SB-C03 · report validation qualification
Classification and audit outcome: report validation qualification; supported with reporting ambiguity.
Finding
Current amendment or qualification
Reported accuracy was92.4%; five-fold internal cross-validation was described. No external validation was performed; the displayed result is not separately labelled resubstitution versus adjusted accuracy. Preserve the length-of-stay future-information warning.
Remaining limitation: Use reported accuracy with described internal CV. Do not rebrand92.4% as definitely cross-validated. Cross-validation is internal validation despite contradictory source Limitations wording. Preserve LOS future-information warning.
Evidence and provenance
Methods model development/validation; Results decision tree
- Heegoo Kim, Chanmi Lee, Nayeong Kim, Eunhye Chung, HyeongMin Jeon, Seyoung Shin, et al. Early functional factors for predicting outcome of independence in daily living after stroke: a decision tree analysis. Journal of rehabilitation medicine. 2024. DOI 10.2340/jrm.v56.35095 · Original source
Affected reports
Original audit locator(s): paragraph 194; table 13, row 4
Audit corrections describe the report only where that classification is explicit. A disagreement within a study, missing protocol, statistical query, access upgrade or optional addition is not silently converted into a report error or a new clinical threshold.
Audit register · Unresolved evidence queue
Linked knowledge pages
- COND-STROKE Stroke
Located in this vault
Mapping status: exact. An exact location match is not an additional empirical verification.