Pathfinder 9: A Bayesian Network for Medical Diagnosis with 109 Nodes

109 nodes and 195 arcs define this large-scale Bayesian network from the Pathfinder project, a seminal expert system for lymph-node pathology diagnosis. The network contains 72,079 parameters and was authored by D. Heckerman, E. Horwitz, and B. Nathwani, with foundational research published in 1992. It serves as a benchmark for discrete probabilistic reasoning and structure learning algorithms.

Use Cases

• Benchmarking structure learning algorithms based on the known network topology of 109 nodes and 195 arcs.
• Evaluating probabilistic inference performance on a large-scale model with 72,079 parameters.
• Studying the design of normative expert systems based on the documented Pathfinder project methodology.

Strengths

• Well-documented provenance as a reference model from the bnlearn Bayesian Network Repository.
• Large-scale structure with 109 nodes and 72,079 parameters, suitable for testing complex models.
• Clear authorship and citation to the foundational 1992 research paper.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and sample data are unknown, which may limit suitability assessment for certain tasks.
• Last update date is unknown; freshness unverified.

Provenance

Source

D. Heckerman, E. Horwitz, and B. Nathwani via the bnlearn Bayesian Network Repository.

Collection Method

Constructed as part of the Pathfinder expert system project for lymph-node pathology.

Time Range

null

Freshness

null

Geography

null