Engagement and Outcomes Associated with Contextual Annotation Features of a Digital Health Solution.

BACKGROUND: Digital health solutions targeting diabetes self-care are popular and promising, but important questions remain about how these tools can most effectively help patients. Consistent with evidence of the salutary effects of note-taking in education, features that enable annotation of structured data entry might enhance the meaningfulness of the interaction, thereby promoting persistent use and benefits of a digital health solution. METHOD: To examine the potential benefits of note-taking, we explored how patients with type 2 diabetes used annotation features of a digital health solution and assessed the relationship between annotation and persistence in engagement as well as improvements in glycated hemoglobin (A1C). Secondary data from 3142 users of the BlueStar digital health solution collected between December 2013 and June 2017 were analyzed, with a subgroup of 372 reporting A1C lab values. RESULTS: About a third of patients recorded annotations while using the platform. Annotation themes largely reflected self-management behaviors (diet, physical activity, medication adherence) and well-being (mood, health status). Early use of contextual annotations was associated with greater engagement over time and with greater improvements in A1C. CONCLUSIONS: Our research provides preliminary evidence of the benefits of annotation features in a digital health solution. Future research is needed to assess the causal impact of note-taking and the moderating role of thematic content reflected in notes.

A New Taxonomy for Technology-Enabled Diabetes Self-Management Interventions: Results of an Umbrella Review.

BACKGROUND: A 2017 umbrella review defined the technology-enabled self-management (TES) feedback loop associated with a significant reduction in A1C. The purpose of this 2021 review was to develop a taxonomy of intervention attributes in technology-enabled interventions; review recent, high-quality systematic reviews and meta-analyses to determine if the TES framework was described and if elements contribute to improved diabetes outcomes; and to identify gaps in the literature. METHODS: We identified key technology attributes needed to describe the active ingredients of TES interventions. We searched multiple databases for English language reviews published between April 2017 and April 2020, focused on PwD (population) receiving diabetes care and education (intervention) using technology-enabled self-management (comparator) in a randomized controlled trial, that impact glycemic, behavioral/psychosocial, and other diabetes self-management outcomes. AMSTAR-2 guidelines were used to assess 50 studies for methodological quality including risk of bias. RESULTS: The TES Taxonomy was developed to standardize the description of technology-enabled interventions; and ensure research uses the taxonomy for replication and evaluation. Of the 26 included reviews, most evaluated smartphones, mobile applications, texting, internet, and telehealth. Twenty-one meta-analyses with the TES feedback loop significantly lowered A1C. CONCLUSIONS: Technology-enabled diabetes self-management interventions continue to be associated with improved clinical outcomes. The ongoing rapid adoption and engagement of technology makes it important to focus on uniform measures for behavioral/psychosocial outcomes to highlight healthy coping. Using the TES Taxonomy as a standard approach to describe technology-enabled interventions will support understanding of the impact technology has on diabetes outcomes.

Complementarity of Digital Health and Peer Support: "This Is What's Coming".

Purpose: This study examined integration of peer support and a Food and Drug Administration-cleared, diabetes management app (DMA) in diabetes self-management support as a scalable model for those with type 2 diabetes mellitus (T2DM). Methods: Two lay health Coaches delivered telephone-based self-management support to adults (N = 43) with T2DM recruited through a primary group practice. Those eligible were offered no-cost access to DMA for the entire 6-month study. Coaches introduced DMA and contacted individuals by phone and text with frequency dependent on participant needs/preferences. DMA supported monitoring of blood glucose, carbohydrate intake, and medication use, as well as messaging personalized to participants' medication regimens. Clinical data were extracted from DMA, electronic medical records, and Coaches' records. Structured interviews of 12 participants, 2 Coaches, and 5 project staff were analyzed using deductive pre-identified codes (regarding adoptability, patterns of use, value added, complementarity, and sustainability) utilizing standard procedures for qualitative analysis. Results: Of the 43 participants, 38 (88.4%) enrolled in DMA. In general, participants used both DMA and lay health coaches, averaging 144.14 DMA entries (structured, e.g., medications, and free form, e.g., "ate at a restaurant" and "stressed") and 5.86 coach contacts over the 6-month intervention. Correlation between DMA entries and coach contacts (r = .613, p < 0.001) was consistent with complementarity as were participants' and coaches' observations that (a) DMA facilitated recognition of patterns and provided reminders and suggestions to achieve self-management plans, whereas (b) coaching provided motivation and addressed challenges that emerged. Mean hemoglobin A1c (A1c) declined from 9.93% to 8.86% (p < 0.001), with no pattern of coaching or DMA use significantly related to reductions. Staff identified resources to coordinate coach/DMA interventions as a major sustainability challenge. Conclusions: DMA and peer support for diabetes management are compatible and complementary. Additional practice integration research is needed for adoption and scale-up.

