A holonic approach to clinical pathway data analysis
A clinical pathway digital twin built from holons that can ingest messy real-world data, validate it, and produce automated analyses and reports for healthcare teams.
Healthcare pathways generate high-volume, high-variety data—and the operational context makes it hard to keep data clean, complete, and usable for decision-making. This paper presents a holonic approach to clinical pathway analysis, implemented as a clinical pathway digital twin.
Using a holon as an autonomous, cooperative software building block, the digital twin ingests and structures pathway data, checks for completion and anomalies, and supports automated statistical analyses and machine-learning predictions. A hip and knee replacement pathway case study demonstrates on-demand report generation and reduced repetitive manual work.
Key takeaways
- Holonic decomposition provides an intuitive way to aggregate/disaggregate pathway information.
- Explicit ingestion + validation improves data completion checks and anomaly handling.
- Automated reporting and prediction can be delivered without turning the twin into a monolith.