Modeling the Relationship Between Diastolic Phenotype and Outcomes in Pediatric Hypertrophic Cardiomyopathy.

BACKGROUND: Pediatric hypertrophic cardiomyopathy (HCM) is associated with adverse events. The contribution of diastolic dysfunction to adverse events is poorly understood. The aim of this study was to explore the association between diastolic phenotype and outcomes in pediatric patients with HCM. METHODS: Children <18 years of age with diagnosed with HCM were included. Diastolic function parameters were measured from the first echocardiogram at the time of diagnosis, including Doppler flow velocities, tissue Doppler velocities, and left atrial volume and function. Using principal-component analysis, key features in echocardiographic parameters were identified. The principal components were regressed to freedom from major adverse cardiac events (MACE), defined as implantable cardioverter-defibrillator insertion, myectomy, aborted sudden cardiac death, transplantation, need for mechanical circulatory support, and death. RESULTS: Variables that estimate left ventricular filling pressures were highly collinear and associated with MACE (hazard ratio, 0.86; 95% CI, 0.75-1.00), though this was no longer significant after controlling for left ventricular thickness and genetic variation. Left atrial size parameters adjusted for body surface area were independently associated with outcomes in the covariate-adjusted model (hazard ratio, 0.69; 95% CI, 0.5-0.94). The covariate-adjusted model had an Akaike information criterion of 213, an adjusted R2 value of 0.78, and a concordance index of 0.82 for association with MACE. CONCLUSION: Echocardiographic parameters of diastolic dysfunction were associated with MACE in this population study, in combination with the severity of left ventricular hypertrophy and genetic variation. Left atrial size parameters adjusted for body surface area were independently associated with adverse events. Additional study of diastolic function parameters adjusted for patient size could facilitate the prediction of adverse events in pediatric patients with HCM.

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.

Decreased Heart Rate Variability in Children with Acute Decompensated Heart Failure is Associated with Poor Outcomes.

Heart rate variability (HRV) is a noninvasive indicator of the health of neurocardiac interactions of the autonomic nervous system. In adults, decreased HRV correlates with increased cardiovascular mortality. However, the relationship between HRV and outcomes in children with acute decompensated heart failure (ADHF) has not been described. Patients < 21 years old hospitalized with ADHF from 2013 to 2019 were included (N = 79). Primary outcome was defined as death, heart transplant, or mechanical circulatory support (MCS). The median standard deviation of the R-to-R interval in 5-min intervals (SDNN) was calculated from telemetry data obtained across the first 24 h of admission. Patients who met the primary outcome had significantly lower median SDNN (13.8 [7.8, 29.1]) compared to those who did not (24.6 [15.3, 84.4]; p = 0.004). A median SDNN of 20 ms resulted in a sensitivity of 68% and specificity of 69%. Median SDNN < 20 ms represented decreased freedom from primary outcome (p = 0.043) and a hazard ratio of 2.2 in multivariate analysis (p = 0.016). Pediatric patients with ADHF who died, underwent heart transplant, or required MCS had significantly decreased HRV at presentation compared to those that did not. This supports HRV as a noninvasive tool to improve prognostication in children in ADHF.

Stratification of Pediatric COVID-19 Cases Using Inflammatory Biomarker Profiling and Machine Learning.

