Use of AI to Predict and Support Medication Adherence in Patients With Breast Cancer: Systematic Review

Area of Science:

• Oncology
• Health Informatics
• Artificial Intelligence

Background:

• Oral medications are crucial for breast cancer (BC) treatment, yet nonadherence is a significant challenge.
• Artificial intelligence (AI) offers potential solutions for enhancing medication adherence in healthcare settings.
• Improving adherence is vital for optimizing treatment outcomes in BC patients.

Purpose of the Study:

• To systematically review the application of AI in addressing medication nonadherence in breast cancer (BC) patients.
• To identify current AI-driven predictive and interventional strategies for BC medication adherence.
• To highlight research gaps and suggest future directions for AI in BC treatment adherence.

Main Methods:

• A systematic literature search was conducted across four major databases (PubMed, Embase, Scopus, Web of Science).
• Studies were included if they utilized AI for predicting, monitoring, or supporting medication adherence in BC patients.
• PRISMA guidelines were followed, and risk of bias was assessed using PROBAST and Downs and Black's scale.

Main Results:

• Ten studies were reviewed, with most focusing on machine learning models to predict nonadherence.
• Predictors of nonadherence included clinical, behavioral, psychosocial, and sociodemographic factors.
• An AI-based chatbot intervention showed a promising 20% increase in adherence; however, all studies had a high risk of bias.

Conclusions:

• This is the first systematic review on AI for BC medication adherence, covering both predictive and interventional studies.
• Significant gaps exist in the implementation phase, necessitating research on actionability, safety, and cost-effectiveness.
• A coordinated, multidisciplinary approach is essential for the responsible development and integration of AI tools into routine BC care.