Inadequate oxygen delivery index dose is associated with cardiac arrest risk in neonates following cardiopulmonary bypass surgery

Pediatric Tele-Critical Care: Initial Experience with a Continuous Surveillance Model Aiming to Prevent Cardiac Arrest in Children with Critical Heart Disease

Introduction: Despite advances in treatment of children with critical heart disease, cardiac arrest (CA) remains a common occurrence. We provided virtual support to bedside teams (BTs) from a tele-critical care (TCC) unit in a pediatric cardiac intensive care unit (CICU) and focused on early detection of concerning trends (CT) and avoidance of CA. Virtual surveillance workflows included a review of remote monitoring, video feed from patient room cameras, medical records, and artificial intelligence tools. We present our initial experience with a focus on critical communications (CCs) to BTs. Methods: A retrospective, descriptive review of TCC activities was conducted from January 2019 to December 2022, involving electronic databases and electronic medical records of patients in the CICU, including related CCs to BTs, responses from BTs, and related CA. Results: We conducted 18,171 TCC activities, including 2,678 non-CCs and 248 CCs. Over time, there was a significant increase in the proportion of CCs related with CT (p = 0.002), respiratory concerns (<0.001), and abnormalities in cardiac rhythm (p = 0.04). Among a sample of 244 CCs, subsequent interventions by BTs resulted in adjustment of medical treatment (127), respiratory support (68), surgery or intervention (19), cardiac rhythm control (17), imaging study (14), early resuscitation (9), and others (10). Conclusions: CCs from a TCC unit in a pediatric CICU changed over time with an increased focus on CT and resulted in early interventions, potentially contributing to avoiding CA. This model of care in pediatric cardiac critical care has the potential to improve patient safety.

A Near Real-Time Risk Analytics Algorithm Predicts Elevated Lactate Levels in Pediatric Cardiac Critical Care Patients

BACKGROUND

Postoperative pediatric congenital heart patients are predisposed to develop low-cardiac output syndrome. Serum lactate (lactic acid [LA]) is a well-defined marker of inadequate systemic oxygen delivery.

OBJECTIVES

We hypothesized that a near real-time risk index calculated by a noninvasive predictive analytics algorithm predicts elevated LA in pediatric patients admitted to a cardiac ICU (CICU).

DERIVATION COHORT

Ten tertiary CICUs in the United States and Pakistan.

VALIDATION COHORT

Retrospective observational study performed to validate a hyperlactatemia (HLA) index using T3 platform data (Etiometry, Boston, MA) from pediatric patients less than or equal to 12 years of age admitted to CICU (n = 3,496) from January 1, 2018, to December 31, 2020. Patients lacking required data for module or LA measurements were excluded.

PREDICTION MODEL

Physiologic algorithm used to calculate an HLA index that incorporates physiologic data from patients in a CICU. The algorithm uses Bayes' theorem to interpret newly acquired data in a near real-time manner given its own previous assessment of the physiologic state of the patient.

RESULTS

A total of 58,168 LA measurements were obtained from 3,496 patients included in a validation dataset. HLA was defined as LA level greater than 4 mmol/L. Using receiver operating characteristic analysis and a complete dataset, the HLA index predicted HLA with high sensitivity and specificity (area under the curve 0.95). As the index value increased, the likelihood of having higher LA increased (p < 0.01). In the validation dataset, the relative risk of having LA greater than 4 mmol/L when the HLA index is less than 1 is 0.07 (95% CI: 0.06-0.08), and the relative risk of having LA less than 4 mmol/L when the HLA index greater than 99 is 0.13 (95% CI, 0.12-0.14).

CONCLUSIONS

These results validate the capacity of the HLA index. This novel index can provide a noninvasive prediction of elevated LA. The HLA index showed strong positive association with elevated LA levels, potentially providing bedside clinicians with an early, noninvasive warning of impaired cardiac output and oxygen delivery. Prospective studies are required to analyze the effect of this index on clinical decision-making and outcomes in pediatric population.

