A computational framework for longitudinal medication adherence prediction in breast cancer survivors: A social cognitive theory based approach

2025-04-20

AI Summary

This study addresses the challenge of predicting medication adherence during long-term adjuvant endocrine therapy (e.g., tamoxifen, aromatase inhibitors) among breast cancer survivors. We propose the first multi-scale computational framework grounded in Social Cognitive Theory (SCT). Methodologically, it integrates dynamic medication-taking patterns (daily-level sequences) with static individual characteristics (clinical, psychological, and sociodemographic factors), implementing an XGBoost-LSTM hybrid model capable of modeling adherence at both daily and weekly granularities—thereby achieving deep coupling of theory-driven and data-driven approaches. Key contributions include: (1) the first systematic integration of SCT into longitudinal adherence modeling; and (2) explicit differentiation of dynamic versus static factor contributions across temporal scales. Experimental results show prediction accuracies of 87.25% (daily) and 76.04% (weekly), significantly outperforming baseline models. Dynamic features dominate daily-level prediction, whereas synergistic dynamic-static interactions better capture macro-level weekly adherence behavior.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Application Domains: Humanities & Computational Social Science
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Social Networks and Social Media: Computational social science
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Non-adherence to medications is a critical concern since nearly half of patients with chronic illnesses do not follow their prescribed medication regimens, leading to increased mortality, costs, and preventable human distress. Amongst stage 0-3 breast cancer survivors, adherence to long-term adjuvant endocrine therapy (i.e., Tamoxifen and aromatase inhibitors) is associated with a significant increase in recurrence-free survival. This work aims to develop multi-scale models of medication adherence to understand the significance of different factors influencing adherence across varying time frames. We introduce a computational framework guided by Social Cognitive Theory for multi-scale (daily and weekly) modeling of longitudinal medication adherence. Our models employ both dynamic medication-taking patterns in the recent past (dynamic factors) as well as less frequently changing factors (static factors) for adherence prediction. Additionally, we assess the significance of various factors in influencing adherence behavior across different time scales. Our models outperform traditional machine learning counterparts in both daily and weekly tasks in terms of both accuracy and specificity. Daily models achieved an accuracy of 87.25%, and weekly models, an accuracy of 76.04%. Notably, dynamic past medication-taking patterns prove most valuable for predicting daily adherence, while a combination of dynamic and static factors is significant for macro-level weekly adherence patterns.

Problem

• Predict medication adherence in breast cancer survivors
• Model multi-scale factors influencing adherence behavior
• Improve accuracy using dynamic and static adherence factors

Innovation

• Social Cognitive Theory guides multi-scale adherence modeling
• Combines dynamic and static factors for prediction
• Outperforms traditional machine learning in accuracy