Accès libre

Accuracy of Diagnostic Tests

Ario Santini
Ario Santini
, 
Adrian Man
Adrian Man
 et 
Septimiu Voidăzan
Septimiu Voidăzan
   | 05 août 2021
The Journal of Critical Care Medicine's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Article Category: Spotlight on...
Publié en ligne: 05 août 2021
Pages: 241 - 248
Reçu: 11 mars 2021
Accepté: 27 juin 2021
DOI: https://doi.org/10.2478/jccm-2021-0022
Mots clés
© 2021 Ario Santini, Adrian Man, Septimiu Voidăzan, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

The ROC curve is composed by calculating the Sensitivity and the False Positive Rate for several thresholds, and plotting them against each other. The False Positive Rate (FPR) or 1 – Specificity is a measurement of how accurate the real negatives are being recorded. The smaller the FPR, the more accurate the identification of the real negative in the data. Sensitivity is recorded on the y axis and is a measure of how accurate people who have a disease are being identified as such.
The ROC curve is composed by calculating the Sensitivity and the False Positive Rate for several thresholds, and plotting them against each other. The False Positive Rate (FPR) or 1 – Specificity is a measurement of how accurate the real negatives are being recorded. The smaller the FPR, the more accurate the identification of the real negative in the data. Sensitivity is recorded on the y axis and is a measure of how accurate people who have a disease are being identified as such.

Fig. 2

Representation of the ROC for a random model
Representation of the ROC for a random model

Fig. 3

Explanation of different points of an ROC curve
Explanation of different points of an ROC curve

Fig. 4

The area under the ROC curve (AUC) is a measurement from values of 0.5 (random classifier) to 1 (perfect classifier). It signifies how well the model classifies the True and False data points. The greater AUC results in the ROC approaching the desired top-left corner.
The area under the ROC curve (AUC) is a measurement from values of 0.5 (random classifier) to 1 (perfect classifier). It signifies how well the model classifies the True and False data points. The greater AUC results in the ROC approaching the desired top-left corner.

Fig. 5

An example for ROC curves of age and ESR in cancer. For age the area under the curve is 0.684, and for ESR = 0.690. It can be seen how the curves are closer to the reference line (area = 0.5) than to the upper left corner, the point of maximum accuracy of the test.
An example for ROC curves of age and ESR in cancer. For age the area under the curve is 0.684, and for ESR = 0.690. It can be seen how the curves are closer to the reference line (area = 0.5) than to the upper left corner, the point of maximum accuracy of the test.

j.jccm-2021-0022.tab.004

True False
Predicted labels Positive TP FP
Negative FN TN
Actual labels

j.jccm-2021-0022.tab.001

Reference test (Gold standard)
Index test Positive Negative
Positive True Positive False positive
Negative False Negative True Negative

The effect of prevalence on the Positive Predictive Value

Prevalence % VVP % Sensitivity Specificity
0.1 1.8 90 95
1 15.4 90 95
5 48.6 90 95
50 94.7 90 95

Results of diagnostic tests

Reference standard
Positive Negative
Index Positive TP FP
test Negative FN TN
eISSN:
2393-1817
Langue:
Anglais
Périodicité:
4 fois par an
Sujets de la revue:
Medicine, Clinical Medicine, Internal Medicine, other, Surgery, Anaesthesiology, Emergency Medicine and Intensive-Care Medicine
RSS Feed de la revue