The Inadequate Oxygen Delivery Index and Its Correlation with Venous Saturation in the Pediatric Cardiac Intensive Care Unit

Continuous monitoring software, T3, has an integrated index called the inadequate oxygen delivery index 50% (IDO2-50) which displays a probability that the mixed venous saturation is below a user-selected threshold of 30-50%. The primary aim of this study was to determine the correlation of the IDO2-50 with a measured venous saturation. The secondary aim of this study was to characterize the hemodynamic factors that contributed to the IDO2-50. This single-center, retrospective study aimed to characterize the correlation between IDO2-50 and inferior vena cava (IVC) saturation. A Bayesian Pearson correlation was conducted to assess the correlation between the collected variables of interest, with a particular interest in the correlation between the IDO2-50 and the IVC saturation. Receiver operator curve (ROC) analysis to assess the ability of the IDO2-50 to identify when the venous saturation was less than 50%. Bayesian linear regression was done with the IDO2-50 (dependent variable) and other independent variables. A total of 113 datasets were collected across 15 unique patients. IDO2-50 had moderate correlation with the IVC saturation (correlation coefficient - 0.569). The IDO2-50 had a weak but significant correlation with cerebral near-infrared spectroscopy (NIRS) values, a weak but significant correlation with heart rate, and a moderate and significant correlation with arterial saturation. ROC analysis demonstrated that the IDO2-50 had a good ability to identify a venous saturation below 50%, with an area under the curve of 0.797, cutoff point of 24.5 with a sensitivity of 81%, specificity of 66%, positive predictive value of 44%, and negative predictive value of 91%. Bayesian linear regression analysis yielded the following model: 237.82 + (1.18 × age in months) - (3.31 × arterial saturation) - (1.92 × cerebral NIRS) + (0.84 × heart rate). The IDO2 index has moderate correlation with IVC saturation. It has good sensitive and negative predictive value. Cerebral NIRS does appear to correlate better with the underlying venous saturation than the IDO2 index.

Clinical parameters to predict adverse outcomes in patients with shunt-dependent physiology with a Blalock-Taussig-Thomas shunt

In patients with shunt-dependent physiology, early risk factor identification can facilitate the prevention of adverse outcomes. This study aims to determine a scoring system to estimate the risk for adverse outcomes after Blalock-Taussig-Thomas shunt placement. Of the 39 neonates with Blalock-Taussig-Thomas shunt placement, 10 experienced the composite outcome. The resulting risk score from clinical and hemodynamic variables attributed 1 point for each of the following: central venous pressure >7.8, serum lactate >1.8 mmol/L, renal oxygen extraction ratio >32, and vasoactive-inotrope score >8.7. A score of 0 was associated with a 0% risk of the composite outcome, a score of 1 or 2 with a 15% risk, and a score of 3 or 4 with a 60% risk. A combination of increased central venous pressure, increased serum lactate, increased renal oxygen extraction ratio, and increased vasoactive-inotrope score are highly accurately associated with the risk of cardiopulmonary arrest, need for extracorporeal membrane oxygenation, or inpatient mortality after a Blalock-Taussig-Thomas shunt in patients with shunt-dependent physiology.

Automated prediction of cardiorespiratory deterioration in patients with single-ventricle parallel circulation: A multicenter validation study

Objectives

Patients with single-ventricle physiology have a significant risk of cardiorespiratory deterioration between their first- and second-stage palliation surgeries. Detection of deterioration episodes may allow for early intervention and improved outcomes.

Methods

A prospective study was executed at Nationwide Children's Hospital, Children's Hospital of Philadelphia, and Children's Hospital Colorado to collect physiologic data of subjects with single ventricle physiology during all hospitalizations between neonatal palliation and II surgeries using the Sickbay software platform (Medical Informatics Corp). Timing of cardiorespiratory deterioration events was captured via chart review. The predictive algorithm previously developed and validated at Texas Children's Hospital was applied to these data without retraining. Standard metrics such as receiver operating curve area, positive and negative likelihood ratio, and alert rates were calculated to establish clinical performance of the predictive algorithm.

Results

Our cohort consisted of 58 subjects admitted to the cardiac intensive care unit and stepdown units of participating centers over 14 months. Approximately 28,991 hours of high-resolution physiologic waveform and vital sign data were collected using the Sickbay. A total of 30 cardiorespiratory deterioration events were observed. the risk index metric generated by our algorithm was found to be both sensitive and specific for detecting impending events one to two hours in advance of overt extremis (receiver operating curve = 0.927).