While pediatric COVID-19 is rarely severe, a small fraction of children infected with SARS-CoV-2 go on to develop multisystem inflammatory syndrome (MIS-C), with substantial morbidity. An objective method with high specificity and high sensitivity to identify current or imminent MIS-C in children infected with SARS-CoV-2 is highly desirable. The aim was to learn about an interpretable novel cytokine/chemokine assay panel providing such an objective classification. This retrospective study was conducted on four groups of pediatric patients seen at multiple sites of Texas Children's Hospital, Houston, TX who consented to provide blood samples to our COVID-19 Biorepository. Standard laboratory markers of inflammation and a novel cytokine/chemokine array were measured in blood samples of all patients. Group 1 consisted of 72 COVID-19, 70 MIS-C and 63 uninfected control patients seen between May 2020 and January 2021 and predominantly infected with pre-alpha variants. Group 2 consisted of 29 COVID-19 and 43 MIS-C patients seen between January and May 2021 infected predominantly with the alpha variant. Group 3 consisted of 30 COVID-19 and 32 MIS-C patients seen between August and October 2021 infected with alpha and/or delta variants. Group 4 consisted of 20 COVID-19 and 46 MIS-C patients seen between October 2021 andJanuary 2022 infected with delta and/or omicron variants. Group 1 was used to train an L1-regularized logistic regression model which was tested using five-fold cross validation, and then separately validated against the remaining naïve groups. The area under receiver operating curve (AUROC) and F1-score were used to quantify the performance of the cytokine/chemokine assay-based classifier. Standard laboratory markers predict MIS-C with a five-fold cross-validated AUROC of 0.86 ± 0.05 and an F1 score of 0.78 ± 0.07, while the cytokine/chemokine panel predicted MIS-C with a five-fold cross-validated AUROC of 0.95 ± 0.02 and an F1 score of 0.91 ± 0.04, with only sixteen of the forty-five cytokines/chemokines sufficient to achieve this performance. Tested on Group 2 the cytokine/chemokine panel yielded AUROC = 0.98 and F1 = 0.93, on Group 3 it yielded AUROC = 0.89 and F1 = 0.89, and on Group 4 AUROC = 0.99 and F1 = 0.97. Adding standard laboratory markers to the cytokine/chemokine panel did not improve performance. A top-10 subset of these 16 cytokines achieves equivalent performance on the validation data sets. Our findings demonstrate that a sixteen-cytokine/chemokine panel as well as the top ten subset provides a highly sensitive, and specific method to identify MIS-C in patients infected with SARS-CoV-2 of all the major variants identified to date.

Comparison of Near-Infrared Spectroscopy-Based Cerebral Autoregulatory Indices in Extremely Low Birth Weight Infants.

BACKGROUND: Premature infants are born with immature cerebral autoregulation function and are vulnerable to pressure passive cerebral circulation and subsequent brain injury. Measurements derived from near-infrared spectroscopy (NIRS) have enabled continuous assessment of cerebral vasoreactivity. Although NIRS has enabled a growing field of research, the lack of clear standardization in the field remains problematic. A major limitation of current literature is the absence of a comparative analysis of the different methodologies. OBJECTIVES: To determine the relationship between NIRS-derived continuous indices of cerebral autoregulation in a cohort of extremely low birth weight (ELBW) infants. METHODS: Premature infants of birth weight 401-1000 g were studied during the first 72 h of life. The cerebral oximetry index (COx), hemoglobin volume index (HVx), and tissue oxygenation heart rate reactivity index (TOHRx) were simultaneously calculated. The relationship between each of the indices was assessed with Pearson correlation. RESULTS: Fifty-eight infants with a median gestational age of 25.8 weeks and a median birth weight of 738 g were included. Intraventricular hemorrhage (IVH) was detected in 33% of individuals. COx and HVx demonstrated the highest degree of correlation, although the relationship was moderate at best (r = 0.543, p < 0.001). No correlation was found either between COx and TOHRx (r = 0.318, p < 0.015) or between HVx and TOHRx (r = 0.287, p < 0.029). No significant differences in these relationships were found with respect to IVH and no IVH in subgroup analysis. CONCLUSIONS: COx, HVx, and TOHRx are not numerically equivalent. Caution must be applied when interpreting or comparing results based on different methodologies for measuring cerebral autoregulation. Uniformity regarding data acquisition and analytical methodology are needed to firmly establish a gold standard for neonatal cerebral autoregulation monitoring.

Stratification of Pediatric COVID-19 cases by inflammatory biomarker profiling and machine learning.

