Use of health administrative data to identify migraine in individuals with a recognized pregnancy: A validation study in Ontario, Canada.

Abstract

Background: Migraine is a common risk factor for adverse perinatal outcomes, showing the importance of studying migraine in pregnancy. Despite growing use of routinely collected administrative data in health research, the validity of such data to detect migraine in pregnant populations is unestablished. We validated algorithms to identify a history of migraine among pregnant individuals using health administrative data and population-representative self-report data.

Methods: We included n=8824 females in Ontario, Canada with a documented pregnancy with an estimated conception date from 09/01/2005 to 12/31/2021 who completed the Canadian Community Health Survey (CCHS) within 5 years before conception. We created algorithms using different combinations of diagnostic codes for headache disorders and migraine-specific drug claims with varying lookback periods before conception. We compared their performance to self-reported migraine diagnosis from the CCHS. Measures of validity were sensitivity, specificity, predictive values, and agreement.

Results: The prevalence of self-reported migraine from the CCHS was 18% (95%CI 16%-19%). The prevalence using administrative data depended on the definition (range: 2%-25%). All algorithms had high specificity (81.7-98.9%), while sensitivity varied (6.1-53.2%). The algorithm requiring ≥2 physician visits or ≥1 hospitalizations or emergency department visits with diagnostic codes ICD-9: 346/ICD-10: G43, with a lifetime lookback, had high specificity (94.0%; 95%CI 93.1%-94.8%) and negative predictive value (86.3%; 95%CI 85.0%-87.6%) and modest sensitivity (30.4%; 95%CI 27.3%-33.6%) and positive predictive value (51.9%; 95%CI 46.8%-57.0%). Agreement was fair (κ = 0.29; 95%CI 0.25-0.33).

Conclusion: Longitudinally linked health administrative data are effective at identifying pregnant individuals with migraine, with high specificity and reasonable sensitivity.