Fluid overload is common after neonatal congenital cardiac surgery (CCS) and is frequently managed with continuous furosemide infusions requiring iterative dose titration. An interpretable prediction model could support more consistent early postoperative dosing decisions. We hypothesized that a novel, interpretable machine learning approach could accurately predict furosemide dosing decisions in neonates following CCS. We identified term neonates admitted to the Pediatric Cardiothoracic ICU at a large academic children’s hospital between 8/1/2014 and 3/1/2023 following CCS with cardiopulmonary bypass. Demographic and clinical data from the first 48 postoperative hours were used to train, validate, and test a Tropical Geometry–Based Fuzzy Neural Network Regressor (TGFNN-R) tasked with predicting furosemide infusion dose changes after CCS. The TGFNN-R was primed with clinician heuristics and provides transparent explanations behind predictions. A held-out internal validation/testing cohort was drawn from the same single-center population. Data from 506 neonates were extracted; 398 received a continuous furosemide infusion. Mean age at surgery was 6.2 (± 5.1) days; 67.3

IMPORTANCE:Excessive cognitive load impairs task performance and contributes to burnout, but studies of cognitive load in pediatric critical care medicine (PCCM) settings are limited. OBJECTIVES:To better understand cognitive load in an academic PCCM setting and how cognitive load differs based on experience, role, task type, and task frequency. DESIGN, SETTINGS, AND PARTICIPANTS:Prospective two-part survey at a quaternary children's hospital PCCM department. Part 1 (February to March 2022) assessed routine role-specific tasks; part 2 (June to August 2022) evaluated acute resuscitation. Participants were registered nurses (RNs), respiratory therapists (RTs), and physicians + advanced practice providers (APPs). MAIN OUTCOMES AND MEASURES:Raw cognitive load (1-9 Paas scale), net cognitive load (Paas × task frequency), and NASA-Task Load Index (NASA-TLX) subdomain scores (0-100) for acute resuscitation. Role was the primary exposure; between-group differences were analyzed using analysis of variance with pairwise comparisons. RESULTS:There were 109-part 1 and 79-part 2 survey respondents. Across all tasks, mean raw Paas scores were highest for physicians + APPs (5.2 ± 1.1), followed by RNs (4.8 ± 1.0) and RTs (4.0 ± 1.4; p = 0.004). In the three highest-load shared tasks-acute resuscitation, rescuing a decompensating patient, and managing advanced life-support devices-RNs reported significantly higher raw load than physicians + APPs and RTs. For bedside patient assessment, RNs had higher net cognitive load (25.0 ± 8.7) than physicians + APPs (20.3 ± 7.0; p = 0.01) and RTs (18.9 ± 8.9; p = 0.01). Nursing experience correlated with overall net cognitive load (r = 0.30; p = 0.02). During resuscitation, RNs reported higher NASA-TLX scores than other providers in all but two subdomains. CONCLUSIONS AND RELEVANCE:Cognitive load in PCCM varies significantly by role and task type. Nurses experience high raw cognitive load from critical events and net cognitive load from bedside patient assessment, suggesting opportunities for role-specific workflow redesign and cognitive load reduction strategies to benefit staff and patients.

This review sought to highlight the foundational principles of cognitive load for pediatric cardiologists and surgeons in high-stakes care environments. Measurement of cognitive load is evolving beyond retrospective and subjective numeric rating scales to include multimodal physiologic measurements that scale with cognitive load. Frequent interruptions, distractions, and task switching that characterize high-stakes cardiology environments increase cognitive load. Excessive cognitive load is increasingly associated with tangible consequences for patients, including medical errors. Cognitive load theory is based on the idea that working memory resources are finite. When working memory demands exceed available capacity, such as under high cognitive load, task performance suffers. Psychometric, behavioral, and physiological methods can be used to measure cognitive load. Strategies for reducing cognitive load in high-stakes cardiology environments include increasing automation, improving visualization, leveraging machine learning for clinical decision support, promoting crisis resource management, utilizing simulation, and optimizing human factors/systems engineering.