An objective method to identify imminent or current Multi-Inflammatory Syndrome in Children (MIS-C) infected with SARS-CoV-2 is highly desirable. The aims was to define an algorithmically interpreted novel cytokine/chemokine assay panel providing such an objective classification. This study was conducted on 4 groups of patients seen at multiple sites of Texas Children's Hospital, Houston, TX who consented to provide blood samples to our COVID-19 Biorepository. Standard laboratory markers of inflammation and a novel cytokine/chemokine array were measured in blood samples of all patients. Group 1 consisted of 72 COVID-19, 66 MIS-C and 63 uninfected control patients seen between May 2020 and January 2021 and predominantly infected with pre-alpha variants. Group 2 consisted of 29 COVID-19 and 43 MIS-C patients seen between January-May 2021 infected predominantly with the alpha variant. Group 3 consisted of 30 COVID-19 and 32 MIS-C patients seen between August-October 2021 infected with alpha and/or delta variants. Group 4 consisted of 20 COVID-19 and 46 MIS-C patients seen between October 2021-January 2022 infected with delta and/or omicron variants. Group 1 was used to train a L1-regularized logistic regression model which was validated using 5-fold cross validation, and then separately validated against the remaining naïve groups. The area under receiver operating curve (AUROC) and F1-score were used to quantify the performance of the algorithmically interpreted cytokine/chemokine assay panel. Standard laboratory markers predict MIS-C with a 5-fold cross-validated AUROC of 0.86 ± 0.05 and an F1 score of 0.78 ± 0.07, while the cytokine/chemokine panel predicted MIS-C with a 5-fold cross-validated AUROC of 0.95 ± 0.02 and an F1 score of 0.91 ± 0.04, with only sixteen of the forty-five cytokines/chemokines sufficient to achieve this performance. Tested on Group 2 the cytokine/chemokine panel yielded AUROC =0.98, F1=0.93, on Group 3 it yielded AUROC=0.89, F1 = 0.89, and on Group 4 AUROC= 0.99, F1= 0.97). Adding standard laboratory markers to the cytokine/chemokine panel did not improve performance. A top-10 subset of these 16 cytokines achieves equivalent performance on the validation data sets. Our findings demonstrate that a sixteen-cytokine/chemokine panel as well as the top ten subset provides a sensitive, specific method to identify MIS-C in patients infected with SARS-CoV-2 of all the major variants identified to date.

Computer simulation of surgical interventions for the treatment of refractory pulmonary hypertension.

This paper describes computer models of three interventions used for treating refractory pulmonary hypertension (RPH). These procedures create either an atrial septal defect, a ventricular septal defect or, in the case of a Potts shunt, a patent ductus arteriosus. The aim in all three cases is to generate a right-to-left shunt, allowing for either pressure or volume unloading of the right side of the heart in the setting of right ventricular failure, while maintaining cardiac output. These shunts are created, however, at the expense of introducing de-oxygenated blood into the systemic circulation, thereby lowering the systemic arterial oxygen saturation. The models developed in this paper are based on compartmental descriptions of human hemodynamics and oxygen transport. An important parameter included in our models is the cross-sectional area of the surgically created defect. Numerical simulations are performed to compare different interventions and various shunt sizes and to assess their impact on hemodynamic variables and oxygen saturations. We also create a model for exercise and use it to study exercise tolerance in simulated pre-intervention and post-intervention RPH patients.

Physiologic profile associated with severe multisystem inflammatory syndrome in children: a retrospective study.

