iMatter2: An AI-Driven Approach to Supercharge a Novel Digital Patient-Reported Outcomes Tool for Diabetes Management
Implementing an artificial intelligence-supported tool to collect patient-reported outcomes for patients with diabetes is expected to enable efficient delivery of high-quality patient-centered care and improve clinical outcomes.
Project Details -
Ongoing
-
Grant NumberR01 HS026522-06
-
Funding Mechanism(s)
-
AHRQ Funded Amount$1,999,996
-
Principal Investigator(s)
-
Organization
-
LocationNew York CityNew York
-
Project Dates07/01/2023 - 05/31/2028
-
Care Setting
-
Medical Condition
-
Population
-
Type of Care
-
Health Care Theme
Type 2 diabetes (T2D) is the eighth leading cause of death and disability in the United States. This nationwide epidemic is a significant burden on patients and health systems and disproportionately affects minority populations, who suffer higher rates of complications. Primary care physicians (PCPs) often lack the resources and tools to effectively help patients manage complex psychosocial and behavioral factors that significantly impact glycemic control. Incorporating patient-reported outcomes (PROs) into care creates an opportunity to improve clinical outcomes in actionable and meaningful ways for patients and providers alike. Researchers will build on a previous study that evaluated the efficacy of an innovative mobile health tool, called iMatter, that uses text messages to capture PROs in real time.
Artificial intelligence (AI)-supported tools will be added to iMatter to create iMatter2. Enhancements will include an interactive dashboard with PROS and hemoglobin A1c (HbA1c) data visualizations, clinical decision support tools, behavioral 'nudging' to prompt providers to review the PRO data, and an AI chatbot delivering two-way digital messages that allows patients to share their PROs and receive personalized motivational and educational messages.
The specific aims of the research are as follows:
- Test the hypothesis that iMatter2 will result in a greater mean reduction in HbA1c at 12 months, compared to usual care.
- Evaluate the reach, adoption, and implementation of the digital tool across practices, patients, and PCPs, with a focus on equity using the Reach, Effectiveness, Adoption, Implementation, Maintenance (RE-AIM) framework.
- Examine the associations between patients’ PRO responses and HbA1c reduction.
Employing a user-centered design approach, the team will refine and user-test iMatter2 in real-world settings. They will then conduct a randomized clinical trial to evaluate the effectiveness of iMatter2 versus usual care on HbA1c reduction at 12 months among 353 patients with uncontrolled T2D. Patients randomized to iMatter2 will receive and may respond to personalized PROs via text message, receive personalized motivational and educational messages via the AI chatbot, and have access to an interactive dashboard that visualizes their daily PRO and HbA1c data. Patients randomized to usual care will receive standard T2D treatment recommendations from their PCPs. PCPs randomized to iMatter2 will have access to clinical decision support tools to view the PRO reports and HbA1c data, while usual care PCPs will not have access to the electronic health record reports.
The findings of this research will have important population health value for patients, PCPs, health systems, and policymakers by identifying the optimal set of tools and procedures to effectively collect and monitor PROs in patients’ daily lives and as part of routine care.
Disclaimer
Disclaimer details