Improving Long-Term Adherence to Endocrine Therapy Among Breast Cancer Survivors: Development of a Multiscale...

Area of Science:

• Oncology
• Behavioral Science
• Health Informatics

Background:

• Breast cancer survivors face challenges with long-term adherence to endocrine therapy (ET).
• Low adherence to ET can increase the risk of breast cancer recurrence.
• Ecological momentary assessment (EMA) and health behavior theories can inform personalized interventions.

Purpose of the Study:

• To describe the development of a multiscale modeling intervention (MMI) system for ET adherence.
• To assess the acceptability of the MMI system among breast cancer survivors.
• To identify modifiable predictors of ET adherence and select relevant survey instruments.

Main Methods:

• Usability interviews with 25 breast cancer survivors to assess MMI system acceptability.
• Secondary data analysis of ET adherence data from 32 survivors using social cognitive theory and neural networks.
• Literature review to identify constructs and surveys associated with ET adherence.

Main Results:

• Survivors were willing to use various components of the MMI system, including smartphone apps and smart devices.
• Machine learning identified 104 survey items significantly predicting 4-week ET medication adherence.
• 42 relevant surveys were identified, and a final survey with 32 items was selected for the MMI system.

Conclusions:

• The MMI system integrates social cognitive theory, data-driven models, and user feedback.
• A prototype MMI system was developed based on study findings.
• The MMI system will be deployed in a future 6-month longitudinal study with 20 breast cancer survivors.