Inferring pregnancy episodes and outcomes within a network of observational databases

Abstract

Administrative claims and electronic health records are valuable resources for evaluating pharmaceutical effects during pregnancy. However, direct measures of gestational age are generally not available. Establishing a reliable approach to infer the duration and outcome of a pregnancy could improve pharmacovigilance activities. We developed and applied an algorithm to define pregnancy episodes in four observational databases: three US-based claims databases: Truven MarketScan® Commercial Claims and Encounters (CCAE), Truven MarketScan® Multi-state Medicaid (MDCD), and the Optum ClinFormatics® (Optum) database and one non-US database, the United Kingdom (UK) based Clinical Practice Research Datalink (CPRD). Pregnancy outcomes were classified as live births, stillbirths, abortions and ectopic pregnancies. Start dates were estimated using a derived hierarchy of available pregnancy markers, including records such as last menstrual period and nuchal ultrasound dates. Validation included clinical adjudication of 700 electronic Optum and CPRD pregnancy episode profiles to assess the operating characteristics of the algorithm, and a comparison of the algorithm's Optum pregnancy start estimates to starts based on dates of assisted conception procedures. Distributions of pregnancy outcome types were similar across all four data sources and pregnancy episode lengths found were as expected for all outcomes, excepting term lengths in episodes that used amenorrhea and urine pregnancy tests for start estimation. Validation survey results found highest agreement between reviewer chosen and algorithm operating characteristics for questions assessing pregnancy status and accuracy of outcome category with 99-100% agreement for Optum and CPRD. Outcome date agreement within seven days in either direction ranged from 95-100%, while start date agreement within seven days in either direction ranged from 90-97%. In Optum validation sensitivity analysis, a total of 73% of algorithm estimated starts for live births were in agreement with fertility procedure estimated starts within two weeks in either direction; ectopic pregnancy 77%, stillbirth 47%, and abortion 36%. An algorithm to infer live birth and ectopic pregnancy episodes and outcomes can be applied to multiple observational databases with acceptable accuracy for further epidemiologic research. Less accuracy was found for start date estimations in stillbirth and abortion outcomes in our sensitivity analysis, which may be expected given the nature of the outcomes.

Fig 1. Illustration of steps performed by pregnancy episode algorithm for sample patient with three classified pregnancy episodes and estimated start dates.

LB: Live birth; SB: Stillbirth; ECT: Ectopic pregnancy; SA: Abortion; PCONF: Pregnancy confirmation marker; ULS: Nuchal ultrasound; AMEN: Amenorrhea record.

Fig 2. Distribution of pregnancy algorithm start estimation method groups for all pregnancy episodes from each data source (CPRD, Optum, Truven CCAE, and Truven MDCD) by outcome (abortion, ectopic pregnancy, live birth, and stillbirth).

Legend for start estimation methods in stacked bars: Group 1 = last menstrual period, gestational age record, fertility procedure; Group 2 = alpha-fetoprotein test, nuchal ultrasound; Group 3 = amenorrhea record, urine pregnancy test record; Group 4 = average gestational age estimate.

Fig 3. Distribution of duration of all pregnancy episodes, with episode lengths shown in 10 day increments for live births, stratified by method of pregnancy start estimation and data source (CPRD, Optum, Truven CCAE, and Truven MDCD).

Legend for start estimation methods referenced in row panels: LMP = last menstrual period GEST = gestational age record INFERT = fertility procedure ULS = nuchal ultrasound AFP = alpha-fetoprotein test AMEN = amenorrhea record URINE = urine pregnancy record AVG = gestational age estimate ALL = all start estimation methods combined.

Fig 4. Performance rating for five operating characteristics of algorithm (survey questions 1,2,4–6) from electronic profile review survey.

Fig 5. The distribution of reviewer estimated pregnancy start difference in days from the algorithm start (< -14, -8 thru -14, -1 thru -7, 0, 1 through 7, 8 through 14 and > 14 days) in the Optum database, stratified by pregnancy outcome (all outcomes, live birth, abortion, ectopic pregnancy, and stillbirth) and method used for pregnancy start estimation.

Legend for start estimation methods referenced in row panels: LMP = last menstrual period GEST = gestational age record INFERT = fertility procedure ULS = nuchal ultrasound AFP = alpha-fetoprotein test AMEN = amenorrhea record URINE = urine pregnancy record AVG = average gestational age estimate ALL = all start estimation methods combined *If percentages do not add up to 100%, reviewer indicated difference in days from the algorithm could not be determined.

Fig 6. The distribution of reviewer estimated pregnancy start difference in days from the algorithm start (< -14, -8 thru -14, -1 thru -7, 0, 1 through 7, 8 through 14 and > 14 days) in the CPRD database, stratified by pregnancy outcome (all outcomes, live birth, abortion, ectopic pregnancy, and stillbirth) and method used for pregnancy start estimation.

Legend for start estimation methods referenced in row panels: LMP = last menstrual period GEST = gestational age record INFERT = fertility procedure ULS = nuchal ultrasound AFP = alpha-fetoprotein test AMEN = amenorrhea record URINE = urine pregnancy record AVG = average gestational age estimate ALL = all start estimation methods combined *If percentages do not add up to 100%, reviewer indicated difference in days from the algorithm could not be determined.