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.

Prediction of lactate concentrations after cardiac surgery using machine learning and deep learning approaches.

Background: Although conventional prediction models for surgical patients often ignore intraoperative time-series data, deep learning approaches are well-suited to incorporate time-varying and non-linear data with complex interactions. Blood lactate concentration is one important clinical marker that can reflect the adequacy of systemic perfusion during cardiac surgery. During cardiac surgery and cardiopulmonary bypass, minute-level data is available on key parameters that affect perfusion. The goal of this study was to use machine learning and deep learning approaches to predict maximum blood lactate concentrations after cardiac surgery. We hypothesized that models using minute-level intraoperative data as inputs would have the best predictive performance. Methods: Adults who underwent cardiac surgery with cardiopulmonary bypass were eligible. The primary outcome was maximum lactate concentration within 24 h postoperatively. We considered three classes of predictive models, using the performance metric of mean absolute error across testing folds: (1) static models using baseline preoperative variables, (2) augmentation of the static models with intraoperative statistics, and (3) a dynamic approach that integrates preoperative variables with intraoperative time series data. Results: 2,187 patients were included. For three models that only used baseline characteristics (linear regression, random forest, artificial neural network) to predict maximum postoperative lactate concentration, the prediction error ranged from a median of 2.52 mmol/L (IQR 2.46, 2.56) to 2.58 mmol/L (IQR 2.54, 2.60). The inclusion of intraoperative summary statistics (including intraoperative lactate concentration) improved model performance, with the prediction error ranging from a median of 2.09 mmol/L (IQR 2.04, 2.14) to 2.12 mmol/L (IQR 2.06, 2.16). For two modelling approaches (recurrent neural network, transformer) that can utilize intraoperative time-series data, the lowest prediction error was obtained with a range of median 1.96 mmol/L (IQR 1.87, 2.05) to 1.97 mmol/L (IQR 1.92, 2.05). Intraoperative lactate concentration was the most important predictive feature based on Shapley additive values. Anemia and weight were also important predictors, but there was heterogeneity in the importance of other features. Conclusion: Postoperative lactate concentrations can be predicted using baseline and intraoperative data with moderate accuracy. These results reflect the value of intraoperative data in the prediction of clinically relevant outcomes to guide perioperative management.

Right ventricular diastolic dysfunction and failure: a review.

Right ventricular diastolic dysfunction and failure (RVDDF) has been increasingly identified in patients with cardiovascular diseases, including heart failure and other diseases with cardiac involvement. It is unknown whether RVDDF exists as a distinct clinical entity; however, its presence and degree have been shown to be a sensitive marker of end-organ dysfunction related to multiple disease processes including systemic hypertension, pulmonary hypertension, heart failure, and endocrine disease. In this manuscript, we review issues pertaining to RVDDF including anatomic features of the right ventricle, physiologic measurements, RVDDF diagnosis, underlying mechanisms, clinical impact, and clinical management. Several unique features of RVDDF are also discussed.

On-label compared to off-label four-factor prothrombin complex concentrate use: a retrospective, observational study.

BACKGROUND: Four-factor prothrombin complex concentrate (4F-PCC) is US Food and Drug Administration approved for the urgent reversal of coagulation factor deficiency induced by a vitamin K antagonist complicated by acute major bleeding or in situations in which invasive procedures are urgently needed. Although recent evidence suggests the superiority of 4F-PCC over plasma for on-label indications, the off-label use of 4F-PCC has not been rigorously studied. STUDY DESIGN AND METHODS: Eighty-nine patients receiving 4F-PCC at a single institution from July 2016 to December 2017 were retrospectively analyzed. Two cohorts, "On-Label" and "Off-Label" uses of 4F-PCC, were evaluated, comparing patient characteristics, blood utilization, and clinical outcomes including in-hospital mortality. RESULTS: Patients receiving 4F-PCC for off-label reasons (n = 46) were younger and sicker compared to those receiving 4F-PCC for on-label reasons (n = 43). Notably, the mortality rate for off-label use was approximately twofold greater than the mortality rate for on-label use (26 of 46 [56.5%] vs. 12 of 43 [27.9%]; p = 0.006). Patients receiving 4F-PCC for off-label reasons received more units per patient of each blood component than their on-label counterparts. The average cost estimate per patient for 4F-PCC was similar (approx. $4300) in each cohort. CONCLUSION: 4F-PCC is an effective but expensive treatment option for those requiring urgent reversal of vitamin K antagonist-induced coagulopathy. However, providers should be conscious of the high costs and questionable efficacy when using 4F-PCC off-label.

Network injury to pulvinar with neonatal arterial ischemic stroke.

The purpose of this study is to establish that newborn stroke involving extensive parts of cerebral cortex immediately leads to secondary network injury in pulvinar. Seven term infants with cortical stroke presented with hypersignal in pulvinar on DWI. Stroke types included: complete MCA stroke (n=4); PCA stroke, ICA stroke and multiple artery stroke (1 each). Age range at scanning was between day 2 and 6 after birth (except for 1 infant scanned within 7 days of acute presentation during ECMO). ADC values in secondarily injured pulvinar were significantly higher than in the area with primary (sub)cortical injury (all patients scanned with identical MR image acquisition). In the absence of asphyxia and because pulvinar is outside of the primary area of infarction, we conclude that there are suggestions from imaging for acute secondary injury to pulvinar following primary damage of their cortical targets and/or connecting axons. Acute secondary injury is probably due to excitotoxicity and deafferentiation. The relevance of network injury for prognosis and the impact of early treatment on it have yet to be studied, in stroke but also in other acute perinatal brain disorders.