Cargando…
A note on Youden's J and its cost ratio
BACKGROUND: The Youden index, the sum of sensitivity and specificity minus one, is an index used for setting optimal thresholds on medical tests. DISCUSSION: When using this index, one implicitly uses decision theory with a ratio of misclassification costs which is equal to one minus the prevalence...
Autor principal: | |
---|---|
Formato: | Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2010
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2959030/ https://www.ncbi.nlm.nih.gov/pubmed/20920288 http://dx.doi.org/10.1186/1471-2288-10-89 |
_version_ | 1782188423410352128 |
---|---|
author | Smits, Niels |
author_facet | Smits, Niels |
author_sort | Smits, Niels |
collection | PubMed |
description | BACKGROUND: The Youden index, the sum of sensitivity and specificity minus one, is an index used for setting optimal thresholds on medical tests. DISCUSSION: When using this index, one implicitly uses decision theory with a ratio of misclassification costs which is equal to one minus the prevalence proportion of the disease. It is doubtful whether this cost ratio truly represents the decision maker's preferences. Moreover, in populations with a different prevalence, a selected threshold is optimal with reference to a different cost ratio. SUMMARY: The Youden index is not a truly optimal decision rule for setting thresholds because its cost ratio varies with prevalence. Researchers should look into their cost ratio and employ it in a decision theoretic framework to obtain genuinely optimal thresholds. |
format | Text |
id | pubmed-2959030 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2010 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-29590302010-10-25 A note on Youden's J and its cost ratio Smits, Niels BMC Med Res Methodol Debate BACKGROUND: The Youden index, the sum of sensitivity and specificity minus one, is an index used for setting optimal thresholds on medical tests. DISCUSSION: When using this index, one implicitly uses decision theory with a ratio of misclassification costs which is equal to one minus the prevalence proportion of the disease. It is doubtful whether this cost ratio truly represents the decision maker's preferences. Moreover, in populations with a different prevalence, a selected threshold is optimal with reference to a different cost ratio. SUMMARY: The Youden index is not a truly optimal decision rule for setting thresholds because its cost ratio varies with prevalence. Researchers should look into their cost ratio and employ it in a decision theoretic framework to obtain genuinely optimal thresholds. BioMed Central 2010-09-30 /pmc/articles/PMC2959030/ /pubmed/20920288 http://dx.doi.org/10.1186/1471-2288-10-89 Text en Copyright ©2010 Smits; licensee BioMed Central Ltd. http://creativecommons.org/licenses/by/2.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Debate Smits, Niels A note on Youden's J and its cost ratio |
title | A note on Youden's J and its cost ratio |
title_full | A note on Youden's J and its cost ratio |
title_fullStr | A note on Youden's J and its cost ratio |
title_full_unstemmed | A note on Youden's J and its cost ratio |
title_short | A note on Youden's J and its cost ratio |
title_sort | note on youden's j and its cost ratio |
topic | Debate |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2959030/ https://www.ncbi.nlm.nih.gov/pubmed/20920288 http://dx.doi.org/10.1186/1471-2288-10-89 |
work_keys_str_mv | AT smitsniels anoteonyoudensjanditscostratio AT smitsniels noteonyoudensjanditscostratio |