Conclusions

Our algorithm can provide a 1- to 2-hour advanced warning for 53.6% of all cardiorespiratory deterioration events in children with single ventricle physiology during their initial postop course as well as interstage hospitalizations after stage I palliation with only 2.5 alarms being generated per patient per day.

Cardiac Children Hospital Early Warning ScoreVersus the Inadequate Oxygen Delivery Index for the Detection of Early Warning Signs of Deterioration

To assess the utility of the Cardiac Children's Hospital Early Warning Score (C-CHEWS) in the early detection of deterioration.

DESIGN

Single-center longitudinal pilot study.

SETTING

Pediatric cardiac ICU (PCICU), Aga Khan University.

INTERVENTIONS

C-CHEWS and Inadequate Oxygen Delivery (IDO₂) Index calculation every 2 hours.

PATIENTS

A total of 60 children (0 d to 18 yr old).

MEASUREMENTS AND MAIN RESULTS

A single-center longitudinal pilot study was conducted at PCICU. All postoperative extubated patients were assessed and scored between 0 and 11, and these scores were then correlated with the IDO₂ index data available from the T3 platform. Adverse events were defined as a need for cardiopulmonary resuscitation, or reintubation, and death. A total of 920 C-CHEWS and IDO₂ scores were analyzed on 60 patients during the study period. There were 36 males and 24 females, and the median age of the study population was 34 months (interquartile range, 9.0-72.0 mo). Fourteen patients (23.3%) developed adverse events; these included 9 reintubations and 5 cardiopulmonary arrests, resulting in 2 deaths. The area under the curve (AUC) for C-CHEWS scores fell in an acceptable range of 0.956 (95% CI, 0.869-0.992), suggesting an optimal accuracy for identifying early warning signs of cardiopulmonary arrest. Whereas, IDO₂ showed no discriminatory power to detect the adverse events with an AUC of 0.522 (95% CI, 0.389-0.652).

CONCLUSIONS

The C-CHEWS tool provides a standardized assessment and approach to deteriorating congenital cardiac surgery patients in recognizing early postoperative deterioration.

Preventing Cardiac Arrest in the Pediatric Cardiac Intensive Care Unit Through Multicenter Collaboration

Importance

Preventing in-hospital cardiac arrest (IHCA) likely represents an effective strategy to improve outcomes for critically ill patients, but feasibility of IHCA prevention remains unclear.

Objective

To determine whether a low-technology cardiac arrest prevention (CAP) practice bundle decreases IHCA rate.

Design, Setting, and Participants

Pediatric cardiac intensive care unit (CICU) teams from the Pediatric Cardiac Critical Care Consortium (PC4) formed a collaborative learning network to implement the CAP bundle consistent with the Institute for Healthcare Improvement framework; 15 hospitals implemented the bundle voluntarily. Risk-adjusted IHCA incidence rates were analyzed across 2 time periods, 12 months (baseline) and 18 months after CAP implementation (intervention) using difference-in-differences (DID) regression to compare 15 CAP and 16 control PC4 hospitals that chose not to participate in CAP but had IHCA rates tracked in the PC4 registry. Patients deemed at high risk for IHCA, based on a priori evidence-based criteria and empirical hospital-specific criteria, were selected to receive the CAP bundle. Data were collected from July 2018 to December 2019, and data were analyzed from March to August 2020.

Interventions

CAP bundle included 5 elements developed to promote increased situational awareness and communication among bedside clinicians to recognize and mitigate deterioration in high-risk patients.

Main Outcomes and Measures

Risk-adjusted IHCA incidence rate across all CICU admissions (IHCA events divided by all admissions).

Results

The bundle was activated in 2664 of 10 510 CAP hospital admissions (25.3%); admission characteristics were similar across study periods. There was a 30% relative reduction in risk-adjusted IHCA incidence rate at CAP hospitals (intervention period: 2.6%; 95% CI, 2.2-2.9; baseline: 3.7%; 95% CI, 3.1-4.0), but no change at control hospitals (intervention period: 2.7%; 95% CI, 2.3-2.9; baseline: 2.7%; 95% CI, 2.2-3.0). DID analysis confirmed significantly reduced odds of IHCA among all admissions at CAP hospitals compared with control hospitals during the intervention period vs baseline (odds ratio, 0.72; 95% CI, 0.56-0.91; P = .01). DID odds ratios were 0.72 (95% CI, 0.53-0.98) for the surgical subgroup, 0.74 (95% CI, 0.48-1.14) for the medical subgroup, and 0.72 (95% CI, 0.50-1.03) for the high-risk admission subgroup at CAP hospitals after intervention. All-cause risk-adjusted mortality rate did not change after intervention.

