A Representation of Uncertainty to Aid Insight into Decision Models

by   Holly B. Jimison, et al.

Many real world models can be characterized as weak, meaning that there is significant uncertainty in both the data input and inferences. This lack of determinism makes it especially difficult for users of computer decision aids to understand and have confidence in the models. This paper presents a representation for uncertainty and utilities that serves as a framework for graphical summary and computer-generated explanation of decision models. The application described that tests the methodology is a computer decision aid designed to enhance the clinician-patient consultation process for patients with angina (chest pain due to lack of blood flow to the heart muscle). The angina model is represented as a Bayesian decision network. Additionally, the probabilities and utilities are treated as random variables with probability distributions on their range of possible values. The initial distributions represent information on all patients with anginal symptoms, and the approach allows for rapid tailoring to more patientspecific distributions. This framework provides a metric for judging the importance of each variable in the model dynamically.



There are no comments yet.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8


Imprecise Subset Simulation

The objective of this work is to quantify the uncertainty in probability...

Probabilistic Logic Programming with Beta-Distributed Random Variables

We enable aProbLog---a probabilistic logical programming approach---to r...

A Theory of Uncertainty Variables for State Estimation and Inference

Probability theory forms an overarching framework for modeling uncertain...

When Should a Decision Maker Ignore the Advice of a Decision Aid?

This paper argues that the principal difference between decision aids an...

Inductive Inference and the Representation of Uncertainty

The form and justification of inductive inference rules depend strongly ...

Decision Theoretic Bootstrapping

The design and testing of supervised machine learning models combine two...

Conflict and Surprise: Heuristics for Model Revision

Any probabilistic model of a problem is based on assumptions which, if v...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.