Article Figures & Data
Figures
- fig 1.
A and B, Test with a low (A) and high (B) threshold. The sensitivity and specificity of a test changes according to the threshold selected; hence, these diagnostic performance parameters are threshold-dependent. Sensitivity with a low threshold (TPa/diseased patients) is greater than sensitivity with a higher threshold (TPb/diseased patients). Specificity with a low threshold (TNa/nondiseased patients) is less than specificity with a high threshold (TNb/nondiseased patients). TP indicates true positive; TN, true negative; FP, false positive; FN, false negative.
- fig 2.
A–C, The perfect test (A) has an area under the curve (AUC) of 1. The useless test (B) has an AUC of 0.5. The typical test (C) has an AUC between 0.5 and 1. The greater the AUC (ie, excellent > good > fair), the better the diagnostic performance
- fig 3.
Validity and reliability of a test.
A, Good validity and reliability means the center of the target is always hit by different gunmen.
B, Good reliability but poor validity means the same area of the target is hit by different gunmen but off center.
C, Poor reliability of the test means the bullets are spread out, all over the target, with a few hitting the center. In the hands of a few gunmen a test can be valid, since the center of the target is hit.
- fig 4.
A and B, Although the mean is the same for study populations of both small (A) and large (B) patient samples, the CI narrows as the number of subjects increases.
- fig 5.
Flow diagram summarizes the key steps required to do sound clinical research
In this issue
Jump to section
- Article
- Assessing the Research Field
- Designing the Study
- Mathematical Analysis and Statistics
- Limitations
- Diagnostic Technology and Technique
- How Much Does the Research Study Cost?
- Starting the Research Project
- Finishing the Research Project
- Making Available the Scientific Results
- Sound Research Is Not Done Overnight
- Conclusion
- Acknowledgments
- Footnotes
- References
- Other Suggested Readings
- Figures & Data
- Info & Metrics
- Responses
- References
Related Articles
Cited By...
- Clinical applications of imaging biomarkers. Part 1. The neuroradiologist's perspective
- Determination of Carotid Artery Atherosclerotic Lesion Type and Distribution in Hypercholesterolemic Patients With Moderate Carotid Stenosis Using Noninvasive Magnetic Resonance Imaging
- Hemorrhage in the Atherosclerotic Carotid Plaque: A High-Resolution MRI Study
- Is diffusion imaging appearance an independent predictor of outcome after ischemic stroke?