OBJECTIVE: The purpose of this study was to describe the clinical presentation and physiologic profile of individuals with varying degrees of severity of multisystem inflammatory syndrome in children (MIS-C). METHODS: We performed a retrospective study of children diagnosed with MIS-C admitted to a single quaternary children's hospital from May 2020 to April 2021. We created an MIS-C severity score using the following parameters: hospital admission status (e.g., floor vs intensive care unit), need for inotropic or vasoactive medications, and need for mechanical ventilation. Univariate and multivariate analyses were performed to associate risk factors corresponding to the MIS-C severity score. RESULTS: The study included 152 children who were followed for 14 days post hospital admission. A stepwise forward selection process identified seven physiologic variables associated with "severe" MIS-C according to a logistic regression. Specifically, a combination of elevated creatinine (p = 0.013), international normalized ratio (p = 0.002), brain natriuretic peptide (p = 0.001), white blood cell count (p = 0.009), ferritin (p = 0.041), respiratory rate (p = 0.047), and decreased albumin (p = 0.047) led to an excellent discrimination between mild versus severe MIS-C (AUC = 0.915). CONCLUSION: This study derived a physiologic profile associated with the stratification of MIS-C severity. IMPACT: Based on a cohort of 152 individuals diagnosed with MIS-C, this study derived a nomenclature that stratifies the severity of MIS-C. Investigated demographic, presentational vital signs, and blood analytes associated with severity of illness. Identification of a multivariate physiologic profile that strongly associates with MIS-C severity. This model allows the care team to recognize patients likely to require a higher level of intensive care.

Descriptors of Failed Extubation in Norwood Patients Using Physiologic Data Streaming.

The objective of this study is to evaluate the utility of high-frequency physiologic data during the extubation process and other clinical variables for describing the physiologic profile of extubation failure in neonates with hypoplastic left heart syndrome (HLHS) post-Norwood procedure. This is a single-center, retrospective analysis. Extubation events were collected from January 2016 until July 2021. Extubation failure was defined as the need for re-intubation within 48 h of extubation. The data included streaming heart rate, respiratory rate, blood pressure, arterial oxygen saturation, and cerebral/renal near-infrared spectroscopy (NIRS). The most recent blood laboratory results before extubation were also included. These markers, demographics, clinical characteristics, and ventilatory settings were compared between successful and failed extubations. The analysis included 311 extubations. The extubation failure rate was 10%. According to univariable analyses, failed extubations were preceded by higher respiratory rates (p = 0.029), lower end-tidal CO2 (p = 0.009), lower pH (p = 0.043), lower serum bicarbonate (p = 0.030), and lower partial pressure of O2 (p = 0.022). In the first 10 min after extubation, the failed events were characterized by lower arterial (p = 0.028) and cerebral NIRS (p = 0.018) saturations. Failed events were associated with persistently lower values for cerebral NIRS 2 h post-extubation (p = 0.027). In multivariable analysis, vocal cord anomaly, cerebral NIRS at 10 min post-extubation, renal NIRS at pre-extubation and post-extubation, and end-tidal CO2 at pre-extubation remained as significant co-variables. Oximetric indices before, in the 10 min immediately after, and 2 h after extubation and vocal cords paralysis are associated with failed extubation events in patients with parallel circulation.

Semi-Automated Construction of Patient-Specific Aortic Valves from Computed Tomography Images.

This paper presents a semi-automatic method for the construction of volumetric models of the aortic valve using computed tomography angiography images. Although the aortic valve typically cannot be segmented directly from a computed tomography angiography image, the method described herein uses manually selected samples of an aortic segmentation derived from this image to inform the construction. These samples capture certain physiologic landmarks and are used to construct a volumetric valve model. As a demonstration of the capabilities of this method, valve models for 25 pediatric patients are created. A selected valve anatomy is used to perform fluid-structure interaction simulations using the immersed finite element/difference method with physiologic driving and loading conditions. Simulation results demonstrate this method creates a functional valve that opens and closes normally and generates pressure and flow waveforms that are similar to those observed clinically.

Noninvasive Respiratory Support Does Not Prevent Extubation Failure in High-Risk Norwood Patients.

