A Tractable Inference Algorithm for Diagnosing Multiple Diseases
This addresses the challenge of efficient inference in medical diagnosis for practitioners, but it is incremental as it builds on existing probabilistic models like QMR.
The paper tackles the problem of diagnosing multiple diseases using a probabilistic model with binary variables and noisy OR-gates, presenting the quickscore algorithm that computes posterior probabilities with time complexity O(nm-2m+), where n is diseases, m+ is positive findings, and m- is negative findings, and it is applied to a probabilistic QMR version with practical utility due to typically fewer positive findings than diseases.
We examine a probabilistic model for the diagnosis of multiple diseases. In the model, diseases and findings are represented as binary variables. Also, diseases are marginally independent, features are conditionally independent given disease instances, and diseases interact to produce findings via a noisy OR-gate. An algorithm for computing the posterior probability of each disease, given a set of observed findings, called quickscore, is presented. The time complexity of the algorithm is O(nm-2m+), where n is the number of diseases, m+ is the number of positive findings and m- is the number of negative findings. Although the time complexity of quickscore i5 exponential in the number of positive findings, the algorithm is useful in practice because the number of observed positive findings is usually far less than the number of diseases under consideration. Performance results for quickscore applied to a probabilistic version of Quick Medical Reference (QMR) are provided.