A Framework for Optimizing Technology-Enabled Diabetes and Cardiometabolic Care and Education: The Role of the Diabetes Care and Education Specialist.

PURPOSE: The purpose of this article is to present a framework for optimizing technology-enabled diabetes and cardiometabolic care and education using a standardized approach. This approach leverages the expertise of the diabetes care and education specialist, the multiplicity of technologies, and integration with the care team. Technology can offer increased opportunity to improve health outcomes while also offering conveniences for people with diabetes and cardiometabolic conditions. The adoption and acceptance of technology is crucial to recognize the full potential for improving care. Understanding and incorporating the perceptions and behaviors associated with technology use can prevent a fragmented health care experience. CONCLUSION: Diabetes care and education specialists (DCES) have a history of utilizing technology and data to deliver care and education when managing chronic conditions. With this unique skill set, DCES are strategically positioned to provide leadership to develop and deliver technology-enabled diabetes and cardiometabolic health services in the rapidly changing healthcare environment.

A Systematic Review of Reviews Evaluating Technology-Enabled Diabetes Self-Management Education and Support.

BACKGROUND: Since the introduction of mobile phones, technology has been increasingly used to enable diabetes self-management education and support. This timely systematic review summarizes how currently available technology impacts outcomes for people living with diabetes. METHODS: A systematic review of high quality review articles and meta analyses focused on utilizing technology in diabetes self-management education and support services was conducted. Articles were included if published between January 2013 and January 2017. RESULTS: Twenty-five studies were included for analysis. The majority evaluated the use of mobile phones and secure messaging. Most studies described healthy eating, being active and metabolic monitoring as the predominant self-care behaviors evaluated. Eighteen of 25 reviews reported significant reduction in A1c as an outcome measure. Four key elements emerged as essential for improved A1c: (1) communication, (2) patient-generated health data, (3) education, and (4) feedback. CONCLUSION: Technology-enabled diabetes self-management solutions significantly improve A1c. The most effective interventions incorporated all the components of a technology-enabled self-management feedback loop that connected people with diabetes and their health care team using 2-way communication, analyzed patient-generated health data, tailored education, and individualized feedback. The evidence from this systematic review indicates that organizations, policy makers and payers should consider integrating these solutions in the design of diabetes self-management education and support services for population health and value-based care models. With the widespread adoption of mobile phones, digital health solutions that incorporate evidence-based, behaviorally designed interventions can improve the reach and access to diabetes self-management education and ongoing support.

Evidence-Based mHealth Chronic Disease Mobile App Intervention Design: Development of a Framework.

BACKGROUND: Mobile technology offers new capabilities that can help to drive important aspects of chronic disease management at both an individual and population level, including the ability to deliver real-time interventions that can be connected to a health care team. A framework that supports both development and evaluation is needed to understand the aspects of mHealth that work for specific diseases, populations, and in the achievement of specific outcomes in real-world settings. This framework should incorporate design structure and process, which are important to translate clinical and behavioral evidence, user interface, experience design and technical capabilities into scalable, replicable, and evidence-based mobile health (mHealth) solutions to drive outcomes. OBJECTIVE: The purpose of this paper is to discuss the identification and development of an app intervention design framework, and its subsequent refinement through development of various types of mHealth apps for chronic disease. METHODS: The process of developing the framework was conducted between June 2012 and June 2014. Informed by clinical guidelines, standards of care, clinical practice recommendations, evidence-based research, best practices, and translated by subject matter experts, a framework for mobile app design was developed and the refinement of the framework across seven chronic disease states and three different product types is described. RESULTS: The result was the development of the Chronic Disease mHealth App Intervention Design Framework. This framework allowed for the integration of clinical and behavioral evidence for intervention and feature design. The application to different diseases and implementation models guided the design of mHealth solutions for varying levels of chronic disease management. CONCLUSIONS: The framework and its design elements enable replicable product development for mHealth apps and may provide a foundation for the digital health industry to systematically expand mobile health interventions and validate their effectiveness across multiple implementation settings and chronic diseases.

