A Combination of Cutset Conditioning with Clique-Tree Propagation in the Pathfinder System
This work addresses inference efficiency for medical diagnosis systems, but it appears incremental as it combines existing methods without claiming major breakthroughs.
The authors tackled the problem of exact probabilistic inference in Bayesian belief networks by combining cutset conditioning and clique-tree propagation into an aggregation after decomposition (AD) method, applied in the Pathfinder medical expert system for hematopathology diagnosis.
Cutset conditioning and clique-tree propagation are two popular methods for performing exact probabilistic inference in Bayesian belief networks. Cutset conditioning is based on decomposition of a subset of network nodes, whereas clique-tree propagation depends on aggregation of nodes. We describe a means to combine cutset conditioning and clique- tree propagation in an approach called aggregation after decomposition (AD). We discuss the application of the AD method in the Pathfinder system, a medical expert system that offers assistance with diagnosis in hematopathology.