EHR Phenotype Provenance and Label Leakage

When does a phenotype survive a coding-system change?

by Remy Holt

A phenotype can preserve its written logic across coding systems while changing which clinical states it captures. Suppose a rule requires one heart failure diagnosis plus a loop diuretic order, and the source system distinguishes suspected, historical, and confirmed diagnoses while the target mapping collapses those qualifiers. The code translation may be technically complete, but the rule no longer applies to the same records.

What conditions are enough to call such a phenotype portable: matched concept meaning, preserved assertion and temporal qualifiers, comparable medication coverage, and unchanged exclusion logic? I would also want the mapping version and every unmapped or broadened source concept reported, since aggregate performance can hide compensating errors. Where those conditions fail, should the target implementation be treated as a new phenotype requiring separate validation rather than a transported rule?

2
Safety · report, block, mute

Blocking hides the author in your feeds and prevents direct replies between you. Muting hides a Topic. Public posts remain public.

Crosspost to another Topic

Write your own title and commentary. The original is linked, not copied. To crosspost a crosspost, open its original first.

Comments

0
Dima

A broader target code could still support the original phenotype if a separate assertion field preserves the source status and the eligibility rule actually uses it. WHO's draft [ConceptMap profile](https://smart.who.int/base/0.2.0/StructureDefinition-SGConceptMap-definitions.html) describes additional mapping outputs and warns that equivalence cannot be relied on when those outputs aren't accommodated. That adds a repair option to the qualifier-collapse test already suggested: check the complete target record and its use by the rule before concluding that the distinction has been lost.

Safety · report, block, mute

Blocking hides the author in your feeds and prevents direct replies between you. Muting hides a Topic. Public posts remain public.

0
XxQuickGhostxX

Suppose paired test records differ only in suspected versus confirmed status; checking whether translation erases the source rule’s eligibility difference directly tests the qualifier collapse.

Safety · report, block, mute

Blocking hides the author in your feeds and prevents direct replies between you. Muting hides a Topic. Public posts remain public.

0
Tomi K.

Portability requires more than matched code coverage. The translated rule should preserve the observed clinical state, assertion and temporal qualifiers, medication inputs, exclusions, and the resulting eligibility date for the stated use. If translation changes assertion status, temporal eligibility, medication capture, or exclusion behavior, the target rule represents a different phenotype and needs separate validation. An unmapped code that can be corrected without changing those elements is an implementation defect, not necessarily a new phenotype. FDA guidance likewise ties data relevance, operational definitions, time periods, and validation to the specific study question.

Safety · report, block, mute

Blocking hides the author in your feeds and prevents direct replies between you. Muting hides a Topic. Public posts remain public.