Conclusions and Relevance

Implementation of this CAP bundle led to significant IHCA reduction across multiple pediatric CICUs. Future studies may determine if this bundle can be effective in other critically ill populations.

Cardiac Arrest in Children Following Cardiac Surgery: A Scoping Review of Contributing Factors

Nearly half of children experiencing cardiac arrest following cardiac surgery do not survive hospital discharge and patients who survive often experience significant neurological impairment. Additionally, increased resource utilization following cardiac arrest translates into adverse logistical and financial consequences. Although some studies have identified patient characteristics that increase the risk of cardiac arrest after pediatric cardiac surgery, modifiable risk factors, which could provide a foundation for effective prevention strategies, have been elusive. This scoping review explores the current knowledge surrounding risk factors associated with cardiac arrest in children following cardiac surgery and provides recommendations for future research.

Prediction of Impending Central Line Associated Bloodstream Infections in Hospitalized Cardiac Patients: Development and Testing of a Machine-Learning Model

BACKGROUND

While modeling of central line-associated blood stream infection (CLABSI) risk factors is common, models that predict an impending CLABSI in real time are lacking.

AIM

To build a prediction model which identifies patients who will develop a CLABSI in the ensuing 24 hours.

METHODS

We collected variables potentially related to infection identification in all patients admitted to the cardiac ICU or cardiac ward at Boston Children's Hospital in whom a central venous catheter (CVC) was in place between January 2010 and August 2020, excluding those with a diagnosis of bacterial endocarditis. We created models predicting whether a patient would develop CLABSI in the ensuing 24 hours. We assessed model performance based on area under the curve (AUC), sensitivity, and false positive rate (FPR) of models run on an independent testing set (40%).

FINDINGS

104,035 patient-days and 139,662 line-days corresponding to 7,468 unique patients were included in the analysis. There were 399 positive blood cultures (0.38%), most commonly with Staphylococcus aureus (23% of infections). Major predictors included a prior history of infection, elevated maximum heart rate, elevated maximum temperature, elevated C-reactive protein, exposure to parenteral nutrition, and use of alteplase for CVC clearance. The model identified 25% of positive cultures with an FPR of 0.11% (AUC = 0.82).

CONCLUSIONS

A machine learning model can be used to predict 25% of patients with impending CLABSI with only 1.1/1,000 of these predictions being incorrect. Once prospectively validated, this tool may allow for early treatment or prevention.

Inadequate Oxygen Delivery Dose and Major Adverse Events in Critically Ill Children With Sepsis

BACKGROUND

The inadequate oxygen delivery (IDo2) index is used to estimate the probability that a patient is experiencing inadequate systemic delivery of oxygen. Its utility in the care of critically ill children with sepsis is unknown.

OBJECTIVE

To evaluate the relationship between IDo2 dose and major adverse events, illness severity metrics, and outcomes among critically ill children with sepsis.

METHODS

Clinical and IDo2 data were retrospectively collected from the records of 102 critically ill children with sepsis, weighing >2 kg, without preexisting cardiac dysfunction. Descriptive, nonparametric, odds ratio, and correlational statistics were used for data analysis.

RESULTS

Inadequate oxygen delivery doses were significantly higher in patients who experienced major adverse events (n = 13) than in those who did not (n = 89) during the time intervals of 0 to 12 hours (P < .001), 12 to 24 hours (P = .01), 0 to 24 hours (P < .001), 0 to 36 hours (P < .001), and 0 to 48 hours (P < .001). Patients with an IDo2 dose at 0 to 12 hours at or above the 80th percentile had the highest odds of a major adverse event (odds ratio, 23.6; 95% CI, 5.6-99.4). Significant correlations were observed between IDo2 dose at 0 to 12 hours and day 2 maximum vasoactive inotropic score (ρ = 0.27, P = .006), day 1 Pediatric Logistic Organ Dysfunction (PELOD-2) score (ρ = 0.41, P < .001), day 2 PELOD-2 score (ρ = 0.44, P < .001), intensive care unit length of stay (ρ = 0.35, P < .001), days receiving invasive ventilation (ρ = 0.42, P < .001), and age (ρ = -0.47, P < .001).