This study aims to determine whether bilevel positive airway pressure (BiPAP) and continuous positive airway pressure (CPAP) effectively mitigate the risk of extubation failure in children status post-Norwood procedure. DESIGN: Single-center, retrospective analysis. Extubation events were collected from January 2015 to July 2021. Extubation failure was defined as the need for reintubation within 48 hours of extubation. Demographics, clinical characteristics, and ventilatory settings were compared between successful and failed extubations. SETTING: Pediatric cardiovascular ICU. PATIENTS: Neonates following Norwood procedure. INTERVENTIONS: Extubation following the Norwood procedure. MEASUREMENTS AND MAIN RESULTS: The analysis included 311 extubations. Extubation failure occurred in 31 (10%) extubation attempts within the first 48 hours. On univariate analysis, higher rate of extubation failure was observed when patients were extubated to CPAP/BiPAP relative to patients who were extubated to either high-flow nasal cannula (HFNC) or nasal cannula (NC) (16% vs 7.8%; p = 0.027). On multivariable analysis, the presence of vocal cord anomaly (odds ratio, 3.08; p = 0.005) and lower pre-extubation end-tidal co2 (odds ratio, 0.91; p = 0.006) were simultaneously associated with extubation failure while also controlling for the post-extubation respiratory support (CPAP/BiPAP/HFNC vs NC). CONCLUSIONS: Clinicians should not rely on CPAP or BiPAP as the only supportive measure for a patient at increased risk of extubation failure. CPAP or BiPAP do not mitigate the risk of extubation failure in the Norwood patients. A multisite study is needed to generalize these conclusions.

Optimal Fenestration of the Fontan Circulation.

In this paper, we develop a pulsatile compartmental model of the Fontan circulation and use it to explore the effects of a fenestration added to this physiology. A fenestration is a shunt between the systemic and pulmonary veins that is added either at the time of Fontan conversion or at a later time for the treatment of complications. This shunt increases cardiac output and decreases systemic venous pressure. However, these hemodynamic benefits are achieved at the expense of a decrease in the arterial oxygen saturation. The model developed in this paper incorporates fenestration size as a parameter and describes both blood flow and oxygen transport. It is calibrated to clinical data from Fontan patients, and we use it to study the impact of a fenestration on several hemodynamic variables, including systemic oxygen availability, effective oxygen availability, and systemic venous pressure. In certain scenarios corresponding to high-risk Fontan physiology, we demonstrate the existence of a range of fenestration sizes in which the systemic oxygen availability remains relatively constant while the systemic venous pressure decreases.

A novel automated junctional ectopic tachycardia detection tool for children with congenital heart disease.

Background: Junctional ectopic tachycardia (JET) is a prevalent life-threatening arrhythmia in children with congenital heart disease (CHD), with marked resemblance to normal sinus rhythm (NSR) often leading to delay in diagnosis. Objective: To develop a novel automated arrhythmia detection tool to identify JET. Methods: A single-center retrospective cohort study of children with CHD was performed. Electrocardiographic (ECG) data produced by bedside monitors is captured automatically by the Sickbay platform. Based on the detection of R and P wave peaks, 2 interpretable ECG features are calculated: P prominence median and PR interval interquartile range (IQR). These features are used as input to a simple logistic regression classification model built to distinguish JET from NSR. Results: This study analyzed a total of 64.5 physician-labeled hours consisting of 509,833 cardiac cycles (R-R intervals), from 40 patients with CHD. The extracted P prominence median feature is much smaller in JET compared to NSR, whereas the PR interval IQR feature is larger in JET compared to NSR. The area under the receiver operating characteristic curve for the unseen patient test cohort was 93%. Selecting a threshold of 0.73 results in a true-positive rate of 90% and a false-positive rate of 17%. Conclusion: This novel arrhythmia detection tool identifies JET, using 2 distinctive features of JET in ECG-the loss of a normal P wave and PR relationship-allowing for early detection and timely intervention.

Social and Demographic Disparities in the Severity of Multisystem Inflammatory Syndrome in Children.

Social constructs are known risk factors for multisystem inflammatory syndrome in children. A review of 206 patients demonstrated that children who were non-Hispanic Black, over the age of 12 years or living in a disadvantaged neighborhood associated with severe multisystem inflammatory syndrome in children (intensive care unit admission, intubation and/or vasopressor use).

Comparison of Laboratory and Hemodynamic Time Series Data Across Original, Alpha, and Delta Variants in Patients With Multisystem Inflammatory Syndrome in Children.

OBJECTIVES: To compare the clinical, laboratory, and hemodynamic parameters during hospitalization for patients with multisystem inflammatory syndrome in children (MIS-C), across the Original/Alpha and the Delta variants of severe acute respiratory syndrome coronavirus 2 infection. DESIGN: Retrospective cohort study. SETTING: Single-center quaternary children's hospital. PATIENTS: Children with MIS-C admitted from May 2020 to February 2021(Original and Alpha variant cohort) and August 2021 to November 2021 (Delta variant cohort). MEASUREMENTS AND MAIN RESULTS: Continuous vital sign measurements, laboratory results, medications data, and hospital outcomes from all subjects were evaluated. Of the 134 patients (102 with Original/Alpha and 32 with Delta), median age was 9 years, 75 (56%) were male, and 61 (46%) were Hispanics. The cohort with Original/Alpha variant had more males (61% vs 41%; p = 0.036) and more respiratory/musculoskeletal symptoms on presentation compared with the Delta variant ( p < 0.05). More patients in the Original/Alpha variant cohort received mechanical ventilation (16 vs 0; p = 0.009). Median hospital length of stay (LOS) was 7 days, and ICU LOS was 3 days for the entire cohort. ICU LOS was shorter in cohort with the Delta variant compared with the Original/Alpha variant (4 vs 2 d; p = 0.001). Only one patient had cardiac arrest, two needed extracorporeal membrane oxygenation, and two needed left ventricular assist device (Impella, Danvers, MA), all in the Original/Alpha variant cohort; no mortality occurred in the entire cohort. MIS-C cohort associated with the Delta variant had lower INR, prothrombin time, WBCs, sodium, phosphorus, and potassium median values ( p < 0.05) during hospitalization compared with the Original/Alpha variants. Hemodynamic assessment showed significant tachycardia in the Original/Alpha variants cohort compared with the Delta variant cohort ( p < 0.05). INTERVENTIONS: None. CONCLUSIONS: Patients with MIS-C associated with the Delta variants had lower severity during hospitalization compared with the Original/Alpha variant. Analysis of distinct trends in clinical and laboratory parameters with future variants of concerns will allow for potential modification of treatment protocol.

Artificial intelligence in the pediatric echocardiography laboratory: Automation, physiology, and outcomes.

Artificial intelligence (AI) is frequently used in non-medical fields to assist with automation and decision-making. The potential for AI in pediatric cardiology, especially in the echocardiography laboratory, is very high. There are multiple tasks AI is designed to do that could improve the quality, interpretation, and clinical application of echocardiographic data at the level of the sonographer, echocardiographer, and clinician. In this state-of-the-art review, we highlight the pertinent literature on machine learning in echocardiography and discuss its applications in the pediatric echocardiography lab with a focus on automation of the pediatric echocardiogram and the use of echo data to better understand physiology and outcomes in pediatric cardiology. We also discuss next steps in utilizing AI in pediatric echocardiography.

Automated Prediction of Cardiorespiratory Deterioration in Patients With Single Ventricle.

