Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Navreet Kaur, Manuel Gonzales, Cristian Garcia Alcaraz, Jiaqi Gong, Kristen J. Wells, Laura E. Barnes

TL;DR

This work introduces a computational framework guided by Social Cognitive Theory for multi-scale (daily and weekly) modeling of longitudinal medication adherence, and assesses the significance of various factors in influencing adherence behavior across different time scales.

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.

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

TL;DR

This work introduces a computational framework guided by Social Cognitive Theory for multi-scale (daily and weekly) modeling of longitudinal medication adherence, and assesses the significance of various factors in influencing adherence behavior across different time scales.

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.

Paper Structure

This paper contains 20 sections, 5 figures, 4 tables.

Table of Contents

  1. Abstract
  2. Author summary
  3. Introduction
  4. Materials and methods
  5. Results
  6. Discussion
  7. Conclusion
  8. Supporting information
  9. Acknowledgments

Figures (5)

  • Figure 1: Multi-scale modeling and intervention for medication adherence
  • Figure 2: Dynamic adherence patterns: A) patient 53, B) patient 65.
  • Figure 3: Machine learning pipeline.
  • Figure 4: Proposed model architecture to integrate dynamic and static data.
  • Figure 5: Model interpretation with SHAP for: A) daily medication adherence, B) weekly medication adherence. The y-axis reflects the relative importance of the top 20 features for each task by the vertical order of features (top being the most important and bottom being the least). The x-axis reflects the mean SHAP values of each feature and represents the magnitude and direction of impact of each feature on the output (whether there's a higher/lower chance of taking (right of 0) or not taking (left of 0) medicine). The color bar represents lower/higher values of features and their relative association with adherence/non-adherence.