CONCLUSIONS

Routine IDo2 monitoring may identify critically ill children with sepsis who are at the highest risk of adverse events and poor outcomes.

Associations With Extubation Failure and Predictive Value of Risk Analytics Algorithms With Extubation Readiness Tests Following Congenital Cardiac Surgery

OBJECTIVES

Extubation failure is associated with morbidity and mortality in children following cardiac surgery. Current extubation readiness tests (ERT) do not consider the nonrespiratory support provided by mechanical ventilation (MV) for children with congenital heart disease. We aimed to identify factors associated with extubation failure in children following cardiac surgery and assess the performance of two risk analytics algorithms for patients undergoing an ERT.

DESIGN

Retrospective cohort study.

SETTING

CICU at a tertiary-care children's hospital.

PATIENTS

Children receiving MV greater than 48 hours following cardiac surgery between January 1, 2017, and December 31, 2019.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Six hundred fifty encounters were analyzed with 49 occurrences (8%) of reintubation. Extubation failure occurred most frequently within 6 hours of extubation. On multivariable analysis, younger age (per each 3-mo decrease: odds ratio [OR], 1.06; 95% CI, 1.001-1.12), male sex (OR, 2.02; 95% CI, 1.03-3.97), Society of Thoracic Surgery-European Association for Cardiothoracic Surgery category 5 procedure (p equals to 0.005), and preoperative respiratory support (OR, 2.08; 95% CI, 1.09-3.95) were independently associated with unplanned reintubation. Our institutional ERT had low sensitivity to identify patients at risk for reintubation (23.8%; 95% CI, 9.7-47.6%). The addition of the inadequate delivery of oxygen (IDO2) index to the ERT increased the sensitivity by 19.0% (95% CI, -2.5 to 40.7%; p = 0.05), but the sensitivity remained low and the accuracy of the test dropped by 8.9% (95% CI, 4.7-13.1%; p < 0.01).

CONCLUSIONS

Preoperative respiratory support, younger age, and more complex operations are associated with postoperative extubation failure. IDO2 and IVCO2 provide unique cardiorespiratory monitoring parameters during ERTs but require further investigation before being used in clinical evaluation for extubation failure.

A Novel Situational Awareness Scoring System in Pediatric Cardiac Intensive Care Unit Patients

The aim of this study was to describe a novel Situational Awareness Scoring System (SASS)'s performance in discriminating between patients who had cardiac arrest (CA) and those who did not, in a pediatric cardiac intensive care unit (PCICU). Retrospective, observational-cohort study in a quaternary-care PCICU. Patients who had CA in the PCICU between January 2014 and December 2018, and patients admitted to the PCICU in 2018 who did not have CA were included. Patients with do not resuscitate or do not intubate orders, extracorporeal membrane oxygenation, ventricular assist device, and PCICU stay < 2 hours were excluded. SASS score statistics were calculated within 2, 4-, 6-, and 8-hour time intervals counting backward from the time of CA, or end of PCICU stay in patients who did not have CA. Cross-validated discrete time logistic regression models were used to calculate area under the receiver operating characteristic (AUC) curves. Odds ratios (ORs) for CA were calculated per unit increase of the SASS score. Twenty-eight CA events were analyzed in 462 PCICU admissions from 267 patients. Maximum SASS score within 4-hour time interval before CA achieved the highest AUC of 0.91 (95% confidence interval [CI]: 0.86–0.96) compared with maximum SASS score within 2-, 6-, and 8-hour time intervals before CA of 0.88 (0.79–96), 0.90 (0.85–0.95), and 0.89 (0.83–0.95), respectively. A cutoff value of 60 for maximum SASS score within 4-hour time interval before CA resulted in 82.1 and 83.2% of sensitivity and specificity, respectively. OR for CA was 1.32 (95% CI: 1.26–1.39) for every 10 units increase in the maximum SASS score within each 4-hour time interval before CA. The maximum SASS score within various time intervals before CA achieved promising performance in discriminating patients regarding occurrence of CA.

