Probabilistic Evaluation of Candidates and Symptom Clustering for Multidisorder Diagnosis

TL;DR

This paper introduces a probabilistic formula for evaluating candidate sets in multidisorder diagnosis, enabling efficient validation and pruning of potential diagnoses by accounting for various symptom states without restrictive assumptions.

Contribution

It derives a novel probability computation method for candidate sets in symptom clustering, accommodating positive, negative, and unknown symptoms without prior assumptions.

Findings

Enables simultaneous validation or pruning of multiple candidates.

Allows specification of positive, negative, and unknown symptoms.

Does not assume disorders outside the candidate set.

Abstract

This paper derives a formula for computing the conditional probability of a set of candidates, where a candidate is a set of disorders that explain a given set of positive findings. Such candidate sets are produced by a recent method for multidisorder diagnosis called symptom clustering. A symptom clustering represents a set of candidates compactly as a cartesian product of differential diagnoses. By evaluating the probability of a candidate set, then, a large set of candidates can be validated or pruned simultaneously. The probability of a candidate set is then specialized to obtain the probability of a single candidate. Unlike earlier results, the equation derived here allows the specification of positive, negative, and unknown symptoms and does not make assumptions about disorders not in the candidate.