Data-driven Personalization for Inclusive Outreach and Equitable Outcomes in a Digital Health Intervention for Hypertension Management: A Prospective Observational Study

Summary

The purpose of the proposed observational study is to explore the relations between data-driven personalization and equitable health outcomes in a digital health intervention (DHI) for hypertension management. In the current intervention, behavioral reinforcement learning is applied to personalize intervention content to maximize the behavioral outcomes of three target behaviors critical for effective hypertension management: clinical encounters, medication adherence, and self-monitoring of blood pressure (SMBP).

Eligibility

Age range

18+ years

Sex

All

Healthy volunteers

No

Interventions

• Behavioral
  Precision Nudging for Hypertension Management

  The hypertension digital health intervention under study combines behavioral science theory with a type of machine learning called reinforcement learning to enable precision nudging: the selection, assembly, and delivery of behavioral science-based messages created to address barriers to, and promote, management of hypertension. The behavioral design process used for the hypertension DHI intentionally includes research on traditionally underserved populations, such as racial and ethnic minorities and people with lower incomes or educational attainment. By including the right ingredients to meet a diverse set of needs and by effectively personalizing the content each individual sees based on their own reactions, the intervention aims to improve health equity by matching each individual to the right behavioral approach.

Location