Causal inference in studies of preterm babies: A simulation study

J. M. Snowden, O. Basso

Research output: Research - peer-reviewArticle

Abstract

Using a simple simulation, we illustrate why associations estimated from studies restricted to preterm births cannot be interpreted causally. Data simulation involving a hypothetical cohort of fetuses who may be healthy or have one or more of four pathological factors (termed A through D, increasing in severity) with known effects on gestational length and risk of mortality. We focus on babies born at ≤32 weeks of gestation. We visually represent the simulated population and compare the association between A (which may represent pre-eclampsia) and neonatal death. We then repeat the exercise with D (standing in for chorioamnionitis) as the exposure of interest. Odds ratios of neonatal death in the simulated data. In most weeks, and for both A and D, the calculated odds ratios are substantially biased and underestimate the true risk of neonatal death associated with each pathology. For example, factor A has a true causal odds ratio of 1.50, yet it appears protective among births ≤32 weeks (estimated crude odds ratio 0.39; gestational age-adjusted odds ratio 0.71). Among very preterm births, virtually all babies are born with pathologies that increase the risk of adverse outcomes. Hence, babies exposed to one factor (e.g. pre-eclampsia) are compared with babies who have a mix of other pathologies. Such selection bias affects studies carried out among very preterm births (e.g. where pre-eclampsia appears to reduce risk of adverse neonatal outcomes). Selection bias affects studies of preterm births, complicating interpretation.

LanguageEnglish (US)
JournalBJOG: An International Journal of Obstetrics and Gynaecology
DOIs
StateAccepted/In press - 2017

Fingerprint

Odds Ratio
Premature Birth
Pre-Eclampsia
Pathology
Perinatal Death
Selection Bias
Chorioamnionitis
Gestational Age
Fetus
Parturition
Pregnancy
Mortality
Population

Keywords

  • Causal inference
  • Neonatal networks
  • Perinatal epidemiology
  • Preterm birth

ASJC Scopus subject areas

  • Obstetrics and Gynecology

Cite this

@article{dbfb117cb35f45afb0ad70c795291089,
title = "Causal inference in studies of preterm babies: A simulation study",
abstract = "Using a simple simulation, we illustrate why associations estimated from studies restricted to preterm births cannot be interpreted causally. Data simulation involving a hypothetical cohort of fetuses who may be healthy or have one or more of four pathological factors (termed A through D, increasing in severity) with known effects on gestational length and risk of mortality. We focus on babies born at ≤32 weeks of gestation. We visually represent the simulated population and compare the association between A (which may represent pre-eclampsia) and neonatal death. We then repeat the exercise with D (standing in for chorioamnionitis) as the exposure of interest. Odds ratios of neonatal death in the simulated data. In most weeks, and for both A and D, the calculated odds ratios are substantially biased and underestimate the true risk of neonatal death associated with each pathology. For example, factor A has a true causal odds ratio of 1.50, yet it appears protective among births ≤32 weeks (estimated crude odds ratio 0.39; gestational age-adjusted odds ratio 0.71). Among very preterm births, virtually all babies are born with pathologies that increase the risk of adverse outcomes. Hence, babies exposed to one factor (e.g. pre-eclampsia) are compared with babies who have a mix of other pathologies. Such selection bias affects studies carried out among very preterm births (e.g. where pre-eclampsia appears to reduce risk of adverse neonatal outcomes). Selection bias affects studies of preterm births, complicating interpretation.",
keywords = "Causal inference, Neonatal networks, Perinatal epidemiology, Preterm birth",
author = "Snowden, {J. M.} and O. Basso",
year = "2017",
doi = "10.1111/1471-0528.14942",
journal = "BJOG: An International Journal of Obstetrics and Gynaecology",
issn = "1470-0328",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Causal inference in studies of preterm babies

T2 - BJOG: An International Journal of Obstetrics and Gynaecology

AU - Snowden,J. M.

AU - Basso,O.

PY - 2017

Y1 - 2017

N2 - Using a simple simulation, we illustrate why associations estimated from studies restricted to preterm births cannot be interpreted causally. Data simulation involving a hypothetical cohort of fetuses who may be healthy or have one or more of four pathological factors (termed A through D, increasing in severity) with known effects on gestational length and risk of mortality. We focus on babies born at ≤32 weeks of gestation. We visually represent the simulated population and compare the association between A (which may represent pre-eclampsia) and neonatal death. We then repeat the exercise with D (standing in for chorioamnionitis) as the exposure of interest. Odds ratios of neonatal death in the simulated data. In most weeks, and for both A and D, the calculated odds ratios are substantially biased and underestimate the true risk of neonatal death associated with each pathology. For example, factor A has a true causal odds ratio of 1.50, yet it appears protective among births ≤32 weeks (estimated crude odds ratio 0.39; gestational age-adjusted odds ratio 0.71). Among very preterm births, virtually all babies are born with pathologies that increase the risk of adverse outcomes. Hence, babies exposed to one factor (e.g. pre-eclampsia) are compared with babies who have a mix of other pathologies. Such selection bias affects studies carried out among very preterm births (e.g. where pre-eclampsia appears to reduce risk of adverse neonatal outcomes). Selection bias affects studies of preterm births, complicating interpretation.

AB - Using a simple simulation, we illustrate why associations estimated from studies restricted to preterm births cannot be interpreted causally. Data simulation involving a hypothetical cohort of fetuses who may be healthy or have one or more of four pathological factors (termed A through D, increasing in severity) with known effects on gestational length and risk of mortality. We focus on babies born at ≤32 weeks of gestation. We visually represent the simulated population and compare the association between A (which may represent pre-eclampsia) and neonatal death. We then repeat the exercise with D (standing in for chorioamnionitis) as the exposure of interest. Odds ratios of neonatal death in the simulated data. In most weeks, and for both A and D, the calculated odds ratios are substantially biased and underestimate the true risk of neonatal death associated with each pathology. For example, factor A has a true causal odds ratio of 1.50, yet it appears protective among births ≤32 weeks (estimated crude odds ratio 0.39; gestational age-adjusted odds ratio 0.71). Among very preterm births, virtually all babies are born with pathologies that increase the risk of adverse outcomes. Hence, babies exposed to one factor (e.g. pre-eclampsia) are compared with babies who have a mix of other pathologies. Such selection bias affects studies carried out among very preterm births (e.g. where pre-eclampsia appears to reduce risk of adverse neonatal outcomes). Selection bias affects studies of preterm births, complicating interpretation.

KW - Causal inference

KW - Neonatal networks

KW - Perinatal epidemiology

KW - Preterm birth

UR - http://www.scopus.com/inward/record.url?scp=85032726751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032726751&partnerID=8YFLogxK

U2 - 10.1111/1471-0528.14942

DO - 10.1111/1471-0528.14942

M3 - Article

JO - BJOG: An International Journal of Obstetrics and Gynaecology

JF - BJOG: An International Journal of Obstetrics and Gynaecology

SN - 1470-0328

ER -