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.
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?
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.
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.
Expert diagnostic support systems have been extensively studied. The practical application of these systems in real-world scenarios have been somewhat limited due to well-understood shortcomings such as extensibility. More recently, machine learned models for medical diagnosis have gained momentum since they can learn and generalize patterns found in very large datasets like electronic health records. These models also have shortcomings. In particular, there is no easy way to incorporate prior knowledge from existing literature or experts. In this paper, we present a method to merge both approaches by using expert systems as generative models that create simulated data on which models can be learned. We demonstrate that such a learned model not only preserve the original properties of the expert systems but also addresses some of their limitations. Furthermore, we show how this approach can also be used as the starting point to combine expert knowledge with knowledge extracted from other data sources such as electronic health records.