iCVS-Inferring Cardio-Vascular hidden States from physiological signals available at the bedside.

Intensive care medicine is complex and resource-demanding. A critical and common challenge lies in inferring the underlying physiological state of a patient from partially observed data. Specifically for the cardiovascular system, clinicians use observables such as heart rate, arterial and venous blood pressures, as well as findings from the physical examination and ancillary tests to formulate a mental model and estimate hidden variables such as cardiac output, vascular resistance, filling pressures and volumes, and autonomic tone. Then, they use this mental model to derive the causes for instability and choose appropriate interventions. Not only this is a very hard problem due to the nature of the signals, but it also requires expertise and a clinician's ongoing presence at the bedside. Clinical decision support tools based on mechanistic dynamical models offer an appealing solution due to their inherent explainability, corollaries to the clinical mental process, and predictive power. With a translational motivation in mind, we developed iCVS: a simple, with high explanatory power, dynamical mechanistic model to infer hidden cardiovascular states. Full model estimation requires no prior assumptions on physiological parameters except age and weight, and the only inputs are arterial and venous pressure waveforms. iCVS also considers autonomic and non-autonomic modulations. To gain more information without increasing model complexity, both slow and fast timescales of the blood pressure traces are exploited, while the main inference and dynamic evolution are at the longer, clinically relevant, timescale of minutes. iCVS is designed to allow bedside deployment at pediatric and adult intensive care units and for retrospective investigation of cardiovascular mechanisms underlying instability. In this paper, we describe iCVS and inference system in detail, and using a dataset of critically-ill children, we provide initial indications to its ability to identify bleeding, distributive states, and cardiac dysfunction, in isolation and in combination.

Development and validation of a multivariable prediction model in pediatric liver transplant patients for predicting intensive care unit length of stay.

BACKGROUND: Liver transplantation is the life-saving treatment for many end-stage pediatric liver diseases. The perioperative course, including surgical and anesthetic factors, have an important influence on the trajectory of this high-risk population. Given the complexity and variability of the immediate postoperative course, there would be utility in identifying risk factors that allow prediction of adverse outcomes and intensive care unit trajectories. AIMS: The aim of this study was to develop and validate a risk prediction model of prolonged intensive care unit length of stay in the pediatric liver transplant population. METHODS: This is a retrospective analysis of consecutive pediatric isolated liver transplant recipients at a single institution between April 1, 2013 and April 30, 2020. All patients under the age of 18 years receiving a liver transplant were included in the study (n = 186). The primary outcome was intensive care unit length of stay greater than 7 days. RESULTS: Recipient and donor characteristics were used to develop a multivariable logistic regression model. A total of 186 patients were included in the study. Using multivariable logistic regression, we found that age < 12 months (odds ratio 4.02, 95% confidence interval 1.20-13.51, p = .024), metabolic or cholestatic disease (odds ratio 2.66, 95% confidence interval 1.01-7.07, p = .049), 30-day pretransplant hospital admission (odds ratio 8.59, 95% confidence interval 2.27-32.54, p = .002), intraoperative red blood cells transfusion >40 mL/kg (odds ratio 3.32, 95% confidence interval 1.12-9.81, p = .030), posttransplant return to the operating room (odds ratio 11.45, 95% confidence interval 3.04-43.16, p = .004), and major postoperative respiratory event (odds ratio 32.14, 95% confidence interval 3.00-343.90, p < .001) were associated with prolonged intensive care unit length of stay. The model demonstrates a good discriminative ability with an area under the receiver operative curve of 0.888 (95% confidence interval, 0.824-0.951). CONCLUSIONS: We develop and validate a model to predict prolonged intensive care unit length of stay in pediatric liver transplant patients using risk factors from all phases of the perioperative period.

Temporal Variability in the Sampling of Vital Sign Data Limits the Accuracy of Patient State Estimation.

