PARCCS: A Machine Learning Risk-Prediction Model for Acute Peripartum Cardiovascular Complications During Delivery Admissions
Authors' conclusion
PARCCS has the potential to be an important tool for identifying pregnant individuals at risk of acute peripartum CV complications at the time of delivery.
Study context
- Population
- Delivery admissions, US National Inpatient Sample (2016–2020)
- Participants
- 2,371,661 pregnant patients
- Outcome
- Acute CV/renal complications during delivery:
- Pre-eclampsia/eclampsia
- Peripartum cardiomyopathy
- Renal complications
- VTE
- Arrhythmias
- Pulmonary edema
- Follow-up
- Delivery hospitalization
Methodological detailsrisk prediction model development, machine learning, validation set
- Risk prediction model development
- Machine learning
- Validation set
Main finding
As reported in the abstract
Discrimination of PARCCS for acute CV complications (validation set)
AUC of the model (ROC), validation set
0.68
95% CI 0.67 to 0.68
Observational data: associations, not effects.
Further findings
Incidence of acute cardiovascular (CV) complications during delivery hospitalization
- Acute CV complications
- 7.0%
PARCCS variables (points)
- Electrolyte imbalances
- 13
- Age <20 years
- 3
- Cesarean delivery
- 4
- Obesity
- 5
- Pre-existing HF
- 28
- Multiple gestations
- 4
- Black race
- 2
- Gestational hypertension
- 3
- Low income
- 1
- Gestational diabetes
- 2
- Chronic diabetes
- 6
- Prior stroke
- 22
- Coagulopathy
- 5
- Nonelective admission
- 2
Characteristics of patients with CV complications
- Higher prevalence of comorbidities; more likely Black race and lower income
Original publication
PARCCS: A Machine Learning Risk-Prediction Model for Acute Peripartum Cardiovascular Complications During Delivery Admissions. JACC Adv. Published 22 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →