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

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.

Regional Differences in the US in Outcomes with Preeclampsia.

This study explores preeclampsia outcomes across US regions and examines regional differences in specific preeclampsia-associated pregnancy complications and disease management. Patient-reported measures were obtained from The Preeclampsia Registry, an open-access database composed of women with at least one pregnancy diagnosed with a hypertensive disorder of pregnancy. Pregnancies and associated outcomes were stratified by US region (Northeast, Midwest, South and West). Among 2,667 pregnancies of which 92% were in White women, maximum systolic blood pressure at any time in pregnancy was highest among women in the South and Midwest (p=0.039). Furthermore, more women in the South received pre-pregnancy antihypertensives (p=0.026) and antenatal steroids (p=0.025) and delivered at an earlier gestational age (p=0.014) compared to women in other regions. Pregnancy complications such as elevated liver enzymes were higher in women in the South (p=0.019), and women in the South and West had additional end-organ damage such as renal complications (p<0.001) and hemolysis (p=0.008) as compared to women in other regions. Further investigation is needed to assess whether healthcare access or policy could be contributing to these regional discrepancies.

A Machine Learning-Derived Score to Effectively Identify Heart Failure With Preserved Ejection Fraction.

Background: The diagnosis of heart failure with preserved ejection fraction (HFpEF) in the clinical setting remains challenging, especially in patients with obesity. Objectives: This study aimed to identify novel predictors of HFpEF well suited for patients with obesity. Methods: We performed a retrospective analysis of a well-characterized cohort of patients with obesity with HFpEF (n = 404; mean body mass index [BMI] 36.6 kg/m2) and controls (n = 67). We used the machine learning algorithm Gradient Boosting Machine to analyze the association of various parameters with the diagnosis of HFpEF and subsequently created a multivariate logistic model for the diagnosis. Results: Gradient Boosting Machine identified BMI, estimated glomerular filtration rate, left ventricular mass index, and left atrial to left ventricular volume ratio as the strongest predictors of HFpEF. These variables were used to build a model that identified HFpEF with a sensitivity of 0.83, a specificity of 0.82, and an area under the curve (AUC) of 0.88. Internal validation of the model with optimism-adjusted AUC showed an AUC of 0.87. Within the studied cohort, the novel score outperformed the H2FPEF score (AUC: 0.88 vs 0.74; P < 0.001). Conclusions: In a HFpEF cohort with obesity, BMI, estimated glomerular filtration rate, left ventricular mass index, and left atrial to left ventricular volume ratio most correlated with the identification of HFpEF, and a score based on these variables (HFpEF-JH score) outperformed the currently used H2PEF score. Further validation of this novel score is warranted, as it may facilitate improved diagnostic accuracy of HFpEF, particularly in patients with obesity.

Association of Lipoprotein(a) with peri-coronary inflammation in persons with and without HIV infection.

BACKGROUND: Persons with human immunodeficiency virus (HIV) (PWH) have an increased risk of developing cardiovascular disease (CVD) compared to persons without HIV (PWoH). Lipoprotein(a) [Lp(a)] is a known atherosclerotic risk factor in PWoH, but there are no studies investigating Lp(a) and peri-coronary inflammation. OBJECTIVE: To investigate whether Lp(a) is associated with peri-coronary inflammation as assessed by the fat attenuation index (FAI) and activated monocytes and T lymphocytes in PWH and PWoH. METHODS: We measured plasma levels of Lp(a) at study entry in 58 PWH and 21 PWoH without CVD and who had FAI measurements. Associations of Lp(a) with FAI values of the right coronary artery (RCA) and left anterior descending artery were evaluated using multivariable regression models adjusted for potential confounders. Correlations between Lp(a) levels and systemic inflammatory markers and immune cell subsets were examined. RESULTS: Lp(a) was associated with greater peri-coronary inflammation among PWH compared to PWoH (ß=1.73, P=0.019) in the RCA, in adjusted models. Significant correlations were observed with certain inflammatory markers (tumor necrosis factor receptor [TNFR]-I, b=0.295, P<0.001; TNFR-II, b=0.270, P=0.002; high-sensitivity C-reactive protein, b=0.195, P=0.028). Significant correlations were found between Lp(a) levels and several markers of monocyte activation: CD16 -CD163+ (b= -0.199, P=0.024), and CD16 -DR+ MFI (b= -0.179, P=0.042) and T cell subset CD38+CD4+ TEMRA (b= 0.177, P= 0.044). CONCLUSIONS: Lp(a) was associated with greater peri-coronary inflammation in the RCA in PWH compared to PWoH, as well as with select systemic inflammatory markers and specific subsets of immune cells in peripheral circulation.

Association of Gestational Diabetes With Subclinical Cardiovascular Disease.

Background: Gestational diabetes mellitus (GDM) is associated with increased long-term risk of cardiovascular disease but the cardiovascular structural and functional changes that contribute to risk are not well understood. Objectives: The purpose of this study was to determine whether GDM is associated with adverse cardiac remodeling and endothelial dysfunction a decade after delivery, independent of type 2 diabetes. Methods: Women with deliveries between 2008 and 2009 were initially selected from a prospective clinical cohort. Pregnancy history was chart abstracted and a follow-up study visit was conducted at 8 to 10 years postpartum. Cardiac structure and function were assessed with echocardiography. Endothelial function was measured with peripheral arterial tonometry and glycocalyx analysis. Results: Among 254 women assessed at an average age of 38 years, 53 (21%) had prior GDM. At follow-up, women with GDM had more incident prediabetes or diabetes (58% vs 20% without GDM), more impairment in peripheral arterial tonometry (reactive hyperemia 1.58 vs 1.95; P = 0.01) and reduced perfusion, a marker of glycocalyx assessment (red blood cell filling 0.70 ± 0.04 vs 0.72 ± 0.05; P < 0.01). Despite adjustment for demographic and reproductive characteristics, women with GDM had great septal wall thickness by 8% (95% CI: 2.3%-14.7%) and worse diastology with higher E/E' by 11% (95% CI: 1.1%-21.5%). After additional adjustment for diabetes and prediabetes, several parameters remained significantly impaired. Conclusions: Having GDM within the past decade was associated with more adverse cardiac structure/function and vascular endothelial function. Some, but not all, risks may be mediated through the development of prediabetes or type 2 diabetes. Enhanced preventive efforts are needed to mitigate cardiovascular risk among women with GDM.

Virtual cardiovascular magnetic resonance training proves feasible and effective: survey data from international participants of the CMR Academy Berlin, Germany.

Aims: This study aims to evaluate the success of the cardiovascular magnetic resonance (CMR) imaging Academy Berlin's transition from in-person to online CMR imaging training during the global pandemic 2020 and to gather recommendations for future courses. Methods and results: We conducted an online survey targeting CMR course participants from both the pre-pandemic, in-person era and the pandemic, online era of the CMR Academy Berlin. The survey primarily used Likert-type questions to assess participants' experiences and preferences.A total of 61 out of 158 invited participants (38.61%) completed the survey, with 31 (50.82%) being in-person alumni and 30 (49.18%) being online alumni. Both in-person [83.87% (26/31)] and online [83.33% (25/30)] participants rated the course as either 'very good' or 'excellent', and both groups found the course either 'extremely helpful' or 'very helpful'. However, a higher percentage of in-person participants [96.77% (30/31)] felt comfortable asking questions compared to online participants [83.33% (25/30); P = 0.025]. The majority in both groups preferred a written exam [total: 75.41% (46/61); in-person alumni: 77.42% (24/31); online alumni 73.33% (22/30)]. In terms of course format preferences, in-person courses were preferred by both in-person alumni [38.71% (12/31)] and online alumni [60% (18/30)], almost as much as a hybrid format combining in-person and online elements [in-person alumni: 41.94% (13/31), online alumni: 30% (9/30)]. Conclusion: The transition from in-person to online CMR training at the CMR Academy Berlin was successful in maintaining overall satisfaction. However, there is room for improvement in terms of increased interaction, particularly for online participants. Future CMR- and potentially also cardiac computer tomography-courses should consider adopting a hybrid format to accommodate participants' preferences and enhance their learning experience, especially to gain level II competency, whereas level I virtual only might be sufficient.

The COVID-19 pandemic has greatly changed the landscape of medical education, necessitating the shift from traditional in-person learning to online platforms. This study evaluated how well an online training programme for cardiovascular magnetic resonance imaging (CMR) was received by doctors who attended the CMR Academy in Berlin, Germany. We asked both in-person and online course participants about their experiences and preferences for future courses. A total of 61 out of 158 participants (38.61%) responded to our survey. Both in-person and online attendees rated the course as either 'very good' or 'excellent'. However, more in-person attendees felt comfortable asking questions during the course compared to online attendees. In terms of future courses, most of the participants preferred a blend of in-person and online learning, known as a hybrid format. They felt that online learning had some benefits, such as increased access, especially during a pandemic. However, they missed the interaction and engagement that in-person learning provides. They also preferred written exams to be conducted online. This study emphasizes the need for future CMR training to be more flexible and include both online and in-person elements. This would not only accommodate the participants' preferences but also enhance their learning experience. It also stresses the importance of interaction during the learning process, which needs to be improved in online platforms. The findings can potentially inform the development of educational frameworks in other areas of medical imaging, like cardiac computer tomography (CT).

Racial and Socioeconomic Disparities in Cardiovascular Outcomes of Preeclampsia Hospitalizations in the United States 2004-2019.

Background: Preeclampsia is associated with higher in-hospital cardiovascular events and mortality with known disparities by race/ethnicity, but data on the interaction between income and these outcomes remain limited. Objectives: This study investigated racial and socioeconomic disparities in cardiovascular outcomes of preeclampsia at delivery hospitalizations. Methods: We analyzed National Inpatient Sample data using International Classification of Diseases-9th Revision/-10th Revision codes between 2004 and 2019. We identified a total of 2,436,991 delivery hospitalizations with preeclampsia/eclampsia as a primary diagnosis representing White (43.1%), Black (18.4%), Hispanic (18.7%), and Asian or Pacific Islander (A/PI; 3.3%) women. We stratified the population based on median household income (low income, medium income, and high income). Logistic regression and propensity-matched analysis were used for reporting outcomes adjusted for age, hospital region, and baseline comorbidities. Results: Black Hispanic, and A/PI women with preeclampsia had higher in-hospital mortality compared with White women across all groups of income. Hispanic women had lower odds of peripartum cardiomyopathy (PPCM) compared with White women. A significant interaction effect was observed with race/ethnicity and median household income for in-hospital mortality and PPCM with preeclampsia. Furthermore, high-income Black women had higher odds of PPCM, stroke, acute kidney injury, heart failure, cardiac arrhythmia, and venous thromboembolism compared with low-income White women. Conclusions: Women with preeclampsia experience significant racial/ethnic and socioeconomic disparities in inpatient mortality and cardiovascular outcomes at delivery. Across all income groups, Black, Hispanic, and A/PI women experience higher odds of in-hospital mortality compared with White women. Furthermore, high-income Black women had greater odds of many CV complications compared with low-income White women.