OBJECTIVES: Physiologic signals are typically measured continuously in the critical care unit, but only recorded at intermittent time intervals in the patient health record. Low frequency data collection may not accurately reflect the variability and complexity of these signals or the patient's clinical state. We aimed to characterize how increasing the temporal window size of observation from seconds to hours modifies the measured variability and complexity of basic vital signs. DESIGN: Retrospective analysis of signal data acquired between April 1, 2013, and September 30, 2015. SETTING: Critical care unit at The Hospital for Sick Children, Toronto. PATIENTS: Seven hundred forty-seven patients less than or equal to 18 years old (63,814,869 data values), within seven diagnostic/surgical groups. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Measures of variability (SD and the absolute differences) and signal complexity (multiscale sample entropy and detrended fluctuation analysis [expressed as the scaling component α]) were calculated for systolic blood pressure, heart rate, and oxygen saturation. The variability of all vital signs increases as the window size increases from seconds to hours at the patient and diagnostic/surgical group level. Significant differences in the magnitude of variability for all time scales within and between groups was demonstrated (p < 0.0001). Variability correlated negatively with patient age for heart rate and oxygen saturation, but positively with systolic blood pressure. Changes in variability and complexity of heart rate and systolic blood pressure from time of admission to discharge were found. CONCLUSIONS: In critically ill children, the temporal variability of physiologic signals supports higher frequency data capture, and this variability should be accounted for in models of patient state estimation.

Variation in care for children undergoing the Fontan operation for hypoplastic left heart syndrome.

BACKGROUND: The Single Ventricle Reconstruction Trial randomised neonates with hypoplastic left heart syndrome to a shunt strategy but otherwise retained standard of care. We aimed to describe centre-level practice variation at Fontan completion. METHODS: Centre-level data are reported as median or median frequency across all centres and range of medians or frequencies across centres. Classification and regression tree analysis assessed the association of centre-level factors with length of stay and percentage of patients with prolonged pleural effusion (>7 days). RESULTS: The median Fontan age (14 centres, 320 patients) was 3.1 years (range from 1.7 to 3.9), and the weight-for-age z-score was -0.56 (-1.35 + 0.44). Extra-cardiac Fontans were performed in 79% (4-100%) of patients at the 13 centres performing this procedure; lateral tunnels were performed in 32% (3-100%) at the 11 centres performing it. Deep hypothermic circulatory arrest (nine centres) ranged from 6 to 100%. Major complications occurred in 17% (7-33%). The length of stay was 9.5 days (9-12); 15% (6-33%) had prolonged pleural effusion. Centres with fewer patients (<6%) with prolonged pleural effusion and fewer (<41%) complications had a shorter length of stay (<10 days; sensitivity 1.0; specificity 0.71; area under the curve 0.96). Avoiding deep hypothermic circulatory arrest and higher weight-for-age z-score were associated with a lower percentage of patients with prolonged effusions (<9.5%; sensitivity 1.0; specificity = 0.86; area under the curve 0.98). CONCLUSIONS: Fontan perioperative practices varied widely among study centres. Strategies to decrease the duration of pleural effusion and minimise complications may decrease the length of stay. Further research regarding deep hypothermic circulatory arrest is needed to understand its association with prolonged pleural effusion.

Distributions and Behavior of Vital Signs in Critically Ill Children by Admission Diagnosis.

OBJECTIVES: Define the distributions of heart rate and intraarterial blood pressure in children at admission to an ICU based on admission diagnosis and examine trends in these physiologic signs over 72 hours from admission (or to discharge if earlier). DESIGN: A retrospective analysis of continuously acquired signals. SETTING: A quaternary and primary referral children's hospital with a general PICU and cardiac critical care unit. PATIENTS: One thousand two hundred eighty-nine patients less than 18 years old were analyzed. Data from individual patient admissions were divided into 19 groups by primary admission diagnosis or surgical procedure. INTERVENTIONS: None. MEASUREMENT AND MAIN RESULTS: Distributions at admission are dependent on patient age and admission diagnosis (p < 10(-6)). Heart rate decreases over time, whereas arterial blood pressure is relatively stable, with differences seen in the directions and magnitude of these trends when analyzed by diagnosis group (p < 10(-6)). Multiple linear regression analysis shows that patient age, diagnosis group, and physiologic vital sign value at admission explain 50-63% of the variation observed for that physiologic signal at 72 hours (or at discharge if earlier) with admission value having the greatest influence. Furthermore, the variance of either heart rate or arterial blood pressure for the individual patient is smaller than the variance measured at the level of the group of patients with the same diagnosis. CONCLUSIONS: This is the first study reporting distributions of continuously measured physiologic variables and trends in their behavior according to admission diagnosis in critically ill children. Differences detected between and within diagnostic groups may aid in earlier recognition of outliers as well as allowing refinement of patient monitoring strategies.

Diagnostic errors in paediatric cardiac intensive care.