BACKGROUND: Patients with single-ventricle physiology have a significant risk of cardiorespiratory deterioration between their first and second stage palliation surgeries. OBJECTIVES: The objective of this study is to develop and validate a real-time computer algorithm that can automatically recognize physiological precursors of cardiorespiratory deterioration in children with single-ventricle physiology during their interstage hospitalization. METHODS: A retrospective study was conducted from prospectively collected physiological data of subjects with single-ventricle physiology. Deterioration events were defined as a cardiac arrest requiring cardiopulmonary resuscitation or an unplanned intubation. Physiological metrics were derived from the electrocardiogram (heart rate, heart rate variability, ST-segment elevation, and ST-segment variability) and the photoplethysmogram (peripheral oxygen saturation and pleth variability index). A logistic regression model was trained to separate the physiological dynamics of the pre-deterioration phase from all other data generated by study subjects. Data were split 50/50 into model training and validation sets to enable independent model validation. RESULTS: Our cohort consisted of 238 subjects admitted to the cardiac intensive care unit and stepdown units of Texas Children's Hospital over a period of 6 years. Approximately 300,000 h of high-resolution physiological waveform and vital sign data were collected using the Sickbay software platform (Medical Informatics Corp., Houston, Texas). A total of 112 cardiorespiratory deterioration events were observed. Seventy-two of the subjects experienced at least 1 deterioration event. The risk index metric generated by our optimized algorithm was found to be both sensitive and specific for detecting impending events 1 to 2 h in advance of overt extremis (receiver-operating characteristic curve area: 0.958; 95% confidence interval: 0.950 to 0.965). CONCLUSIONS: Our algorithm can provide 1 to 2 h of advanced warning for 62% of all cardiorespiratory deterioration events in children with single-ventricle physiology during their interstage period, with only 1 alarm being generated at the bedside per patient per day.

An Extended DEIM Algorithm for Subset Selection and Class Identification.

The discrete empirical interpolation method (DEIM) has been shown to be a viable index-selection technique for identifying representative subsets in data. Having gained some popularity in reducing dimensionality of physical models involving differential equations, its use in subset-/pattern-identification tasks is not yet broadly known within the machine learning community. While it has much to offer as is, the DEIM algorithm is limited in that the number of selected indices cannot exceed the rank of the corresponding data matrix. Although this is not an issue for many data sets, there are cases in which the number of classes represented in a given data set is greater than the rank of the data matrix; in such cases, it is impossible for the standard DEIM algorithm to identify all classes. To overcome this issue, we present a novel extension of DEIM, called E-DEIM. With the proposed algorithm, we also provide some theoretical results for using extensions of DEIM to form the CUR matrix factorization in identifying both rows and columns to approximate the original data matrix. Results from applying variations of E-DEIM to two different data sets indicate that the presented extension can indeed allow for the identification of additional classes along with those selected by standard DEIM. In addition, comparing these results to those of some more familiar methods demonstrates that the proposed deterministic E-DEIM approach including coherence performs comparably to or better than the other evaluated methods and should be considered in future class-identification tasks.

Novel Method of Calculating Pulse Pressure Variation to Predict Fluid Responsiveness to Transfusion in Very Low Birth Weight Infants.

A novel technique was used to calculate pulse pressure variation. The algorithm reliably predicted fluid responsiveness to transfusion, with a receiver operating characteristic area under the curve of 0.89. This technique may assist clinicians in the management of fluids and vasoactive medications for premature infants.

Critical Closing Pressure by Diffuse Correlation Spectroscopy in a Neonatal Piglet Model.

The critical closing pressure (CrCP) of the cerebral vasculature is the arterial blood pressure (ABP) at which cerebral blood flow (CBF) ceases. Because the ABP of preterm infants is low and close to the CrCP, there is often no CBF during diastole. Thus, estimation of CrCP may become clinically relevant in preterm neonates. Transcranial Doppler (TCD) ultrasound has been used to estimate CrCP in preterm infants. Diffuse correlation spectroscopy (DCS) is a continuous, noninvasive optical technique that measures microvascular CBF. Our objective was to compare and validate CrCP measured by DCS versus TCD ultrasound. Hemorrhagic shock was induced in 13 neonatal piglets, and CBF was measured continuously by both modalities. CrCP was calculated using a model of cerebrovascular impedance, and CrCP determined by the two modalities showed good correlation by linear regression, median r 2 = 0.8 (interquartile range (IQR) 0.71-0.87), and Bland-Altman analysis showed a median bias of -3.5 (IQR -4.6 to -0.28). This is the first comparison of CrCP determined by DCS versus TCD ultrasound in a neonatal piglet model of hemorrhagic shock. The difference in CrCP between the two modalities may be due to differences in vasomotor tone within the microvasculature of the cerebral arterioles versus the macrovasculature of a major cerebral artery.