Abstract
Diagnostic systems of several kinds are used to distinguish between two classes of events, essentially "signals" and "noise." For them, analysis in terms of the "relative operating characteristic" of signal detection theory provides a precise and valid measure of diagnostic accuracy. It is the only measure available that is uninfluenced by decision biases and prior probabilities, and it places the performances of diverse systems on a common, easily interpreted scale. Representative values of this measure are reported here for systems in medical imaging, materials testing, weather forecasting, information retrieval, polygraph lie detection, and aptitude testing. Though the measure itself is sound, the values obtained from tests of diagnostic systems often require qualification because the test data on which they are based are of unsure quality. A common set of problems in testing is faced in all fields. How well these problems are handled, or can be handled in a given field, determines the degree of confidence that can be placed in a measured value of accuracy. Some fields fare much better than others.
Keywords
Measure (data warehouse)Computer scienceField (mathematics)Noise (video)Quality (philosophy)Set (abstract data type)Lie detectionScale (ratio)PolygraphSIGNAL (programming language)Data miningDetection theoryArtificial intelligenceMachine learningStatisticsMathematicsPsychology
Related Publications
Using Formative Measures in International Marketing Models: A Cautionary Tale Using Consumer Animosity as an Example
Purpose – Despite the increasing use of formative measurement models in literature, little is known about potential consequences for substantive theory testing. Against this bac...
Relative Sensing Networks: Observability, Estimation, and the Control Structure
In this paper we consider various structural aspects of estimation and control over relative sensing networks. We first expand on our earlier characterization of equivalent sens...
A Database-Centric Virtual Chemistry System
We describe an Oracle database application for general use within virtual chemistry. The application functions as a central hub and repository for chemical data with interfaces ...
Evaluating Structural Equation Models with Unobservable Variables and Measurement Error
The statistical tests used in the analysis of structural equation models with unobservable variables and measurement error are examined. A drawback of the commonly applied chi s...
The theory of signal detectability
The problem of signal detectability treated in this paper is the following: Suppose an observer is given a voltage varying with time during a prescribed observation interval and...
Publication Info
- Year
- 1988
- Type
- review
- Volume
- 240
- Issue
- 4857
- Pages
- 1285-1293
- Citations
- 9681
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
9681
OpenAlex
Cite This
John A. Swets
(1988).
Measuring the Accuracy of Diagnostic Systems.
Science
, 240
(4857)
, 1285-1293.
https://doi.org/10.1126/science.3287615
Identifiers
- DOI
- 10.1126/science.3287615