Hypoglycemia prediction using machine learning models for patients with type 2 diabetes.

Minimizing the occurrence of hypoglycemia in patients with type 2 diabetes is a challenging task since these patients typically check only 1 to 2 self-monitored blood glucose (SMBG) readings per day. We trained a probabilistic model using machine learning algorithms and SMBG values from real patients. Hypoglycemia was defined as a SMBG value < 70 mg/dL. We validated our model using multiple data sets. In addition, we trained a second model, which used patient SMBG values and information about patient medication administration. The optimal number of SMBG values needed by the model was approximately 10 per week. The sensitivity of the model for predicting a hypoglycemia event in the next 24 hours was 92% and the specificity was 70%. In the model that incorporated medication information, the prediction window was for the hour of hypoglycemia, and the specificity improved to 90%. Our machine learning models can predict hypoglycemia events with a high degree of sensitivity and specificity. These models-which have been validated retrospectively and if implemented in real time-could be useful tools for reducing hypoglycemia in vulnerable patients.

Integration of a mobile-integrated therapy with electronic health records: lessons learned.

BACKGROUND: Responses to the chronic disease epidemic have predominantly been standardized in their approach to date. Barriers to better health outcomes remain, and effective management requires patient-specific data and disease state knowledge be presented in methods that foster clinical decision-making and patient self-management. Mobile technology provides a new platform for data collection and patient-provider communication. The mobile device represents a personalized platform that is available to the patient on a 24/7 basis. Mobile-integrated therapy (MIT) is the convergence of mobile technology, clinical and behavioral science, and scientifically validated clinical outcomes. In this article, we highlight the lessons learned from functional integration of a Food and Drug Administration-cleared type 2 diabetes MIT into the electronic health record (EHR) of a multiphysician practice within a large, urban, academic medical center. METHODS: In-depth interviews were conducted with integration stakeholder groups: mobile and EHR software and information technology teams, clinical end users, project managers, and business analysts. Interviews were summarized and categorized into lessons learned using the Architecture for Integrated Mobility® framework. RESULTS: Findings from the diverse stakeholder group of a MIT-EHR integration project indicate that user workflow, software system persistence, environment configuration, device connectivity and security, organizational processes, and data exchange heuristics are key issues that must be addressed. CONCLUSIONS: Mobile-integrated therapy that integrates patient self-management data with medical record data provides the opportunity to understand the potential benefits of bidirectional data sharing and reporting that are most valuable in advancing better health and better care in a cost-effective way that is scalable for all chronic diseases.

Mobile diabetes intervention study: testing a personalized treatment/behavioral communication intervention for blood glucose control.

BACKGROUND: National data find glycemic control is within target (A1c<7.0%) for 37% of patients with diabetes, and only 7% meet recommended glycemic, lipid, and blood pressure goals. OBJECTIVES: To compare active interventions and usual care for glucose control in a randomized clinical trial (RCT) among persons with diabetes cared for by primary care physicians (PCPs) over the course of 1 year. METHODS: Physician practices (n=36) in 4 geographic areas are randomly assigned to 1 of 4 study groups. The intervention is a diabetes communication system, using mobile phones and patient/physician portals to allow patient-specific treatment and communication. All physicians receive American Diabetes Association (ADA) Guidelines for diabetes care. Patients with poor diabetes control (A1c> or =7.5%) at baseline (n=260) are enrolled in study groups based on PCP randomization. All study patients receive blood glucose (BG) meters and a year's supply of testing materials. Patients in three treatment groups select one of two mobile phone models, receive one-year unlimited mobile phone data and service plan, register on the web-based individual patient portal and receive study treatment phone software based on study assignment. Control group patients receive usual care from their PCP. The primary outcome is mean change in A1c over a 12-month intervention period. CONCLUSION: Traditional methods of disease management have not achieved adequate control for BG and other conditions important to persons with diabetes. Tools to improve communication between patients and PCPs may improve patient outcomes and be satisfactory to patients and physicians. This RCT is ongoing.

