A Causal Bayesian Model for the Diagnosis of Appendicitis

arXiv.org Artificial Intelligence

The causal Bayesian approach is based on the assumption that effects (e.g., symptoms) that are not conditionally independent with respect to some causal agent (e.g., a disease) are conditionally independent with respect to some intermediate state caused by the agent, (e.g., a pathological condition). This paper describes the development of a causal Bayesian model for the diagnosis of appendicitis. The paper begins with a description of the standard Bayesian approach to reasoning about uncertainty and the major critiques it faces. The paper then lays the theoretical groundwork for the causal extension of the Bayesian approach, and details specific improvements we have developed. The paper then goes on to describe our knowledge engineering and implementation and the results of a test of the system. The paper concludes with a discussion of how the causal Bayesian approach deals with the criticisms of the standard Bayesian model and why it is superior to alternative approaches to reasoning about uncertainty popular in the Al community.

The use of Evidence Conflict to extend Diagnostic Models

AAAI Conferences

Medical practitioners are pragmatic about defining new diseases to explain rarely occurring combinations of symptoms. This paper reviews a case from the literature that introduced a new disease by comparing two Bayes network diagnostic models, one that contains the disease, the other a sub-model without it. The analysis shows how the measure of evidence conflict proposed by Jensen 1990 applies in the case of a diagnosis where conflict appears as the disease progresses. We demonstrate how such a model with a known set of diseases can be extended to include a new disease. I. Introduction: What constitutes a disease?

The accuracy vs. coverage trade-off in patient-facing diagnosis models

arXiv.org Machine Learning

In these online tools, patients input their initial symptoms and then proceed to answer a series of questions that the system deems relevant to those symptoms. The output of these online tools is a differential diagnosis (ranked list of diseases) that helps educate patients on possible relevant health conditions. Online symptom checkers are powered by underlying diagnosis models or engines similar to those used for advising physicians in "clinical decision support tools"; the main difference in this scenario being that the resulting differential diagnosis is not directly shared with the patient, but rather used by a physician for professional evaluation. Diagnosis models must have high accuracy while covering a large space of symptoms and diseases to be useful to patients and physicians. Accuracy is critically important, as incorrect diagnoses can give patients unnecessary cause for concern.

Communication of Uncertainty in Clinical Genetics Patient Health Communication Systems

AAAI Conferences

This paper presents an overview of communication of uncertainty in a corpus of patient letters written by genetic counselors to their clients. The typical patient letter summarizes (possibly quite complex) information about a case discussed during the counselor's meeting with a client (Baker et al. 2002). The goal of our study is to inform development of intelligent multimedia systems for patient-tailored health communication in clinical genetics. As a first step, we are designing GenIE, a prototype system that will generate the first draft of a patient letter as a tool for genetic counselors. In addition, GenIE could be used to brief physicians on communicating with a patient about a genetics-related diagnosis or risk assessment.

Probabilistic Evaluation of Candidates and Symptom Clustering for Multidisorder Diagnosis

arXiv.org Artificial Intelligence

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.