Specificity (tests): Difference between revisions
Jump to navigation
Jump to search
No edit summary |
|||
| (7 intermediate revisions by 2 users not shown) | |||
| Line 3: | Line 3: | ||
==Overview== | ==Overview== | ||
The '''specificity''' is a statistical measure of how well a [[binary classification]] test correctly identifies the negative cases | The '''specificity''' is a statistical measure of how well a [[binary classification]] test correctly identifies the negative cases. It is the probability that a test correctly classifies individuals without preclinical disease as negative. It is a proportional measurement and is often expressed in terms of percentage. | ||
==Calculation== | |||
For example, given a medical test that determines if a person has a certain disease, the specificity of the test to the disease is the probability that the test indicates `negative' if the person does not have the disease. | |||
That is, the specificity is the proportion of [[true negative]]s of all negative cases in the population. It is a parameter of the test. | That is, the specificity is the proportion of [[true negative]]s of all negative cases in the population. It is a parameter of the test. | ||
High specificity is important when the treatment or diagnosis is harmful to the patient mentally and/or physically.<ref>{{cite journal |author=Altman DG, Bland JM |title=Diagnostic tests. 1: Sensitivity and specificity |journal=BMJ |volume=308 |issue=6943 |pages=1552 |year=1994 |pmid=8019315 |doi= |url=http://www.bmj.com/cgi/content/full/308/6943/1552}}</ref> | High specificity is important when the treatment or diagnosis is harmful to the patient mentally and/or physically.<ref name="book">{{cite journal |author=Altman DG, Bland JM |title=Diagnostic tests. 1: Sensitivity and specificity |journal=BMJ |volume=308 |issue=6943 |pages=1552 |year=1994 |pmid=8019315 |doi= |url=http://www.bmj.com/cgi/content/full/308/6943/1552}}</ref> | ||
==Worked example== | ==Worked example== | ||
| Line 15: | Line 18: | ||
:<math>{\rm specificity}=\frac{\rm number\ of\ True\ Negatives}{{\rm number\ of\ True\ Negatives}+{\rm number\ of\ False\ Positives}}</math> | :<math>{\rm specificity}=\frac{\rm number\ of\ True\ Negatives}{{\rm number\ of\ True\ Negatives}+{\rm number\ of\ False\ Positives}}</math> | ||
A specificity of 100% means that the test recognizes all healthy people as healthy. The maximum is trivially achieved by a test that claims everybody healthy regardless of the true condition. Therefore, the specificity alone does not tell us how well the test recognizes positive cases. We also need to know the [[sensitivity (tests)|sensitivity]] of the test to the class, or equivalently, the specificities to the other classes.<ref>{{cite journal |author=Altman DG, Bland JM |title=Diagnostic tests. 1: Sensitivity and specificity |journal=BMJ |volume=308 |issue=6943 |pages=1552 |year=1994 |pmid=8019315 |doi= |url=http://www.bmj.com/cgi/content/full/308/6943/1552}}</ref> | A specificity of 100% means that the test recognizes all healthy people as healthy. The maximum is trivially achieved by a test that claims everybody healthy regardless of the true condition. Therefore, the specificity alone does not tell us how well the test recognizes positive cases. We also need to know the [[sensitivity (tests)|sensitivity]] of the test to the class, or equivalently, the specificities to the other classes.<ref name="book">{{cite journal |author=Altman DG, Bland JM |title=Diagnostic tests. 1: Sensitivity and specificity |journal=BMJ |volume=308 |issue=6943 |pages=1552 |year=1994 |pmid=8019315 |doi= |url=http://www.bmj.com/cgi/content/full/308/6943/1552}}</ref> | ||
A test with a high specificity has a low [[Type I and type II errors | Type I error]] rate. | A test with a high specificity has a low [[Type I and type II errors | Type I error]] rate. | ||
Specificity is sometimes confused with the [[precision]] or the [[positive predictive value]], both of which refer to the fraction of returned positives that are true positives. The distinction is critical when the classes are different sizes. A test with very high specificity can have very low precision if there are far more true negatives than true positives, and vice versa.<ref>{{cite journal |author=Altman DG, Bland JM |title=Diagnostic tests. 1: Sensitivity and specificity |journal=BMJ |volume=308 |issue=6943 |pages=1552 |year=1994 |pmid=8019315 |doi= |url=http://www.bmj.com/cgi/content/full/308/6943/1552}}</ref> | Specificity is sometimes confused with the [[precision]] or the [[positive predictive value]], both of which refer to the fraction of returned positives that are true positives. The distinction is critical when the classes are different sizes. A test with very high specificity can have very low precision if there are far more true negatives than true positives, and vice versa.<<ref name="book">{{cite journal |author=Altman DG, Bland JM |title=Diagnostic tests. 1: Sensitivity and specificity |journal=BMJ |volume=308 |issue=6943 |pages=1552 |year=1994 |pmid=8019315 |doi= |url=http://www.bmj.com/cgi/content/full/308/6943/1552}}</ref> | ||
