The foundation of our clinical rigor
Proven science drives everything we do. Through rigorous research, we demonstrate how our health technology delivers real results: better patient outcomes, greater value for healthcare systems, and more advanced AI capabilities. Key areas include:
Our AI transforms complex health data into personalized insights and guidance when individuals need it most.
We convert continuous glucose data into personalized guidance that elevates traditional diabetes care standards.
We address interconnected health conditions, turning digital engagement into measurable clinical improvements.
We offer FDA-cleared solutions for T1 and T2 diabetes that simplify treatment while addressing daily health challenges.
Impact of a Combined Continuous Glucose Monitoring–Digital Health Solution on Glucose Metrics and Self-Management Behavior for Adults With Type 2 Diabetes: Real-World, Observational Study
In this journal article, Welldoc builds upon prior research focused on advancing chronic care through the use of digital health and real-time connected devices. This study examines the impact of combing real-time continuous glucose monitoring (RT-CGM) with an AI-driven digital health solution on helping individuals with type 2 diabetes to improve their glycemic metrics like time in range (TIR).
Improving Diabetes Self-Management with a Mobile App: Preliminary Results of a Pilot Program at a Safety Net Hospital System
For patients with type 2 diabetes, self-management remains a significant challenge. In recent years, the use of digital health technologies for chronic disease management has increased. In this study presented at the ADA 2020 Virtual Conference, patients with uncontrolled type 2 diabetes were analyzed using BlueStar® by Welldoc to determine mean changes in A1c.
Implementation Strategy for a Digital Health Tool Influences User Engagement
Published by the American Diabetes Association publication, this study by Welldoc authors examined the company's BlueStar® used in three different models: a healthcare provider model, a diabetes educator model and a health plan model to demonstrate how the implementation strategy has the potential to influence user engagement and outcomes.
Expanding Reach: AADE7® Moves into the Digital Space
Identifying Digital Health Habits Correlated with Improved Blood Glucose Control
This research, conducted by Welldoc in collaboration with the Robert H. Smith School of Business Center for Health Information and Decision Systems, evaluated the performance of a Welldoc automated method for detecting significantly adverse glucose events and, further, classifying those events by level of severity.
Evaluating the Impact of a Combined Real-Time CGM/Digital Health Solution on Glucose Control for People with Type 2 Diabetes
Welldoc®, a digital health leader revolutionizing chronic care, today announced the presentation of data at the 15th International Conference on Advanced Technologies & Treatments for Diabetes (ATTD), evaluating how the combination of real-time CGM (rtCGM) with a digital health solution impacts glucose control for individuals with Type 2 diabetes not treated with insulin. For all participants and subgroups that were examined, the time in range (TIR) and glucose management indicator (GMI) improved significantly, demonstrating that a combined CGM and digital therapeutic solution has the potential to improve Type 2 diabetes management and glycemic control.
Evidence-Based mHealth Chronic Disease Mobile App Intervention Design: Development of a Framework
Food Detection from Continuous Glucose Monitoring Sensors Using Pretrained Transformer-Based Models
Nutrition is an essential component of managing chronic health conditions like diabetes and obesity. However, logging meals within health apps is time-consuming and cumbersome for many people. Welldoc continues to research opportunities to streamline this process through advanced AI.
In this research, we successfully developed a novel approach for automatedly detecting recent food intake solely based on continuous glucose monitoring (CGM) data and AI with an accuracy of 77.8%.
This research is a blueprint for the next generation of digital health. By enabling tools to gather consistent, complete dietary information without any input from the user, we are moving toward zero-effort self-management.
Human vs. Machine: A Comparative Study on CGM Event Detection and Classification
This research, conducted by Welldoc in collaboration with the Robert H. Smith School of Business Center for Health Information and Decision Systems, evaluated the performance of a Welldoc automated method for detecting significantly adverse glucose events and, further, classifying those events by level of severity.
Evaluating a State-of-the-art Generative Pre-trained Transformer Model to Predict Continuous Glucose Monitoring Values at Different Time Intervals
Welldoc is actively developing generative-AI models specific to continuous glucose monitoring (CGM) value prediction. Our GPT-like AI modeling approach, based on a vast CGM dataset for individuals with type 1 and type 2 diabetes, has achieved state-of-the-art performance in predicting short-term CGM trajectories, at five-minute intervals, up to two hours in advance. Specifically, when predicting one of the 5 glucose categories (VeryLow, Low, InRange, High, VeryHigh), the model demonstrated an overall accuracy of 94% in predicting CGM values within 30 minutes. The absolute prediction accuracy to predict glucose values within 5mg/dL and 10 mg/dL error range in 30mins was 62% and 80% respectively. This exceptional accuracy highlights the model's potential to provide valuable insights into the dynamic interplay between blood sugar levels, lifestyle factors, and interventions. By leveraging these insights, personalized, automated coaching can be developed to optimize diabetes management and improve individual outcomes. This work is integral to Welldoc’s Advanced AI and our ability to transform the care continuum.