Where is the patient in diabetes performance measures? The case for including patient-centered and self-management measures.

OBJECTIVE: Health policies are important determinants of clinician and patient behavior, and an important policy issue is what items are included in healthcare quality and performance measures. There is consensus that patient-centered care and self-management support are essential evidence-based components of good diabetes care. However, most major diabetes performance measures such as the National Committee for Quality Assurance (NCQA)/American Diabetes Association (ADA) Provider Recognition Program indexes have not included self-management or psychosocial items. RESEARCH DESIGN AND METHODS AND RESULTS: We review the case for and propose a set of patient-centered, self-management indicators to be included as a standard part of diabetes quality indicators. The proposed indicators include: patient self-management goal(s), measures of health behaviors (e.g., healthy eating, medication taking, physical activity, and smoking status), quality of life, and patient-centered collaborative care. We discuss the evidence and the concerns about patient-report measures and summarize successful incorporation of such patient-centered measures in other countries and by the American Association of Diabetes Educators (AADE). CONCLUSIONS: The adage that "what gets measured, gets done" applies to diabetes management and many other areas of healthcare. Inclusion of the proposed indicators in national diabetes performance measures would be consistent with Institute of Medicine (IOM), ADA, Centers for Disease Control (CDC), Diabetes Attitudes, Wishes, and Needs (DAWN), AADE, and Society of Behavioral Medicine (SBM) recommendations. Such action would enhance both the priority and delivery of quality, patient-centered care, and diabetes self-management support.

Computerized learning technologies for diabetes: a systematic review.

BACKGROUND: The objective of this study was to evaluate computerized learning technology interventions that can empower patients in the self-management of diabetes and support diabetes education over a distance. METHODS: We searched Medline (1966-2006), CINAHL (1982-2006), and the Cochrane Central Register of Controlled Trials (first quarter 2007) databases. We also reviewed reference lists from included studies to identify additional studies. We included 25 articles representing 21 randomized controlled trials that evaluated a computerized learning technology and measured the outcome of patient care. We extracted patient sample, intervention, educational content topics, outcome measures, and statistical significance. RESULTS: Of 21 eligible trials, 18 trials (85.7%) reported significant positive outcomes. Almost 44% (43.8%) of the outcomes demonstrated significant improvements (49 of 112 outcomes). CONCLUSIONS: Patient self-management behaviors are important in chronic disease management, and initial evidence suggests that computerized learning technology interventions can play a significant role in the future.

Evolution of the American Association of Diabetes Educators' diabetes education outcomes project.

PURPOSE: This is the initial article in a series that describes a multiyear project of a professional membership organization to define, standardize, collect, and report the outcomes of diabetes self-management education. The purpose of this article is to describe and summarize the contributions of each phase of the project: determining a conceptual framework, developing and testing measurement instruments, defining outcome standards for diabetes self-management education, and implementing a technology approach to capturing the outcomes. METHODS: Association archives, project participants, presentation slides, and published articles provide the historical information that is presented in this article. RESULTS: Evidence for diabetes education as an intervention has been demonstrated, but key questions remain about what settings and which interventions, provided by whom and over what period of time, produce what outcomes. This project integrated diabetes education outcomes reporting into a system of diabetes care through the development of measurement methods and a data collection system for patients and educators at the point of service. CONCLUSIONS: The AADE7 Outcomes System supports educators in collecting and reporting on program design, patient self-care behaviors, and educational, behavioral, and clinical interventions and outcomes.

Development of the American Association of Diabetes Educators' Diabetes Self-management Assessment Report Tool.