Machine learning (ML) has the potential to transform patient care and outcomes. However, there are important differences between measuring the performance of ML models in silico and usefulness at the point of care. One lens to use to evaluate models during early development is actionability, which is currently undervalued. We propose a metric for actionability intended to be used before the evaluation of calibration and ultimately decision curve analysis and calculation of net benefit. Our metric should be viewed as part of an overarching effort to increase the number of pragmatic tools that identify a model’s possible clinical impacts.

Pediatric intensivists are bombarded with more patient data than ever before. Integration and interpretation of data from patient monitors and the electronic health record (EHR) can be cognitively expensive in a manner that results in delayed or suboptimal medical decision making and patient harm. Machine learning (ML) can be used to facilitate insights from healthcare data and has been successfully applied to pediatric critical care data with that intent. However, many pediatric critical care medicine (PCCM) trainees and clinicians lack an understanding of foundational ML principles. This presents a major problem for the field. We outline the reasons why in this perspective and provide a roadmap for competency-based ML education for PCCM trainees and other stakeholders.

Electronic health records in critical care medicine offer unprecedented opportunities for clinical reasoning and decision making. Paradoxically, these data-rich environments have also resulted in clinical decision support systems (CDSSs) that fit poorly into clinical contexts, and increase health workers cognitive load. In this paper, we introduce a novel approach to designing CDSSs that are embedded in clinical workflows, by presenting problem-based curated data views tailored for problem-driven discovery, team communication, and situational awareness. We describe the design and evaluation of one such CDSS, In-Sight, that embodies our approach and addresses the clinical problem of monitoring critically ill pediatric patients. Our work is the result of a co-design process, further informed by empirical data collected through formal usability testing, focus groups, and a simulation study with domain experts. We discuss the potential and limitations of our approach, and share lessons learned in our iterative co-design process.

Background: Early warning systems that utilize dense physiologic data and machine learning may aid prediction of decompensation after congenital heart surgery (CHS). The Compensatory Reserve Index (CRI) analyzes changing features of the pulse waveform to predict hemodynamic decompensation in adults, but it has never been studied after CHS. This study sought to understand the feasibility, safety, and potential utility of CRI monitoring after CHS with cardiopulmonary bypass (CPB). Methods: A single-center prospective pilot cohort of patients undergoing pulmonary valve replacement was studied. Compensatory Reserve Index was continuously measured from preoperative baseline through the first 24 postoperative hours. Average CRI values during selected procedural phases were compared between patients with an intensive care unit (ICU) length of stay (LOS) <3 days versus LOS ≥3 days. Results: Twenty-three patients were enrolled. On average, 17,445 (±3,152) CRI data points were collected and 0.33% (±0.40) of data were missing per patient. There were no adverse events related to monitoring. Five (21.7%) patients had an ICU LOS ≥3 days. Compared to the ICU LOS <3 days group, the ICU LOS ≥3 days group had a greater decrease in CRI from baseline to immediately after CPB (−0.3 ± 0.1 vs −0.1 ± 0.2, P = .003) and were less likely to recover to baseline CRI during the monitoring period (20% vs 83%, P = .017). Conclusions: Compensatory Reserve Index monitoring after CHS with CPB seems feasible and safe. Early changes in CRI may precede meaningful clinical outcomes, but this requires further study.