From Data to Outcomes: Digital Health & the Role of the Healthcare Provider
For this study presented at the Academy Health Health Datapalooza, the authors presented the Digital Health Engagement Chain as a framework to assess each of the implementation approaches were used. Evaluations included the target population, the outreach modalities, and activation rate for each type of implementation: direct to consumer, a program approach, a healthcare provider (HCP), direct to patient, and a HCP via an electronic medical record (EMR) integration.
Examining The Ability of Different Machine Learning Approaches to Predict Health Outcomes with a Digital Health Platform
In this study, Welldoc builds upon our prior research on advancing digital health AI through machine learning (ML) and connection with real-time connected devices, such as continuous glucose monitoring (CGM). This study examines how CGM data combined with digital health My E-Diary for Activities and Lifestyle (MEDAL) data and behavior patterns can lead to better understanding of optimal digital health feature utilization and ML models, which can be used to predict future Time in Range (TIR). This research continues Welldoc's efforts in advancing our AI models and developing next generation digital health solutions geared towards personalized prevention and prediction.
Hypoglycemia prediction using machine learning models for patients with type 2 diabetes
Educators: Go Mobile & Join the Digital Revolution!
Estimating the Economic Value of a Digital Therapeutic in Type 2 Diabetes
Truven Health Analytics, part of IBM Watson Health, conducted an analysis of commercial and Medicare consumers within the MarketScan databases for Welldoc. The research findings show Welldoc's ability to help lower and control A1C and generate savings per user per month.
Early Engagement Measures Can Accurately Identify Users at Risk of Abandoning Digital Therapeutics
The purpose of this research study was to develop a predictive model of digital health persistence and explore important factors in identifying those who are likely to abandon a digital therapeutic.
Enhancing Mobile Health to Achieve Both Hypertension and Diabetes Goals
Meeting goals for hypertension, a common co-morbidity with Type 2 diabetes (T2D), can be a challenge. In this study, data from patients with T2D who activated BlueStar® by Welldoc were analyzed as a way to illustrate the potential for digital solutions to support patients for both type 2 diabetes and blood pressure.
Enhancing Diabetes and Hypertension Self-Management: A Randomized Trial of a Mobile Phone Strategy
Engagement With an AI-enabled Digital Health Tool by Individuals With Overweight or Obesity Enrolled in a Weight Management Program Differs by Use of Anti-obesity Medications
We investigated user engagement patterns within our digital health application, comparing individuals utilizing a weight management program both with and without anti-diabetic/anti-obesity medications (AOMs).
Studying engagement patterns is a key focus area for Welldoc as we continue to focus our research on further personalizing the weight management journey.
This research indicates that engagement can vary based on medication usage. We observed significantly higher engagement with the non-AOM group. This supports the idea that the need for tracking, guidance, and support needs may be more pronounced for individuals navigating their weight without these medications.
Consistent Engagement with a Digital Health Solution Enhances the Effect of Medication Changes on Blood Glucose Control
This research, conducted by Welldoc in collaboration with the Robert H. Smith School of Business Center for Health Information and Decision Systems, evaluated the performance of a Welldoc automated method for detecting significantly adverse glucose events and, further, classifying those events by level of severity.
Contextual Annotations Predict Digital Health Solution Persistence and Diabetes Outcomes
The purpose of this research, presented at the Diabetes Technology Society, was to explore how patients use annotation features, the relationship between annotations and persistent engagement, and diabetes outcomes through patient-generated annotations.
Development of Self-Management Behavior Scores and Profiles with Digital Health Data
Diabetes Digital Health Learning Network (DDHLN): Educators Designing the Future
Determinants of Engagement in Digital Health: What Makes it Stick?
Unveiled at the 2018 Diabetes Technology Meeting, the co-authors presented results of a study conducted on the determinants of digital health engagement among patients of a primary care clinic in Boston, MA. The authors sought to systematically assess patient characteristics that influence uptake or attrition.
Complementarity of Digital Health and Peer Support: “This Is What’s Coming”
This collaborative study, with Dr. Edwin Fisher PhD of University of North Carolina, Peers for Progress and Vanguard Medical Group, assess the effectiveness of the Welldoc solution and peer support in providing health management and education for adults with Type 2 Diabetes.
Let’s partner to elevate cardiometabolic health.
Contact our sales team to talk about a solution for your enterprise or request a demo to see Welldoc’s predictive AI in healthcare in action.
.webp)
.avif)