Open-source datasets and code accompanying research on visualizing patient pathways and clinical trajectories.
📄 Publication:
Interactive network visualization of opioid crisis research: a tool for reinforcing data linkage skills for public health policy researchers
Healthcare journeys are complex and often difficult to interpret using traditional tabular representations. This project explores approaches for representing patient pathways and clinical trajectories using graph-based visualizations, including Directed Acyclic Graphs (DAGs) and Sankey diagrams.
The repository provides datasets and supporting code to facilitate reproducible research and further exploration in healthcare analytics and visualization.
This work demonstrates how graph-based approaches can:
- Reveal patterns in patient pathways
- Improve interpretability of longitudinal healthcare data
- Support clinical decision-making
- Enable visual exploration of complex trajectories
Scrivner O., et al.
Interactive network visualization of opioid crisis research: a tool for reinforcing data linkage skills for public health policy researchers
Frontiers in Artificial Intelligence (2024)
🔗 https://pmc.ncbi.nlm.nih.gov/articles/PMC11026550/
- Datasets
- Visualization examples
- Supporting code
- Reproducible research artifacts
- Healthcare Analytics
- Biomedical Informatics
- Graph Visualization
- Network Analysis
- Data Science
- Explainable AI
If you use this work, please cite the associated publication. Scrivner O, Nguyen T, Ginda M, Simon K and Börner K (2024) Interactive network visualization of opioid crisis research: a tool for reinforcing data linkage skills for public health policy researchers. Front. Artif. Intell. 7:1208874. doi: 10.3389/frai.2024.1208874