IntroductionDiagnostic errors cause significant patient harm and increase costs. Data characterising such errors in the paediatric cardiac intensive care population are limited. We sought to understand the perceived frequency and types of diagnostic errors in the paediatric cardiac ICU. METHODS: Paediatric cardiac ICU practitioners including attending and trainee physicians, nurse practitioners, physician assistants, and registered nurses at three North American tertiary cardiac centres were surveyed between October 2014 and January 2015. RESULTS: The response rate was 46% (N=200). Most respondents (81%) perceived that diagnostic errors harm patients more than five times per year. More than half (65%) reported that errors permanently harm patients, and up to 18% perceived that diagnostic errors contributed to death or severe permanent harm more than five times per year. Medication side effects and psychiatric conditions were thought to be most commonly misdiagnosed. Physician groups also ranked pulmonary overcirculation and viral illness to be commonly misdiagnosed as bacterial illness. Inadequate care coordination, data assessment, and high clinician workload were cited as contributory factors. Delayed diagnostic studies and interventions related to the severity of the patient's condition were thought to be the most commonly reported process breakdowns. All surveyed groups ranked improving teamwork and feedback pathways as strategies to explore for preventing future diagnostic errors. CONCLUSIONS: Paediatric cardiac intensive care practitioners perceive that diagnostic errors causing permanent harm are common and associated more with systematic and process breakdowns than with cognitive limitations.

Risk Factors for Cardiac Arrest or Mechanical Circulatory Support in Children with Fulminant Myocarditis.

In children with fulminant myocarditis (FM), we sought to describe presenting characteristics and clinical outcomes, and identify risk factors for cardiac arrest and mechanical circulatory support (MCS). A retrospective review of patients with FM admitted at our institution between January 1, 2004, and June 31, 2015, was performed. We compared characteristics and outcomes of FM patients who received cardiopulmonary resuscitation (CPR) and/or were placed on MCS (CPR/MCS group) to those who did not develop these outcomes (Control group). There were 28 patients who met criteria for FM. Median age was 1.2 years (1 day-17 years). Recovery of myocardial function occurred in 13 patients (46%); 6 (21%) had chronic ventricular dysfunction, 6 (21%) underwent heart transplantation, and 3 (11%) died prior to hospital discharge (including one death following heart transplant). Of the 28 FM patients, 13 (46%) developed cardiac arrest (n = 11) and/or received MCS (n = 8). When compared to controls, patients in the CPR/MCS group had a higher peak b-type natriuretic peptide (BNP) levels (p = 0.03) and peak inotropic scores (p = 0.02). No significant differences were found between groups in demographics; chest radiograph, electrocardiogram, or echocardiogram findings; or initial laboratory values including BNP, troponin, C-reactive protein, lactate, and creatinine (p > 0.05 for all). Children with FM are at high risk of cardiovascular collapse leading to the use of CPR or MCS. Aside from peak BNP levels and inotropic scores, the most presenting characteristics were not helpful for predicting these outcomes. FM patients should ideally receive care in centers that provide emergent MCS.

Shunt Lesions Part I: Patent Ductus Arteriosus, Atrial Septal Defect, Ventricular Septal Defect, and Atrioventricular Septal Defect.

OBJECTIVES: This review summarizes the current understanding of the pathophysiology and perioperative management of patent ductus arteriosus, atrial septal defect, ventricular septal defect, and atrioventricular septal defect. DATA SOURCE: MEDLINE and PubMed. CONCLUSIONS: The four congenital cardiac lesions that are the subject of this review, patent ductus arteriosus, atrial septal defect, ventricular septal defect, and atrioventricular septal defect, are the most commonly found defects causing a left-to-right shunt. These defects frequently warrant transcatheter or surgical intervention. Although the perioperative care is relatively straightforward for many of these patients, there are a number of management strategies and complications associated with each intervention. The treatment outcomes for all of these lesions are very good in the current era.

Critical care for paediatric patients with heart failure.

