Dataset Information

PARCCS: A Machine Learning Risk-Prediction Model for Acute Peripartum Cardiovascular Complications During Delivery Admissions.

ABSTRACT:

Background

Maternal mortality in the United States remains high, with cardiovascular (CV) complications being a leading cause.

Objectives

The purpose of this paper was to develop the PARCCS (Prediction of Acute Risk for Cardiovascular Complications in the Peripartum Period Score) for acute CV complications during delivery.

Methods

Data from the National Inpatient Sample (2016-2020) and International Classification of Diseases, Tenth Revision codes to identify delivery admissions were used. Acute CV/renal complications were defined as a composite of pre-eclampsia/eclampsia, peripartum cardiomyopathy, renal complications, venous thromboembolism, arrhythmias, and pulmonary edema. A risk prediction model, PARCCS, was developed using machine learning consisting of 14 variables and scored out of 100 points.

Results

Of the 2,371,661 pregnant patients analyzed, 7.0% had acute CV complications during delivery hospitalization. Patients with CV complications had a higher prevalence of comorbidities and were more likely to be of Black race and lower income. The PARCCS variables included electrolyte imbalances (13 points [p]), age (3p for age <20 years), cesarean delivery (4p), obesity (5p), pre-existing heart failure (28p), multiple gestations (4p), Black race (2p), gestational hypertension (3p), low income (1p), gestational diabetes (2p), chronic diabetes (6p), prior stroke (22p), coagulopathy (5p), and nonelective admission (2p). Using the validation set, the performance of the model was evaluated with an area under the receiver-operating characteristic curve of 0.68 and a 95% CI of 0.67 to 0.68.

Conclusions

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. Future studies should further validate this score and determine whether it can improve patient outcomes.

SUBMITTER: Zahid S

PROVIDER: S-EPMC11318475 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

PARCCS: A Machine Learning Risk-Prediction Model for Acute Peripartum Cardiovascular Complications During Delivery Admissions.

Zahid Salman S Jha Shikha S Kaur Gurleen G Jung Youn-Hoa YH Minhas Anum S AS Hays Allison G AG Michos Erin D ED

JACC. Advances 20240722 8

<h4>Background</h4>Maternal mortality in the United States remains high, with cardiovascular (CV) complications being a leading cause.<h4>Objectives</h4>The purpose of this paper was to develop the PARCCS (Prediction of Acute Risk for Cardiovascular Complications in the Peripartum Period Score) for acute CV complications during delivery.<h4>Methods</h4>Data from the National Inpatient Sample (2016-2020) and International Classification of Diseases, Tenth Revision codes to identify delivery admis ...[more]

PMID: 39135918

Similar Datasets

Project description:Background and purposePeripartum strokes during delivery admissions are rare but have high maternal morbidity. Infections have been proposed as a possible stroke trigger. We hypothesized that women who had infections diagnosed at the time of delivery admission would have higher risk of stroke during their delivery hospitalization.MethodsWe conducted a case-control study using state inpatient administrative databases for California (2007-2011), Florida (2009-2011), and New York (2009-2011). Women whose admission included a vaginal or cesarean delivery, with a new diagnosis of stroke during the admission, were considered cases and were randomly matched to 3 in-state controls by age/admission year and presence and severity of hypertensive disorders of pregnancy. The primary exposure of interest was infection of any type present on admission. Secondary exposures included race/ethnicity, payer status, delivery method, and known vascular risk factors such as chronic hypertension, diabetes mellitus, smoking, alcohol abuse, hypercoagulable states, coagulopathies, and renal disease. We used multivariable conditional logistic regression to estimate the odds ratios and 95% confidence intervals for the association of infections and known vascular risk factors with stroke risk.ResultsA total of 455 cases (mean age, 29.8), of whom 195 (42.9%) had hypertensive disorders of pregnancy, were matched with 1365 controls. Infection of any type present on admission increased the odds of stroke diagnosis during the admission (adjusted odds ratio, 1.74; 95% confidence interval, 1.29-2.35). Risk was higher for genitourinary infections (adjusted odds ratio, 2.56; 95% confidence interval, 1.25-5.24) and sepsis (adjusted odds ratio, 10.4; 95% confidence interval, 2.15-20.0). The association between infection and stroke during delivery admission did not differ by the presence of hypertensive disorders of pregnancy.ConclusionsInfections present on admission increased stroke risk during delivery admissions in women with and without hypertensive disorders of pregnancy. The results were driven by genitourinary infections and sepsis. Infections may be an underrecognized precipitant of peripartum stroke.

Project description:ImportanceIndividuals with systemic lupus erythematosus (SLE) have an increased risk of pregnancy-related complications. However, data on acute cardiovascular complications during delivery admissions remain limited.ObjectiveTo investigate whether SLE is associated with an increased risk of acute peripartum cardiovascular complications during delivery hospitalization among individuals giving birth.Design, setting, and participantsThis population-based cross-sectional study was conducted with data from the National Inpatient Sample (2004-2019) by using International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) or International Statistical Classification of Diseases and Related Health Problems, Tenth Revision, Clinical Modification (ICD-10-CM) codes to identify delivery hospitalizations among birthing individuals with a diagnosis of SLE. A multivariable logistic regression model was developed to report an adjusted odds ratio (OR) for the association between SLE and acute peripartum cardiovascular complications. Data were analyzed from May 1 through September 1, 2022.ExposureDiagnosed SLE.Main outcomes and measuresPrimary study end points were preeclampsia, peripartum cardiomyopathy, and heart failure. Secondary end points included ischemic and hemorrhagic stroke, pulmonary edema, cardiac arrhythmias, acute kidney injury (AKI), venous thromboembolism (VTE), length of stay, and cost of hospitalization.ResultsA total of 63 115 002 weighted delivery hospitalizations (median [IQR] age, 28 [24-32] years; all were female patients) were identified, of which 77 560 hospitalizations (0.1%) were among individuals with SLE and 63 037 442 hospitalizations (99.9%) were among those without SLE. After adjustment for age, race and ethnicity, comorbidities, insurance, and income level, SLE remained an independent risk factor associated with peripartum cardiovascular complications, including preeclampsia (adjusted OR [aOR], 2.12; 95% CI, 2.07-2.17), peripartum cardiomyopathy (aOR, 4.42; 95% CI, 3.79-5.13), heart failure (aOR, 4.06; 95% CI, 3.61-4.57), cardiac arrhythmias (aOR, 2.06; 95% CI, 1.94-2.21), AKI (aOR, 7.66; 95% CI, 7.06-8.32), stroke (aOR, 4.83; 95% CI, 4.18-5.57), and VTE (aOR, 6.90; 95% CI, 6.11-7.80). For resource use, median (IQR) length of stay (3 [2-4] days vs 2 [2-3] days; P < .001) and cost of hospitalization ($4953 [$3305-$7517] vs $3722 [$2606-$5400]; P < .001) were higher for deliveries among individuals with SLE.Conclusions and relevanceThis study found that SLE was associated with increased risk of complications, including preeclampsia, peripartum cardiomyopathy, heart failure, arrhythmias, AKI, stroke, and VTE during delivery hospitalization and an increased length and cost of hospitalization.

Dataset Information

PARCCS: A Machine Learning Risk-Prediction Model for Acute Peripartum Cardiovascular Complications During Delivery Admissions.

Background

Objectives

Methods

Results

Conclusions

Publications

PARCCS: A Machine Learning Risk-Prediction Model for Acute Peripartum Cardiovascular Complications During Delivery Admissions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets