referred to education programs attended the program. We have developed a Web-based structured education program named Healthy Living for People with type 2 Diabetes (HeLP-Diabetes): Starting Out (HDSO), as an alternative to face-to-face courses. A Web-based program gives people more options for accessing structured education and may help improve overall uptake. Objective: The aim was to explore the feasibility and acceptability of delivering a Web-based structured education program (named HeLP-Diabetes: Starting Out) in routine primary health care and its potential impact on self-efficacy and diabetes-related distress. Methods: HDSO was delivered as part of routine diabetes services in primary health care in the United Kingdom, having been commissioned by local Clinical Commissioning Groups. Quantitative data were collected on uptake, use of the program, demographic characteristics, self-reported self-efficacy, and diabetes-related distress. A subsample of people with type 2 diabetes and health care professionals were interviewed about acceptability of the program. Results: It was feasible to deliver the program, but completion rates were low: of 791 people with type 2 diabetes registered, only 74 (9.0%) completed it. Completers improved their self-efficacy (change in median score 2.5, P=.001) and diabetes-related distress (change in median score 6.0, P=.001). Interview data suggested that the course was acceptable, and that uptake and completion may be related to nonprioritization of structured education. Conclusions: The study provides evidence of the feasibility and acceptability of a Web-based structured education. However, uptake and completion rates were low, limiting potential population impact. Further research is needed to improve completion rates, and to determine the relative effectiveness of Web-based versus face-to-face education.

  • Source: Freepik; Copyright: pch.vector; URL: https://www.freepik.com/free-photo/happy-expectant-mom-with-tablet-relaxing-bedroom_6101343.htm#page=2&query=pregnant+woman&position=6; License: Licensed by JMIR.

    Understanding the Adoption and Diffusion of a Telemonitoring Solution in Gestational Diabetes Mellitus: Qualitative Study

    Authors List:

    Abstract:

    Background: Women with gestational diabetes mellitus (GDM) require regular follow-ups and overall management to normalize maternal blood glucose and improve pregnancy outcomes. With the advancements made in the digital field, telemedicine is gaining popularity over traditional health care approaches in different medical fields. As for GDM, telemonitoring solutions seem to improve women’s quality of life and enhance self-management. Objective: The aim of this study is to understand, from patients’ and health care professionals’ (HCPs) perspectives, what drives the adoption and diffusion of a telemonitoring solution (myDiabby) in a context where telemonitoring activities are still not compensated like traditional follow-ups. Methods: The study was conducted in 12 diabetes services in France using myDiabby for monitoring and managing patients with GDM. A qualitative research approach was adopted for collecting and analyzing data. A total of 20 semistructured interviews were conducted with HCPs working in different health structures in France, and 15 semistructured interviews were conducted with patients who had been using myDiabby. Data were analyzed using a thematic analysis approach. Results: Different determinants need to be taken into consideration when adopting an innovative health technology. By drawing on the diffusion of innovation theory, a set of factors associated with the technology (the relative advantages, compatibility, ease of use, testability, and observability of the telemedicine platform) has been identified as affecting the adoption and diffusion of telemonitoring solutions in French diabetes services. In addition, data analysis shows a set of environmental factors (the demographic situation of HCPs, the health care access in rural communities, and the economic and political context in France) that also influences the spread and adoption of telemonitoring systems in French hospitals. Conclusions: Even though telemonitoring activities are still not remunerated as traditional follow-ups, many French HCPs support and encourage the adoption of telemonitoring systems in GDM. As for patients, telemonitoring systems are perceived as a useful and easy way to monitor their GDM. This study contributes to recognizing the value of telemonitoring interventions in managing GDM and considering the expansion of telemonitoring to other chronic conditions.

  • Source: The Authors; Copyright: Livongo; URL: https://www.livongo.com/docs/press-images/LivongoMeter2.jpg; License: Licensed by JMIR.