Background: Major Depressive Disorder (MDD) has been linked in the literature to poorer prognosis in patients with cardiovascular dysfunction, although the mechanisms of this relationship remain unclear. Underlying Sleep Disordered Breathing (SDB) serves as a potential candidate to explain this effect due to its downstream effects on inflammatory activation and decreased nitric oxide (NO) bioavailability, both of which have been shown to contribute to the pathophysiology of both MDD and cardiovascular disease (CVD). Methods: This study utilizes overnight polysomnography and an inflammation panel to examine the links between cardiovascular dysfunction and sleep difficulties in control participants and patients diagnosed with SDB only, MDD only, and both SDB and MDD. Results: Results demonstrate a strong positive relationship between sleep dysfunction and the nitric oxide synthesis inhibitor Symmetric Dimethyl Arginine (SDMA) in the MDD-only cohort, suggesting a link between SDMA-mediated NO dysregulation and CVD pathogenesis in individuals with MDD. Additionally, hypopneas, a form of sleep impairment characterized by partial reduction of airflow, were found to play a significant role in the relationship between SDB and cardiovascular dysfunction in MDD-only patients. Conclusions: Results of this study demonstrate the need for widespread screening for SDB in MDD populations to detect predisposition to CVD, and also offer SDMA as a new potential target for CVD treatment in individuals with MDD.

Background Comparison of care among centers is currently limited to major end points, such as mortality, length of stay, or complication rates. Creating “care curves” and comparing individual elements of care over time may highlight modifiable differences in intensive care among centers. Methods and Results We performed an observational retrospective study at 5 centers in the United States to describe key elements of postoperative care following the stage 1 palliation. A consecutive sample of 502 infants undergoing stage 1 palliation between January 2009 and December 2018 were included. All electronic health record entries relating to mandatory mechanical ventilator rate, opioid administration, and fluid intake/outputs between postoperative days (POD) 0 to 28 were extracted from each institution's data warehouse. During the study period, 502 patients underwent stage 1 palliation among the 5 centers. Patients were weaned to a median mandatory mechanical ventilator rate of 10 breaths/minute by POD 4 at Center 5 but not until POD 7 to 8 at Centers 1 and 2. Opioid administration peaked on POD 2 with extreme variance (median 6.9 versus 1.6 mg/kg per day at Center 3 versus Center 2). Daily fluid balance trends were variable: on POD 3 Center 1 had a median fluid balance of −51 mL/kg per day, ranging between −34 to 19 mL/kg per day among remaining centers. Intercenter differences persist after adjusting for patient and surgical characteristics (P<0.001 for each end point). Conclusions It is possible to detail and compare individual elements of care over time that represent modifiable differences among centers, which persist even after adjusting for patient factors. Care curves may be used to guide collaborative quality improvement initiatives.

Major depressive disorder (MDD), found in females at rates 2x higher than males, has been linked to increased incidence of cardiovascular disease (CVD). Sleep-disordered breathing (SDB), commonly associated with MDD, shows higher mortality in females and has been shown to increase cardiovascular risk due to increased inflammation and decreased bioavailability of nitric oxide (NO). In order to better understand cardiovascular risk in MDD, we investigated the separate and additive effects of MDD and SDB by sex on these cardiovascular risk biomarkers.

This review sought to highlight the current paradigms and emerging treatment options for two common and serious problems after congenital cardiac surgery: low cardiac output syndrome (LCOS) and vasoplegia. Low cardiac output syndrome and vasoplegia remain prevalent after congenital cardiac surgery. Recent studies on adjunctive agents for LCOS have not shown consistent improvements in patient outcomes. Recent studies of targeted vasoconstrictors, adjunctive nitric oxide antagonists, and perioperative corticosteroids have limitations precluding their routine use in pediatric patients after congenital cardiac surgery. The treatment of LCOS is predicated on approaches that improve cardiac output by augmentation of heart rate, contractility, preload, and minimization of afterload. Strategies that minimize tissue oxygen demand can also be helpful to restore matching of tissue oxygen delivery and demand. The hallmark of vasoplegia treatment is augmentation of systemic vascular tone. A variety of emerging therapies are under investigation for their role in LCOS and vasoplegia after congenital cardiac surgery, but none are ready for routine use.