PURPOSE: The purpose of this article is to describe the development and testing of a new tool for collecting patient information for diabetes self-management education (DSME): the Diabetes Self-management Assessment Report Tool (D-SMART). The D-SMART was designed through expert panel consensus based on a hybrid conceptual framework and is intended to serve multiple functions at the level of the patient, the program, and the field. METHODS: The D-SMART has completed 3 rounds of pilot testing and is currently undergoing a fourth round, with each round resulting in revisions to the original instrument. RESULTS: Findings from the pilot testing indicate that the instrument has acceptable reliability, validity, and sensitivity (or responsiveness) to change. A full-scale field test is currently under way, in which data from the D-SMART will be used to guide the delivery of services and to evaluate and enhance program functioning with a goal of improving education and care. Additional data from the field test are reported elsewhere, and further analyses are planned. CONCLUSIONS: The D-SMART provides educators with a tool that measures patients' behaviors and identifies those priorities for, and barriers to, change.

The Diabetes Self-management Assessment Report Tool (D-SMART): process evaluation and patient satisfaction.

PURPOSE: The purpose of this article is to present the results of the process evaluation and patient experience in completing the Diabetes Self-management Assessment Report Tool (D-SMART), an instrument within the AADE Outcome System to assist diabetes educators to assess, facilitate, and track behavior change in the provision of diabetes self-management education (DSME). METHODS: The D-SMART was integrated into computer and telephonic systems at 5 sites within the Pittsburgh Regional Initiative for Diabetes Education (PRIDE) network. Data were obtained from 290 patients with diabetes using the system at these programs via paper-and-pencil questionnaires following baseline D-SMART assessments and electronic system measurement of system performance. Process evaluation included time of completion, understanding content, usability of technology, and satisfaction with the system. Patients were 58% female and 85% Caucasian and had a mean age of 58 years. Fifty-six percent of patients had no more than a high school education, and 78% had Internet access at home. RESULTS: Most patients reported completing the D-SMART at home (78%), in 1 attempt (86%) via the Internet (55%), and in less than 30 minutes. Seventy-six percent believed the questions were easy to understand, and 80% did not need assistance. Age was negatively associated with ease of use. Moreover, 76% of patients believed the D-SMART helped them think about their diabetes, with 67% indicating that it gave the diabetes educator good information about themselves and their diabetes. Most (94%) were satisfied with the D-SMART. Level of satisfaction was independent of the system being used. CONCLUSIONS: The D-SMART was easily completed at home in 1 attempt, content was understandable, and patients were generally satisfied with the wording of questions and selection of answers. The D-SMART is easy to use and enhanced communication between the patient and clinician; however, elderly patients may need more assistance. Computer-based and telephonic D-SMARTs appear to be feasible and useful assessment methods for diabetes educators.

Using the American Association of Diabetes Educators Outcomes System to identify patient behavior change goals and diabetes educator responses.

PURPOSE: The purpose of this article is to ascertain patients' self-identified and mutually identified or agreed on (working with diabetes educators) behavior change goals and examine the diabetes educators' response to these goals during the provision of diabetes self-management education. METHODS: The American Association of Diabetes Educators Outcome System was integrated into Web-based, touch-screen, and telephonic systems within 8 sites within the Pittsburgh Regional Initiative for Diabetes Education network. Data from patients and their diabetes educators were obtained from the Diabetes Self-management Assessment Report Tool (D-SMART) and Diabetes Educator Tool (D-ET). RESULTS: Nine hundred fifty-four individuals with diabetes (type 1 and type 2) using the D-SMART self-identified healthy eating (74%) and being active (54%) as the most common behavior change goals. From that sample, 527 patients identified goals that were mutually identified or agreed on with their diabetes educator: healthy eating (94%), being active (59%), monitoring (49%), taking medication (26%), reducing risks (19%), problem solving (18%), and healthy coping (18%). CONCLUSION: The most common behavior change goals identified by patients (self-identified or mutually identified with their diabetes educator) were healthy eating and being active. The behavior change goal least addressed by patients and educators alike was healthy coping. Mutually identified goals among educators and patients may improve targeted appropriate educational strategies to support patients in meeting their goals.