Cargando…

Understanding racial disparities in severe maternal morbidity using Bayesian network analysis

Previous studies have evaluated the marginal effect of various factors on the risk of severe maternal morbidity (SMM) using regression approaches. We add to this literature by utilizing a Bayesian network (BN) approach to understand the joint effects of clinical, demographic, and area-level factors....

Descripción completa

Detalles Bibliográficos
Autores principales: Rezaeiahari, Mandana, Brown, Clare C., Ali, Mir M., Datta, Jyotishka, Tilford, J. Mick
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550416/
https://www.ncbi.nlm.nih.gov/pubmed/34705872
http://dx.doi.org/10.1371/journal.pone.0259258
Descripción
Sumario:Previous studies have evaluated the marginal effect of various factors on the risk of severe maternal morbidity (SMM) using regression approaches. We add to this literature by utilizing a Bayesian network (BN) approach to understand the joint effects of clinical, demographic, and area-level factors. We conducted a retrospective observational study using linked birth certificate and insurance claims data from the Arkansas All-Payer Claims Database (APCD), for the years 2013 through 2017. We used various learning algorithms and measures of arc strength to choose the most robust network structure. We then performed various conditional probabilistic queries using Monte Carlo simulation to understand disparities in SMM. We found that anemia and hypertensive disorder of pregnancy may be important clinical comorbidities to target in order to reduce SMM overall as well as racial disparities in SMM.