Pathfinder 5: Bayesian Network for Medical Diagnosis

109 nodes and 195 arcs define the Pathfinder Bayesian network, a probabilistic model for medical diagnosis. The network, authored by D. Heckerman, E. Horwitz, and B. Nathwani, contains 72,079 parameters and was published in a 1992 research paper. It represents a foundational expert system for reasoning under uncertainty in pathology.

Use Cases

• Benchmarking Bayesian network structure learning algorithms based on the known graph topology.
• Evaluating probabilistic inference algorithms based on the network's 72,079 parameters.
• Studying the design of expert systems for medical diagnosis based on the model's domain.
• Analyzing Markov blanket properties for feature selection based on the average size of 3.82.

Strengths

• Well-defined graph structure with 109 nodes and 195 arcs.
• Large, complex model with 72,079 parameters.
• Clear academic provenance with a cited 1992 publication.

Limitations

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

Provenance

Source

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

Collection Method

Constructed as an expert system model for the Pathfinder project.

Time Range

null

Freshness

null

Geography

null