    The Effect of a Cellular-Enabled Glucose Meter on Glucose Control for Patients With Diabetes: Prospective Pre-Post Study

    Abstract:

    Background: Diabetes is a global epidemic affecting approximately 30 million people in the United States. The World Health Organization recommends using technology and telecommunications to improve health care delivery and disease management. The Livongo for Diabetes Program offers a remote monitoring technology with Certified Diabetes Educator outreach. Objective: The purpose of this study was to examine health outcomes measured by changes in HbA1c, time in target blood glucose range, and depression symptoms for patients enrolled in a remote digital diabetes management program in a Diabetes Center of Excellence setting. Methods: The impact of the Livongo for Diabetes Program on Hemoglobin A1c (HbA1c), blood glucose ranges, and depression screening survey results (Patient Health Questionnaire-2) were assessed over 12 months in a prospective cohort recruited from the University of South Florida Health Diabetes Home for Healthy Living. Any patient >18 years old with a diagnosis of diabetes was approached for voluntary inclusion into the program. The analysis was a pre-post design for those members enrolled in the study. Data was collected at outpatient clinic visits and remotely through the Livongo glucose meter. Results: A total of 86 adults were enrolled into the Livongo for Diabetes program, with 49% (42/86) female, an average age of 50 (SD 15) years, 56% (48/86) with type 2 diabetes mellitus, and 69% (59/86) with insulin use. The mean HbA1c drop amongst the group was 0.66% (P=.17), with all participants showing a decline in HbA1c at 12 months. A 17% decrease of blood glucose checks <70 mg/dL occurred concurrently. Participants with type 2 diabetes not using insulin had blood glucose values within target range (70-180 mg/dL) 89% of the time. Participants with type 2 diabetes using insulin were in target range 68% of the time, and type 1 diabetes 58% of the time. Average PHQ-2 scores decreased by 0.56 points during the study period. Conclusions: Participants provided with a cellular-enabled blood glucose meter with real-time feedback and access to coaching from a certified diabetes educator in an outpatient clinical setting experienced improved mean glucose values and fewer episodes of hypoglycemia relative to the start of the program.

  • Mobile phone. Source: Flickr; Copyright: Ken Banks, kiwanja.net; URL: https://www.flickr.com/photos/kiwanja/3170277538/in/album-72157612134575211/; License: Creative Commons Attribution (CC-BY).

    Acceptability of Mobile Health Interventions to Increase Diabetic Risk Factor Awareness Among the Commuter Population in Johannesburg: Descriptive...

    Abstract:

    Background: Developing countries are experiencing a shift from infectious diseases such as HIV and tuberculosis to noncommunicable diseases (NCDs) such as diabetes. Diabetes accounts for more disability-adjusted life years than any other NCD in South Africa, and research has identified a number of preventable risk factors; however, there is not enough evidence from lower resource settings as to how best to disseminate this information to the population. Today, 90% of the world’s population lives in mobile phone coverage areas, and this provides a unique opportunity to reach large populations with health information. Objective: This study aimed to investigate how potential mobile health (mHealth) platforms should be paired with diabetes risk factor education so that at-risk communities are empowered with information to prevent and manage diabetes. Methods: A Likert-style survey was distributed to commuters in the City of Johannesburg in July 2018 that explored participants’ background characteristics as well as their knowledge and awareness surrounding diabetic risk factors (such as exercise, smoking, and hypertension) and their comfort level with various information delivery methods (such as WhatsApp, short message service, and email). The grouped variables from diabetic risk factors and information delivery methods were described with mean Likert scores and then investigated for relationships with Spearman Rho correlation coefficients. Results: Background characteristics revealed that the self-reported prevalence of diabetes was twice as high in this studied commuter population than the national average. WhatsApp was the most favorable mHealth information delivery method and had a moderate correlation coefficient with diet and nutrition (0.338; P<.001) as well as a weaker correlation with physical activity (0.243; P<.001). Although not as robust as the WhatsApp correlations, each of the other information delivery methods also showed weaker, yet statistically significant, relationships with one or more of the risk factors. Conclusions: The elevated self-reported diabetes prevalence reinforces the need for diabetes risk factor education in the studied commuter population of Johannesburg. The most feasible mHealth intervention for diabetic risk factor education should focus on WhatsApp messaging while also offering content across other mHealth and traditional platforms to remove barriers to access and enhance the user experience. The content should emphasize diet and nutrition as well as physical activity while also incorporating information on secondary risk factors.

  • Brainstorm session. Source: GoodFreePhotos.com; Copyright: Kaboompics; URL: https://www.goodfreephotos.com/business-and-technology/collaborating-on-a-business-project.jpg.php; License: Public Domain (CC0).