==SPPIN and SNNOUT== | |||
{| class="wikitable" | |||
! | |||
! SPPIN | |||
! SNNOUT | |||
! Neither | |||
! Near-perfect | |||
|- | |||
| Proposed definition | |||
| Sp > 95% | |||
| SN > 95% | |||
| Both < 95% | |||
| Both > 99% | |||
|- | |||
| Example | |||
| Many physical dx findings | |||
| Ottawa fracture rules<ref name="ottawa">{{cite web |url=http://www.theottawarules.ca/ |title=The Ottawa Rules |author=Stiell, Ian |date= |website= |publisher=University of Ottawa |access-date=January 5, 2020 |quote=}}</ref> | |||
| [[Exercise treadmill test]]<ref name="pmid22512607">{{cite journal| author=Banerjee A, Newman DR, Van den Bruel A, Heneghan C| title=Diagnostic accuracy of exercise stress testing for coronary artery disease: a systematic review and meta-analysis of prospective studies. | journal=Int J Clin Pract | year= 2012 | volume= 66 | issue= 5 | pages= 477-92 | pmid=22512607 | doi=10.1111/j.1742-1241.2012.02900.x | pmc= | url=https://www.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&tool=sumsearch.org/cite&retmode=ref&cmd=prlinks&id=22512607 }} ''Note that 80% is a rough estimate of sensitivity and specificity.''</ref> | |||
| HIV-1/HIV-2 4th gen test<ref name="pmid24342484">{{cite journal| author=Malloch L, Kadivar K, Putz J, Levett PN, Tang J, Hatchette TF et al.| title=Comparative evaluation of the Bio-Rad Geenius HIV-1/2 Confirmatory Assay and the Bio-Rad Multispot HIV-1/2 Rapid Test as an alternative differentiation assay for CLSI M53 algorithm-I. | journal=J Clin Virol | year= 2013 | volume= 58 Suppl 1 | issue= | pages= e85-91 | pmid=24342484 | doi=10.1016/j.jcv.2013.08.008 | pmc= | url=https://www.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi?dbfrom=pubmed&tool=sumsearch.org/cite&retmode=ref&cmd=prlinks&id=24342484 }} </ref> | |||
|- | |||
| colspan="5" | '''Predictive values:''' | |||
|- | |||
| 10% pretest prob | |||
|<span style="color:red;font-weight:bold">PPV= 35%</span> | |||
<span style="color:lime;font-weight:bold">NPV = 99%</span> | |||
| PPV = 64% | |||
<span style="color:lime;font-weight:bold">NPV = 98%</span> | |||
| PPV = 31% | |||
<span style="color:lime;font-weight:bold">NPV = 97%</span> | |||
| PPV = 92% | |||
<span style="color:lime;font-weight:bold">NPV > 99%</span> | |||
|- | |||
| 50% pretest prob | |||
| PPV = 94% | |||
NPV = 83% | |||
| PPV = 83% | |||
NPV = 94% | |||
| PPV = 80% | |||
NPV = 80% | |||
| <span style="color:lime;font-weight:bold">PPV = 99%</span> | |||
<span style="color:lime;font-weight:bold">NPV = 99%</span> | |||
|- | |||
| 90% pretest prob | |||
|<span style="color:lime;font-weight:bold">PPV = 98%</span> | |||
NPV = 64% | |||
|<span style="color:lime;font-weight:bold">PPV = 99%</span> | |||
<span style="color:red;font-weight:bold">NPV = 35%</span> | |||
|<span style="color:lime;font-weight:bold">PPV = 97%</span> | |||
NPV = 31% | |||
| <span style="color:lime;font-weight:bold">PPV > 99%</span> | |||
NPV = 92% | |||
|- | |||
| Clinical messages | |||
| colspan="2" valign="top"| Accept test result when: | |||
# confirms your suspicion | |||
# maybe when pretest was a toss-up | |||
| valign="top"| Accept test result when: | |||
# confirms a strong suspicion | |||
| valign="top"| Accept test result ''unless'': | |||
# Contradicts a strong suspicion | |||
|- | |||
| colspan="5" | '''Notes:'''<br/> | |||
<span style="color:lime;font-weight:bold">Green font</span> indicates when results are more likely to be trustable<br/> | |||
<span style="color:red;font-weight:bold">Red font</span> indicates SPPIN/SNNOUT errors when you should be suspicous a a SPPIN/SNNOUT result | |||
|} | |||
==Related Chapters== | ==Related Chapters== | ||
| Line 30: | Line 103: | ||
== Online Calculators == | == Online Calculators == | ||
* [ | * [https://www.medcalc.org/calc/diagnostic_test.php MedCalc's Sensitivity/Specificity Calculator] | ||
==References== | ==References== | ||
| Line 44: | Line 117: | ||
[[ja:特異度]] | [[ja:特異度]] | ||
[[su:Spésifisitas]] | [[su:Spésifisitas]] | ||
[[zh:特异度]] | [[zh:特异度]] | ||
{{WikiDoc Help Menu}} | {{WikiDoc Help Menu}} | ||
{{WikiDoc Sources}} | {{WikiDoc Sources}} | ||
Latest revision as of 22:16, 9 January 2020
Editor-In-Chief: C. Michael Gibson, M.S., M.D. [1]; Assistant Editor(s)-In-Chief: Kristin Feeney, B.S.
