Prediction threshold selection contract ======================================= StatMedAnalysis | Original downloadable worksheet | 6 November 2026 Separate choosing a decision threshold from evaluating its consequences. How to use this worksheet State the intended action and relative consequences of false positives and false negatives. Choose a threshold rule using development data or prior decision requirements. Freeze it before independent evaluation. Report performance at the chosen threshold with denominators and uncertainty. Save a working copy and keep the original blank version. Use public, hypothetical or aggregate information only; do not enter patient identifiers, credentials or confidential records. Keep source evidence in your approved project workspace. Mark unresolved text fields UNKNOWN or NOT REPORTED with a reason; never substitute zero for an unknown count. Project/version __________________ Prepared by role/date __________________ Working fields 1. Clinical or operational action Response/evidence: _________________________________________________________ ___________________________________________________________________________ 2. False-positive consequence Response/evidence: _________________________________________________________ ___________________________________________________________________________ 3. False-negative consequence Response/evidence: _________________________________________________________ ___________________________________________________________________________ 4. Threshold selection dataset Response/evidence: _________________________________________________________ ___________________________________________________________________________ 5. Prespecified rule or utility rationale Response/evidence: _________________________________________________________ ___________________________________________________________________________ 6. Frozen threshold and date Response/evidence: _________________________________________________________ ___________________________________________________________________________ 7. Independent evaluation sample Response/evidence: _________________________________________________________ ___________________________________________________________________________ 8. Sensitivity to alternative thresholds Response/evidence: _________________________________________________________ ___________________________________________________________________________ Hypothetical worked case A fictional model threshold is chosen to maximize a metric in the test set. Reporting performance at that threshold on the same set is optimistic because the test outcomes influenced the decision rule. Decision rule and limitations Evaluate a selected threshold on data not used to choose it when possible. A statistically convenient threshold is not automatically clinically useful. Decision _______________________ Remaining uncertainty ____________________ Next action ____________________ Owner / review date ______________________ Independent check and discrepancy resolution _______________________________ Official method or reporting reference checked 6 November 2026 https://scikit-learn.org/stable/model_selection.html This is an original planning aid, not an official checklist, validated instrument, clinical recommendation or certificate of expert approval. Apply the referenced guidance to the specific design and record any additional requirements.