    Digital Person-Centered Self-Management Support for People With Type 2 Diabetes: Qualitative Study Exploring Design Challenges

    Abstract:

    Background: Self-management is a substantial part of treatment for patients with type 2 diabetes (T2D). Modern digital technology, being small, available, and ubiquitous, might work well in supporting self-management. This study follows the process of developing a pilot implementation of an electronic health (eHealth) service for T2D self-management support in primary health care. The use of digital health, or eHealth, solutions for supporting self-management for patients with T2D is increasing. There are good examples of successful implementations that can serve as guides in the development of new solutions. However, when adding person-centered principles as a requirement, the examples are scarce. Objective: The objective of this study was to explore challenges that could impact the design of a person-centered eHealth service for T2D self-management support. The study included data collection from multiple sources, that is, interviews, observations, focus groups, and a Mentimeter (interactive presentation with polling) survey among stakeholders, representing various perspectives of T2D. Methods: A user-centered design approach was used to exploratively collect data from different sources. Data were collected from a workshop, interviews, and observations. The different data sources enabled a triangulation of data. Results: Results show that user needs related to an eHealth service for person-centered T2D self-management support are multifaceted and situated in a complex context. The two main user groups, patients and diabetes specialist nurses, express needs that both diverge and converge, which indicates that critical design decisions have to be made. There is also a discrepancy between the needs expressed by the potential users and the current work practice, suggesting more attention toward changing the organization of work to fully support a new eHealth service. Conclusions: A total of three overarching challenges—flexible access, reducing administrative tasks, and patient empowerment—each having a significant impact on design, are discussed. These challenges need to be considered and resolved through careful design decisions. Special attention has to be given to the patient user group that could greatly impact current work practice and power structures at the primary care unit. A need for further studies investigating patient needs in everyday life is identified to better support the implementation of technology that does not give specific attention to organizational perspectives but instead approach design with the patient perspective in focus.

  • Source: freepik; Copyright: jcomp; URL: https://www.freepik.com/free-photo/old-lady-is-testing-blood-sugar-level-using-blood-sugar-test-kid-set_5192594.htm#page=1&query=diabetes&position=27; License: Licensed by JMIR.

    A Reinforcement Learning–Based Method for Management of Type 1 Diabetes: Exploratory Study

    Abstract:

    Background: Type 1 diabetes mellitus (T1DM) is characterized by chronic insulin deficiency and consequent hyperglycemia. Patients with T1DM require long-term exogenous insulin therapy to regulate blood glucose levels and prevent the long-term complications of the disease. Currently, there are no effective algorithms that consider the unique characteristics of T1DM patients to automatically recommend personalized insulin dosage levels. Methods: This research presents a model-free data-driven RL algorithm, namely Q-learning, that recommends insulin doses to regulate the blood glucose level of a T1DM patient, considering his or her state defined by glycated hemoglobin (HbA1c) levels, body mass index, engagement in physical activity, and alcohol usage. In this approach, the RL agent identifies the different states of the patient by exploring the patient’s responses when he or she is subjected to varying insulin doses. On the basis of the result of a treatment action at time step t, the RL agent receives a numeric reward, positive or negative. The reward is calculated as a function of the difference between the actual blood glucose level achieved in response to the insulin dose and the targeted HbA1c level. The RL agent was trained on 10 years of clinical data of patients treated at the Mass General Hospital. Results: A total of 87 patients were included in the training set. The mean age of these patients was 53 years, 59% (51/87) were male, 86% (75/87) were white, and 47% (41/87) were married. The performance of the RL agent was evaluated on 60 test cases. RL agent–recommended insulin dosage interval includes the actual dose prescribed by the physician in 53 out of 60 cases (53/60, 88%). Conclusions: This exploratory study demonstrates that an RL algorithm can be used to recommend personalized insulin doses to achieve adequate glycemic control in patients with T1DM. However, further investigation in a larger sample of patients is needed to confirm these findings.

Citing this Article

Right click to copy or hit: ctrl+c (cmd+c on mac)

Latest Submissions Open for Peer-Review:

There are no articles available for open peer-review at this time. Please check back later.

Advertisement