Pathway Exploration for Breast Cancer Care

Abstract

Pathway exploration can support clinical research efforts and shared decision making between providers, patients, and their families. In this work, we extend the Pathfinder temporal abstraction method and developed a corresponding visualization platform to identify treatment event paths. We used manually curated cancer registry data and administrative data to generate a pathway exploration framework to compare data sources, assess clinical quality measures, re-create the analysis of published studies. We additionally developed a decision aid based on the care path visualizations to support patient education and shared decision making. We demonstrated how our exploration framework is generalizable enough to represent the majority of breast cancer quality measures from certain organizations and that we could support replicating previously published studies. Additionally, we developed, received feedback on, and plan to pilot a patient education decision aid to support shared decision making. Future work is needed to develop data driven methods that fit the abstraction framework and can utilize clinical data that is generated during the course of care. This work can help healthcare providers, organizations, and patients make better healthcare decisions and assess performance.