Performance of a Risk Analytic Tool (Index of Tissue Oxygen Delivery "IDO2") in Pediatric Cardiac Intensive Care Unit of a Developing Country

OBJECTIVE

To determine the performance of a commercially available risk analytic tool (IDO2) to estimate the risk for SVO2 < 40% in patients admitted in cardiac intensive care unit (CICU).

METHODS

Medical and T3 records of all patients (aged 1 day to 12 years, weight >2 kg) who received care in the CICU between October 1st, 2019 and October 1st, 2020, had SvO2 lab(s) drawn during CICU course and whose data was transmitted to T3, were included. The average IDO2 Index was computed in the 30-min period immediately prior to each SvO2 measurement and used as a predictor score for SvO2 < 40%.

RESULTS

A total of 69 CICU admissions from 65 patients, median age 9.3 months (interquartile range 20.8) were identified. Surgical and medical patients were 61 (88%) and 8 (12%) respectively; 4 (5.7%) patients had single ventricle physiology. Tetralogy of Fallot n = 23 (33.3%) and ventricular septal defects 17 (24.6%) were major cardiac diagnosis. Sixty-one (89.9%) of the admissions were successfully discharged from the hospital. Of the 187-total included SvO2 labs, 17 (9%) were <40%. The AUC of estimating SvO2 < 40% IDO2 was 0.87 [confidence interval (CI): 0.79-0.94]. Average IDO2 above 75 had the highest absolute risk (42.11, CI: 20.25-66.50) and highest RR (4.63, CI: 2.31-9.28, p-value < 0.0001) of SvO2 < 40%.

CONCLUSION

IDO2 performed well in estimating low SvO2 (<40%) in pediatric patients presenting to a CICU in a low resource setting. Future work is needed to determine the effect of this risk analytic tool on clinical outcomes in such a setting.

The horizon of pediatric cardiac critical care

Pediatric Cardiac Critical Care (PCCC) is a challenging discipline where decisions require a high degree of preparation and clinical expertise. In the modern era, outcomes of neonates and children with congenital heart defects have dramatically improved, largely by transformative technologies and an expanding collection of pharmacotherapies. Exponential advances in science and technology are occurring at a breathtaking rate, and applying these advances to the PCCC patient is essential to further advancing the science and practice of the field. In this article, we identified and elaborate on seven key elements within the PCCC that will pave the way for the future.

Early prediction of clinical deterioration using data-driven machine-learning modeling of electronic health records

OBJECTIVES

To develop and evaluate a high-dimensional, data-driven model to identify patients at high risk of clinical deterioration from routinely collected electronic health record (EHR) data.

MATERIALS AND METHODS

In this single-center, retrospective cohort study, 488 patients with single-ventricle and shunt-dependent congenital heart disease <6 months old were admitted to the cardiac intensive care unit before stage 2 palliation between 2014 and 2019. Using machine-learning techniques, we developed the Intensive care Warning Index (I-WIN), which systematically assessed 1028 regularly collected EHR variables (vital signs, medications, laboratory tests, and diagnoses) to identify patients in the cardiac intensive care unit at elevated risk of clinical deterioration. An ensemble of 5 extreme gradient boosting models was developed and validated on 203 cases (130 emergent endotracheal intubations, 34 cardiac arrests requiring cardiopulmonary resuscitation, 10 extracorporeal membrane oxygenation cannulations, and 29 cardiac arrests requiring cardiopulmonary resuscitation onto extracorporeal membrane oxygenation) and 378 control periods from 446 patients.

RESULTS

At 4 hours before deterioration, the model achieved an area under the receiver operating characteristic curve of 0.92 (95% confidence interval, 0.84-0.98), 0.881 sensitivity, 0.776 positive predictive value, 0.862 specificity, and 0.571 Brier skill score. Performance remained high at 8 hours before deterioration with 0.815 (0.688-0.921) area under the receiver operating characteristic curve.

CONCLUSIONS

I-WIN accurately predicted deterioration events in critically-ill infants with high-risk congenital heart disease up to 8 hours before deterioration, potentially allowing clinicians to target interventions. We propose a paradigm shift from conventional expert consensus-based selection of risk factors to a data-driven, machine-learning methodology for risk prediction. With the increased availability of data capture in EHRs, I-WIN can be extended to broader applications in data-rich environments in critical care.