This review offers a critical-care perspective on the pathophysiology, monitoring, and management of acute heart failure syndromes in children. An in-depth understanding of the cardiovascular physiological disturbances in this population of patients is essential to correctly interpret clinical signs, symptoms and monitoring data, and to implement appropriate therapies. In this regard, the myocardial force-velocity relationship, the Frank-Starling mechanism, and pressure-volume loops are discussed. A variety of monitoring modalities are used to provide insight into the haemodynamic state, clinical trajectory, and response to treatment. Critical-care treatment of acute heart failure is based on the fundamental principles of optimising the delivery of oxygen and minimising metabolic demands. The former may be achieved by optimising systemic arterial oxygen content and the variables that determine cardiac output: heart rate and rhythm, preload, afterload, and contractility. Metabolic demands may be decreased by a number of ways including positive pressure ventilation, temperature control, and sedation. Mechanical circulatory support should be considered for refractory cases. In the near future, monitoring modalities may be improved by the capture and analysis of complex clinical data such as pressure waveforms and heart rate variability. Using predictive modelling and streaming analytics, these data may then be used to develop automated, real-time clinical decision support tools. Given the barriers to conducting multi-centre trials in this population of patients, the thoughtful analysis of data from multi-centre clinical registries and administrative databases will also likely have an impact on clinical practice.

AnnoDash, a clinical terminology annotation dashboard.

Background: Standard ontologies are critical for interoperability and multisite analyses of health data. Nevertheless, mapping concepts to ontologies is often done with generic tools and is labor-intensive. Contextualizing candidate concepts within source data is also done in an ad hoc manner. Methods and Results: We present AnnoDash, a flexible dashboard to support annotation of concepts with terms from a given ontology. Text-based similarity is used to identify likely matches, and large language models are used to improve ontology ranking. A convenient interface is provided to visualize observations associated with a concept, supporting the disambiguation of vague concept descriptions. Time-series plots contrast the concept with known clinical measurements. We evaluated the dashboard qualitatively against several ontologies (SNOMED CT, LOINC, etc.) by using MIMIC-IV measurements. The dashboard is web-based and step-by-step instructions for deployment are provided, simplifying usage for nontechnical audiences. The modular code structure enables users to extend upon components, including improving similarity scoring, constructing new plots, or configuring new ontologies. Conclusion: AnnoDash, an improved clinical terminology annotation tool, can facilitate data harmonizing by promoting mapping of clinical data. AnnoDash is freely available at https://github.com/justin13601/AnnoDash (https://doi.org/10.5281/zenodo.8043943).

Beyond Conventional Hemodynamic Monitoring-Monitoring to Improve Our Understanding of Disease Process and Interventions.

Monitoring the hemodynamic state of patients is a hallmark of any intensive care environment. However, no single monitoring strategy can provide all the necessary data to paint the entire picture of the state of a patient; each monitor has strengths and weaknesses, advantages, and limitations. We review the currently available hemodynamic monitors used in pediatric critical care units using a clinical scenario. This provides the reader with a construct to understand the progression from basic to more advanced monitoring modalities and how they serve to inform the practitioner at the bedside.

Making machine learning matter to clinicians: model actionability in medical decision-making.

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.

Pitfalls and Possibilities of Ventricular Assist Device Support in Congenitally Corrected Transposition of the Great Arteries in Children.

Congenitally corrected transposition of the great arteries (ccTGAs) represents a complex form of congenital heart disease that is associated with several cardiac complications. Herein is a case series of three children with ccTGA and ventricular assist device (VAD) inserted for systemic right ventricle failure at a single institution. All patients remained hemodynamically stable postimplant and were successfully discharged from the intensive care unit to undergo postoperative rehabilitation. All three patients received an orthotopic heart transplant with uneventful posttransplant courses. This case series provides insight into the medical management and technical feasibility of VAD support in children with ccTGA with end-stage heart failure.

The truth Hertz-synchronization of electroencephalogram signals with physiological waveforms recorded in an intensive care unit.

Objective.The ability to synchronize continuous electroencephalogram (cEEG) signals with physiological waveforms such as electrocardiogram (ECG), invasive pressures, photoplethysmography and other signals can provide meaningful insights regarding coupling between brain activity and other physiological subsystems. Aligning these datasets is a particularly challenging problem because device clocks handle time differently and synchronization protocols may be undocumented or proprietary.Approach.We used an ensemble-based model to detect the timestamps of heartbeat artefacts from ECG waveforms recorded from inpatient bedside monitors and from cEEG signals acquired using a different device. Vectors of inter-beat intervals were matched between both datasets and robust linear regression was applied to measure the relative time offset between the two datasets as a function of time.Main Results.The timing error between the two unsynchronized datasets ranged between -84 s and +33 s (mean 0.77 s, median 4.31 s, IQR25-4.79 s, IQR75 11.38s). Application of our method improved the relative alignment to within ± 5ms for more than 61% of the dataset. The mean clock drift between the two datasets was 418.3 parts per million (ppm) (median 414.6 ppm, IQR25 411.0 ppm, IQR75 425.6 ppm). A signal quality index was generated that described the quality of alignment for each cEEG study as a function of time.Significance.We developed and tested a method to retrospectively time-align two clinical waveform datasets acquired from different devices using a common signal. The method was applied to 33,911h of signals collected in a paediatric critical care unit over six years, demonstrating that the method can be applied to long-term recordings collected under clinical conditions. The method can account for unknown clock drift rates and the presence of discontinuities caused by clock resynchronization events.