Introduction: Comparisons of care among centers is currently limited to major endpoints, such as mortality, length of stay, or complication rates. Hypothesis: We hypothesized that comparing individual elements of intensive care over time using classical statistics and “care curves” may highlight important modifiable differences among centers. Methods: We retrospectively reviewed data of key elements of postoperative care after stage-1-palliation (S1P) among 5 US centers during 2009-2018. Minimum mandatory ventilation rate (MMVR), opioid total daily dose (TDD) and fluid balance (FB) were computed from postoperative day (POD) 0 to 28. Cox regression, mixed random effect models and growth chart-like care curves were used to analyze data variability and trajectory over time. Results: During the study period, 502 patients underwent S1P (median age 5 [IQR 3-6] days). Patients were weaned from MMV by POD 8 (IQR 5-16), with significant differences among centers (P<0.001). Opioid administration peaked on POD 2 (3.7 [IQR 1.5-7.5] mg morphine equivalents/kg/day), and freedom from opioids was achieved in a median of 13 (IQR 8-25) days (P<0.001 among centers). After adjusting for patient-level characteristics, center affiliation was independently predictive of time to freedom from MMV and from opioids. The median daily FB per patient was +23 (IQR -3 to +39) ml/kg/day (P<0.001 among centers). Center affiliation was independently predictive of both trajectories over time and daily variation in MMVR, opioid TDD, and FB. Growth chart-like care curves can be used to visualize variation in elements over time (Fig1). Conclusions: Both “care curves” and classical statistics highlighted important modifiable differences in the elements of care among centers. MMVR, opioid TDD, and FB following S1P significantly differ even after adjusting for patient and operative factors. Care curves may be used to guide collaborative quality improvement initiatives in the intensive care unit.

Patients with congenital heart disease (CHD) who undergo cardiac procedures may become hemodynamically unstable. Predictive algorithms that utilize dense physiologic data may be useful. The compensatory reserve index (CRI) trends beat-to-beat progression from normovolemia (CRI = 1) to decompensation (CRI = 0) in hemorrhagic shock by continuously analyzing unique sets of features in the changing pulse photoplethysmogram (PPG) waveform. We sought to understand if the CRI accurately reflects changing hemodynamics during and after a cardiac procedure for patients with CHD. A transcatheter pulmonary valve replacement (TcPVR) model was used because left ventricular stroke volume decreases upon sizing balloon occlusion of the right ventricular outflow tract (RVOT) and increases after successful valve placement. A single-center, prospective cohort study was performed. The CRI was continuously measured to determine the change in CRI before and after RVOT occlusion and successful TcPVR. Twenty-six subjects were enrolled with a median age of 19 (interquartile range (IQR) 13–29) years. The mean (± standard deviation) CRI decreased from 0.66 ± 0.15 1-min before balloon inflation to 0.53 ± 0.16 (p = 0.03) 1-min after balloon deflation. The mean CRI increased from a pre-valve mean CRI of 0.63 [95% confidence interval (CI) 0.56–0.70] to 0.77 (95% CI 0.71–0.83) after successful TcPVR. In this study, the CRI accurately reflected acute hemodynamic changes associated with TcPVR. Further research is justified to determine if the CRI can be useful as an early warning tool in patients with CHD at risk for decompensation during and after cardiac procedures.