Use of a Risk Analytic Algorithm to Inform Weaning From Vasoactive Medication in Patients Following Pediatric Cardiac Surgery

OBJECTIVES

Advanced clinical decision support tools, such as real-time risk analytic algorithms, show promise in assisting clinicians in making more efficient and precise decisions. These algorithms, which calculate the likelihood of a given underlying physiology or future event, have predominantly been used to identify the risk of impending clinical decompensation. There may be broader clinical applications of these models. Using the inadequate delivery of oxygen index, a U.S. Food and Drug Administration-approved risk analytic algorithm predicting the likelihood of low cardiac output state, the primary objective was to evaluate the association of inadequate delivery of oxygen index with success or failure of weaning vasoactive support in postoperative cardiac surgery patients.

DESIGN

Multicenter retrospective cohort study.

SETTING

Three pediatric cardiac ICUs at tertiary academic children's hospitals.

PATIENTS

Infants and children greater than 2 kg and less than 12 years following cardiac surgery, who required vasoactive infusions for greater than 6 hours in the postoperative period.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Postoperative patients were identified who successfully weaned off initial vasoactive infusions (n = 2,645) versus those who failed vasoactive wean (required reinitiation of vasoactive, required mechanical circulatory support, renal replacement therapy, suffered cardiac arrest, or died) (n = 516). Inadequate delivery of oxygen index for final 6 hours of vasoactive wean was captured. Inadequate delivery of oxygen index was significantly elevated in patients with failed versus successful weans (inadequate delivery of oxygen index 11.6 [sd 19.0] vs 6.4 [sd 12.6]; p < 0.001). Mean 6-hour inadequate delivery of oxygen index greater than 50 had strongest association with failed vasoactive wean (adjusted odds ratio, 4.0; 95% CI, 2.5-6.6). In patients who failed wean, reinitiation of vasoactive support was associated with concomitant fall in inadequate delivery of oxygen index (11.1 [sd 18] vs 8.9 [sd 16]; p = 0.007).

CONCLUSIONS

During the de-escalation phase of postoperative cardiac ICU management, elevation of the real-time risk analytic model, inadequate delivery of oxygen index, was associated with failure to wean off vasoactive infusions. Future studies should prospectively evaluate utility of risk analytic models as clinical decision support tools in de-escalation practices in critically ill patients.

Avoidable Serum Potassium Testing in the Cardiac ICU: Development and Testing of a Machine-Learning Model

OBJECTIVES

To create a machine-learning model identifying potentially avoidable blood draws for serum potassium among pediatric patients following cardiac surgery.

DESIGN

Retrospective cohort study.

SETTING

Tertiary-care center.

PATIENTS

All patients admitted to the cardiac ICU at Boston Children's Hospital between January 2010 and December 2018 with a length of stay greater than or equal to 4 days and greater than or equal to two recorded serum potassium measurements.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

We collected variables related to potassium homeostasis, including serum chemistry, hourly potassium intake, diuretics, and urine output. Using established machine-learning techniques, including random forest classifiers, and hyperparameter tuning, we created models predicting whether a patient's potassium would be normal or abnormal based on the most recent potassium level, medications administered, urine output, and markers of renal function. We developed multiple models based on different age-categories and temporal proximity of the most recent potassium measurement. We assessed the predictive performance of the models using an independent test set. Of the 7,269 admissions (6,196 patients) included, serum potassium was measured on average of 1 (interquartile range, 0-1) time per day. Approximately 96% of patients received at least one dose of IV diuretic and 83% received a form of potassium supplementation. Our models predicted a normal potassium value with a median positive predictive value of 0.900. A median percentage of 2.1% measurements (mean 2.5%; interquartile range, 1.3-3.7%) was incorrectly predicted as normal when they were abnormal. A median percentage of 0.0% (interquartile range, 0.0-0.4%) critically low or high measurements was incorrectly predicted as normal. A median of 27.2% (interquartile range, 7.8-32.4%) of samples was correctly predicted to be normal and could have been potentially avoided.

CONCLUSIONS

Machine-learning methods can be used to predict avoidable blood tests accurately for serum potassium in critically ill pediatric patients. A median of 27.2% of samples could have been saved, with decreased costs and risk of infection or anemia.

Lessons Learned From the First Pilot Study of the Compensatory Reserve Index After Congenital Heart Surgery Requiring Cardiopulmonary Bypass

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.