Accuracy and precision plan
Specify paired measures and uncertainty
Sensitivity uses reference-positive participants; specificity uses reference-negative participants. Positive and negative predictive values also depend on the clinical population. Preserve indeterminate and incompletely verified results rather than silently deleting them.
Flow diagram
Steps
Define accuracy measures
Specify sensitivity, specificity and any predictive values for the intended setting.
Define paired evaluable data
Define the paired index-test and reference-standard dataset. Retain missing, failed and indeterminate results with reasons and assess incomplete verification rather than silently restricting to complete pairs.
Specify precision and size rationale
Plan diseased and nondiseased information requirements.
Specify estimation and comparisons
Define intervals, paired comparisons, thresholds and dependence.
Plan sensitivity for incomplete verification
Assess missing, indeterminate and verification mechanisms.
Interpret clinical applicability
Assess sensitivity and specificity in the intended spectrum and predictive values at relevant prevalence. Accuracy alone does not establish improvement in patient outcomes.
Accuracy and precision plan
End flow
Tables and supporting information
Paired test table shell
Do not populate observed counts until analysis; track missing and indeterminate results separately.
Accuracy precision scenarios
Enter verified calculations only.
Accuracy definitions
TP, FN, TN and FP refer to paired index/reference classifications. Define populations and thresholds; no values are calculated.