Objective To test the hypothesis that specific echocardiographic measurements of right ventricular (RV) mechanics at 36 weeks postmenstrual age (PMA) are associated with the severity of bronchopulmonary dysplasia (BPD). Study design A subset of 93 preterm infants (born between 27 and 29 weeks of gestation) was selected retrospectively from a prospectively enrolled cohort. BPD was defined using the National Institutes of Health workshop definition, with modifications for oxygen reduction testing and altitude. The cohort was divided into no-BPD and BPD groups using previously published methodology for analyses. Echocardiographic measurements of RV function (ie, tricuspid annular plane systolic excursion, fractional area of change, systolic-to-diastolic ratio, tissue Doppler myocardial performance index, and RV strain), RV remodeling/morphology (end-systolic left ventricular eccentricity index), and RV afterload (pulmonary artery acceleration time measure) were evaluated at 36 weeks PMA. Multivariable logistic regression determined associations between RV measurements and BPD severity. Results Compared with the no-BPD cohort, the BPD group had lower birth weight z-scores (P= .04) and trended toward a male predominance (P= .08). After adjusting for birth weight z-score, gestational age, and sex, there were no between-group differences in echocardiographic measurements except for the eccentricity index (scaled OR [0.1-unit increase], 1.49; 95% Cl, 1.13-2.12; P= .01). Conclusions Among conventional and emerging echocardiographic measurements of RV mechanics, eccentricity index was the sole variable independently associated with BPD severity in this study. The eccentricity index may be a useful echocardiographic measurement for characterizing RV mechanics in patients with BPD at 36 weeks PMA.

BACKGROUND Feeding practices after neonatal and congenital heart surgery are complicated and variable, which may be associated with prolonged hospitalization length of stay (LOS). Systematic assessment of feeding skills after cardiac surgery may earlier identify those likely to have protracted feeding difficulties, which may promote standardization of care. METHODS Neonates and infants ≤3 months old admitted for their first cardiac surgery were retrospectively identified during a 1-year period at a single center. A systematic feeding readiness assessment (FRA) was utilized to score infant feeding skills. FRA scores were assigned immediately prior to surgery and 1, 2, and 3 weeks after surgery. FRA scores were analyzed individually and in combination as predictors of gastrostomy tube (GT) placement prior to hospital discharge by logistic regression. RESULTS Eighty-six patients met inclusion criteria and 69 patients had complete data to be included in the final model. The mean age of admit was five days and 51% were male. Forty-six percent had single ventricle physiology. Twenty-nine (42%) underwent GT placement. The model containing both immediate presurgical and 1-week postoperative FRA scores was of highest utility in predicting discharge with GT (intercept odds = 10.9, P = .0002; sensitivity 69%, specificity 93%, AUC 0.913). The false positive rate was 7.5%. CONCLUSIONS In this analysis, systematic and standardized measurements of feeding readiness employed immediately before and one week after congenital cardiac surgery predicted need for GT placement prior to hospital discharge. The FRA score may be used to risk stratify patients based on likelihood of prolonged feeding difficulties, which may further improve standardization of care.

Background: Infants with shunt-dependent pulmonary blood flow are at risk for developing proximal pulmonary artery (PA) stenosis, which may result in morbidity and mortality. Transthoracic echocardiography (TTE) is the primary means of surveillance for PA narrowing but has significant limitations and has not been compared to computed tomographic angiography (CTA)–derived measurements of the proximal PA anatomy in this population. Methods: A retrospective chart review identified infants with shunt-dependent pulmonary blood flow who had both TTE and CTA performed <14 days apart during a five-year period. Proximal right pulmonary artery (RPA) and left pulmonary artery (LPA) diameters were measured by TTE and CTA. Pulmonary artery z-score, linear and intraclass correlation (ICC) coefficients, and Bland-Altman plots were computed. Results: Seventeen pairs of studies were analyzed. The TTE and CTA proximal PA diameters had moderate linear correlation and agreement (R = 0.67, P ≤ .0001, ICC = 0.65); the RPA showed stronger correlation and agreement (R = 0.76, P = .0004, ICC = 0.72) than the LPA (R = 0.59, P = .01, ICC = 0.59). Computed tomographic angiography detected missed PA stenosis (Z score < −2) in five (14.7%) cases, four of which were on the LPA. Conclusion: In this study of infants with shunt-dependent pulmonary blood flow, TTE and CTA proximal PA diameters had only moderate correlation and agreement overall, which was worse when comparing LPA measurements. This resulted in missed PA stenosis by TTE. Computed tomographic angiography may be warranted in patients with poorly visualized PAs by TTE or suspicion for deficient pulmonary blood flow.