Overview
The specificity is a statistical measure of how well a binary classification test correctly identifies the negative cases. It is the probability that a test correctly classifies individuals without preclinical disease as negative. It is a proportional measurement and is often expressed in terms of percentage.
Calculation
For example, given a medical test that determines if a person has a certain disease, the specificity of the test to the disease is the probability that the test indicates `negative' if the person does not have the disease.
That is, the specificity is the proportion of true negatives of all negative cases in the population. It is a parameter of the test.
High specificity is important when the treatment or diagnosis is harmful to the patient mentally and/or physically.[1]
Worked example
Definition
- <math>{\rm specificity}=\frac{\rm number\ of\ True\ Negatives}{{\rm number\ of\ True\ Negatives}+{\rm number\ of\ False\ Positives}}</math>
A specificity of 100% means that the test recognizes all healthy people as healthy. The maximum is trivially achieved by a test that claims everybody healthy regardless of the true condition. Therefore, the specificity alone does not tell us how well the test recognizes positive cases. We also need to know the sensitivity of the test to the class, or equivalently, the specificities to the other classes.[1]
A test with a high specificity has a low Type I error rate.
Specificity is sometimes confused with the precision or the positive predictive value, both of which refer to the fraction of returned positives that are true positives. The distinction is critical when the classes are different sizes. A test with very high specificity can have very low precision if there are far more true negatives than true positives, and vice versa.<[1]
SPPIN and SNNOUT
| SPPIN | SNNOUT | Neither | Near-perfect | |
|---|---|---|---|---|
| Proposed definition | Sp > 95% | SN > 95% | Both < 95% | Both > 99% |
| Example | Many physical dx findings | Ottawa fracture rules[2] | Exercise treadmill test[3] | HIV-1/HIV-2 4th gen test[4] |
| Predictive values: | ||||
| 10% pretest prob | PPV= 35%
NPV = 99% |
PPV = 64%
NPV = 98% |
PPV = 31%
NPV = 97% |
PPV = 92%
NPV > 99% |
| 50% pretest prob | PPV = 94%
NPV = 83% |
PPV = 83%
NPV = 94% |
PPV = 80%
NPV = 80% |
PPV = 99%
NPV = 99% |
| 90% pretest prob | PPV = 98%
NPV = 64% |
PPV = 99%
NPV = 35% |
PPV = 97%
NPV = 31% |
PPV > 99%
NPV = 92% |
| Clinical messages | Accept test result when:
|
Accept test result when:
|
Accept test result unless:
| |
| Notes: Green font indicates when results are more likely to be trustable | ||||
Related Chapters
- binary classification
- receiver operating characteristic
- sensitivity (tests)
- statistical significance
- Type I and type II errors
- Selectivity
Online Calculators
References
- ↑ 1.0 1.1 1.2 Altman DG, Bland JM (1994). "Diagnostic tests. 1: Sensitivity and specificity". BMJ. 308 (6943): 1552. PMID 8019315.
- ↑ Stiell, Ian. "The Ottawa Rules". University of Ottawa. Retrieved January 5, 2020.
- ↑ Banerjee A, Newman DR, Van den Bruel A, Heneghan C (2012). "Diagnostic accuracy of exercise stress testing for coronary artery disease: a systematic review and meta-analysis of prospective studies". Int J Clin Pract. 66 (5): 477–92. doi:10.1111/j.1742-1241.2012.02900.x. PMID 22512607. Note that 80% is a rough estimate of sensitivity and specificity.
- ↑ Malloch L, Kadivar K, Putz J, Levett PN, Tang J, Hatchette TF; et al. (2013). "Comparative evaluation of the Bio-Rad Geenius HIV-1/2 Confirmatory Assay and the Bio-Rad Multispot HIV-1/2 Rapid Test as an alternative differentiation assay for CLSI M53 algorithm-I". J Clin Virol. 58 Suppl 1: e85–91. doi:10.1016/j.jcv.2013.08.008. PMID 24342484.
External links
- Sensitivity and Specificity Medical University of South Carolina