Diabetes Bayesian Network with 413 Nodes for Insulin Adjustment Modeling

A Bayesian network model for diabetes with 413 nodes, 602 arcs, and 429,409 parameters. The model was developed by S. Andreassen, R. Hovorka, J. Benn, K. G. Olesen, and E. R. Carson. It was presented in a 1991 conference paper titled 'A Model-based Approach to Insulin Adjustment'.

Use Cases

• Probabilistic inference for patient state estimation based on the network's conditional dependencies.
• Research into causal relationships in diabetes pathophysiology based on the graph structure.
• Benchmarking structure learning algorithms based on the known network topology and parameters.
• Developing model-based clinical decision support tools for insulin adjustment.

Strengths

• The network structure is explicitly defined with 413 nodes and 602 arcs.
• Model complexity is quantified with 429,409 parameters and an average Markov blanket size of 3.97.
• Has a clear academic provenance with a cited 1991 publication.

Limitations

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

Provenance

Source

S. Andreassen, R. Hovorka, J. Benn, K. G. Olesen, and E. R. Carson.

Collection Method

Model-based approach described in the cited conference paper.

Time Range

null

Freshness

null

Geography

null