Ignorance Isn't Bliss: We Must Close the Machine Learning Knowledge Gap in Pediatric Critical Care.

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.

Relieving bronchial compression due to cardiomegaly: The role of aortopexy when left ventricular assist device support just is not enough.

Enlarged cardiac structures, especially those on left side have the potential to cause airway compression in pediatric patients with chronic heart failure, owing to their proximity to and impact on the trachea-bronchial tree. Ventricular assist devices are effective in decompressing such hearts thereby alleviating airway problems. Aortopexy serves as an effective airway decompressive measure in cases with persistent airway compression despite effective cardiac decompression by ventricular assist devices. We report a case of 1-year-old male patient with dilated cardiomyopathy in whom airway compression persisted despite ventricular assist device implantation. Aortopexy was effective in relieving airway compression allowing for subsequent extubation and successful heart transplantation.

Successful Pediatric Mechanical Thrombectomy for HeartMate 3-Related Intracranial Thromboembolism.

Thromboembolic events post left ventricular assist devices (LVAD) implantation remain a major cause of morbidity and mortality. Mechanical thrombectomy for the treatment of pediatric intracranial thromboembolic events have been reported in LVADs, but never following HeartMate 3 (HM3) implantation. We present the case of an 8-year-old, 26.5 kg male with dilated cardiomyopathy and decompensated heart failure who presented with extensive intracranial thromboembolism in the early postoperative period following HM3 implantation and underwent successful mechanical thrombectomy with a favorable neurological outcome.

Care of the critically ill neonate with hypoxemic respiratory failure and acute pulmonary hypertension: framework for practice based on consensus opinion of neonatal hemodynamics working group.

Circulatory transition after birth presents a critical period whereby the pulmonary vascular bed and right ventricle must adapt to rapidly changing loading conditions. Failure of postnatal transition may present as hypoxemic respiratory failure, with disordered pulmonary and systemic blood flow. In this review, we present the biological and clinical contributors to pathophysiology and present a management framework.

An integration engineering framework for machine learning in healthcare.

Background and Objectives: Machine Learning offers opportunities to improve patient outcomes, team performance, and reduce healthcare costs. Yet only a small fraction of all Machine Learning models for health care have been successfully integrated into the clinical space. There are no current guidelines for clinical model integration, leading to waste, unnecessary costs, patient harm, and decreases in efficiency when improperly implemented. Systems engineering is widely used in industry to achieve an integrated system of systems through an interprofessional collaborative approach to system design, development, and integration. We propose a framework based on systems engineering to guide the development and integration of Machine Learning models in healthcare. Methods: Applied systems engineering, software engineering and health care Machine Learning software development practices were reviewed and critically appraised to establish an understanding of limitations and challenges within these domains. Principles of systems engineering were used to develop solutions to address the identified problems. The framework was then harmonized with the Machine Learning software development process to create a systems engineering-based Machine Learning software development approach in the healthcare domain. Results: We present an integration framework for healthcare Artificial Intelligence that considers the entirety of this system of systems. Our proposed framework utilizes a combined software and integration engineering approach and consists of four phases: (1) Inception, (2) Preparation, (3) Development, and (4) Integration. During each phase, we present specific elements for consideration in each of the three domains of integration: The Human, The Technical System, and The Environment. There are also elements that are considered in the interactions between these domains. Conclusion: Clinical models are technical systems that need to be integrated into the existing system of systems in health care. A systems engineering approach to integration ensures appropriate elements are considered at each stage of model design to facilitate model integration. Our proposed framework is based on principles of systems engineering and can serve as a guide for model development, increasing the likelihood of successful Machine Learning translation and integration.