Diagnostic performance and ROC curve software for method validation
ROC curve analysis per EP24-A2 and qualitative test evaluation per EP12-A2 — AUC comparison, optimal threshold determination, and diagnostic accuracy metrics.
Establish the diagnostic accuracy of your test
A measurement procedure that’s precise and linear can still be clinically useless if it can’t reliably distinguish positive from negative cases. Diagnostic performance tells you how well the test discriminates, what threshold to use, and how it compares against other tests or the current standard. IVD manufacturers need this for product labelling and regulatory submissions; clinical laboratories need it when evaluating new tests or validating existing ones.
Analyse-it has been a tremendous help. I’ve published and presented at national cardiology meetings and couldn’t have accomplished most of my research without it. Using Analyse-it, I even found errors or omissions in the work of our statistician!
Regina S. Druz, MD, FACC, FASNC
Director, Nuclear Cardiology
North Shore University Hospital
Analyse-it covers both quantitative tests (EP24-A2 ROC curve analysis) and qualitative tests (EP12-A2). Examine a single test, or compare up to 10 paired or independent tests with DeLong AUC comparison. Find optimal decision thresholds based on Youden index or cost of misdiagnosis. Sensitivity, specificity, likelihood ratios, predictive values, and all the standard accuracy metrics with appropriate confidence intervals.
What's included
ROC curves for quantitative tests
Diagnostic performance for 1 test, up to 10 paired tests, or up to 10 independent tests. Wilcoxon-Mann-Whitney AUC with DeLong confidence intervals. Z test of AUC better than chance.
Compare tests statistically
DeLong difference in AUC between tests. Equality, equivalence, and non-inferiority tests — determine whether a new test is comparable, equivalent, or not unacceptably worse.
Find the optimal decision threshold
Decision plot showing sensitivity vs specificity, likelihood ratios, predictive values, or cost across all possible thresholds. Optimal threshold by Youden index or cost of diagnosis/misdiagnosis.
Sensitivity, specificity, and all the accuracy metrics
Sensitivity, specificity, likelihood ratios, predictive values, odds ratio, and Youden’s index with appropriate confidence intervals. Bi-histogram and dot-plot of positive/negative outcomes.
Qualitative test evaluation per EP12-A2
Sensitivity and specificity with Clopper-Pearson exact or Wilson score CIs. Difference between paired tests with Newcombe CIs and Score Z test. Mosaic plot of outcomes.
Example analyses
See diagnostic performance results in detail — ROC curves, AUC comparison, threshold determination, and qualitative test evaluation — using CLSI example datasets you can download and follow along with.
EP24-A2 — Appendix D
OxLDL and LDL diagnostic accuracy.
Two paired tests. ROC curves, AUC with DeLong CIs. DeLong comparison of AUC between tests. Bi-histogram and decision plot.
EP12-A2 — Example 10.3.1
H. pylori qualitative test evaluation.
Two paired tests against true state. Sensitivity, specificity, predictive values with Wilson CIs. Difference with Newcombe CIs and Score Z test. Mosaic plots.
EP12-A2 — Example 10.3.2
H. pylori method comparison.
HM-CAP EIA vs Immunochromatic. Proportion in positive and negative agreement with Wilson CIs.
Validated, reliable, trusted for over 30-years
Validated calculations you can defend at inspection
Every calculation by Analyse-it, no Excel formulas, and no third-party functions. Validated against CLSI reference datasets, published datasets, and thousands of internal test cases. Defensible in a 510(k), CE-IVD technical file, CAP inspection, or ISO 15189 audit. See how we
develop and validate Analyse-it →
Data stays in your facility
Analyse-it runs entirely within Excel on your PC. No cloud processing, no data transmission.
Your pre-submission and patient-adjacent data stays within your facility under your data governance controls.
Standard Excel workbooks
Analyses are ordinary Excel workbooks that you can share with colleagues, archive for audit, and open on any machine with Excel — no Analyse-it licence required.
No formulas to break
Results contain no formulas, so they can’t be accidentally edited or corrupted. The results you reported will be exactly what you find when you reopen the workbook.
Technical details
CLSI protocols
- EP24-A2: Assessment of the Diagnostic Accuracy of Laboratory Tests Using Receiver Operating Characteristic Curves
- EP12-A2: User Protocol for Evaluation of Qualitative Test Performance
ROC (quantitative)
- 1 test, up to 10 paired tests, or up to 10 independent tests/groups
- Wilcoxon-Mann-Whitney AUC with DeLong CIs
- Z test of AUC better than chance
- DeLong difference in AUC: equality, equivalence, non-inferiority
- Predict FPF at fixed sensitivity, sensitivity at fixed FPF, or both at fixed threshold
Threshold determination
- Decision plot: sensitivity vs specificity, likelihood ratios, predictive values, or cost
- Optimal threshold by Youden index or cost of diagnosis/misdiagnosis
Accuracy metrics (ROC)
- Sensitivity / specificity
- Positive / negative likelihood ratios
- Positive / negative predictive values
- Odds ratio
- Youden’s index
- TP, TN, FP, FN counts
Qualitative (EP12-A2)
- 1 test, 2 paired tests, or 2 independent tests/groups
- Sensitivity/specificity (Clopper-Pearson exact, Wilson score CIs)
- Likelihood ratios (Miettinen-Nurminen score CIs)
- Predictive values (Mercado-Wald logit CIs)
- Difference in sensitivity/specificity (Newcombe, Tango score CIs)
- McNemar-Mosteller exact, Fisher exact, Score Z test
Plots
- ROC curve with no-discrimination line
- Decision plot
- Bi-histogram of positive/negative outcomes new in v4.00
- Dot-plot of positive/negative outcomes new in v4.00
- Mosaic plot (qualitative)
