Derivation, Validation, and Clinical Relevance of a Pediatric Sepsis Phenotype With Persistent Hypoxemia, Encephalopathy, and Shock

Diagnostic Identification of Acute Brain Dysfunction in Pediatric Sepsis and Septic Shock in the Electronic Health Record: A Comparison of Four Definitions in a Reference Dataset

OBJECTIVES

Acute brain dysfunction (ABD) in pediatric sepsis has a prevalence of 20%, but can be difficult to identify. Our previously validated ABD computational phenotype (CPABD) used variables obtained from the electronic health record indicative of clinician concern for acute neurologic or behavioral change. We tested whether the CPABD has better diagnostic performance to identify confirmed ABD than other definitions using the Glasgow Coma Scale or delirium scores.

DESIGN

Diagnostic testing in a curated cohort of pediatric sepsis/septic shock patients.

SETTING

Quaternary freestanding children's hospital.

SUBJECTS

The test dataset comprised 527 children with sepsis/septic shock managed between 2011 and 2021 with a prevalence (pretest probability) of confirmed ABD of 30% (159/527).

MEASUREMENTS AND MAIN RESULTS

CPABD was based on use of neuroimaging, electroencephalogram, and/or administration of new antipsychotic medication. We compared the performance of the CPABD with three GCS/delirium-based definitions of ABD-Proulx et al, International Pediatric Sepsis Consensus Conference, and Pediatric Organ Dysfunction Information Update Mandate. The posttest probability of identifying ABD was highest in CPABD (0.84) compared with other definitions. CPABD also had the highest sensitivity (83%; 95% CI, 76-89%) and specificity (93%; 95% CI, 90-96%). The false discovery rate was lowest in CPABD (1-in-6) as was the false omission rate (1-in-14). Finally, the prevalence threshold for the definitions varied, with the CPABD being the definition closest to 20%.

CONCLUSIONS

In our curated dataset of pediatric sepsis/septic shock, CPABD had favorable characteristics to identify confirmed ABD compared with GCS/delirium-based definitions. The CPABD can be used to further study the impact of ABD in studies using large electronic health datasets.

Host gene expression signatures to identify infection type and organ dysfunction in children evaluated for sepsis: a multicentre cohort study

BACKGROUND

Sepsis is defined as dysregulated host response to infection that leads to life-threatening organ dysfunction. Biomarkers characterising the dysregulated host response in sepsis are lacking. We aimed to develop host gene expression signatures to predict organ dysfunction in children with bacterial or viral infection.

METHODS

This cohort study was done in emergency departments and intensive care units of four hospitals in Queensland, Australia, and recruited children aged 1 month to 17 years who, upon admission, underwent a diagnostic test, including blood cultures, for suspected sepsis. Whole-blood RNA sequencing of blood was performed with Illumina NovaSeq (San Diego, CA, USA). Samples with completed phenotyping, monitoring, and RNA extraction by March 31, 2020, were included in the discovery cohort; samples collected or completed thereafter and by Oct 27, 2021, constituted the Rapid Paediatric Infection Diagnosis in Sepsis (RAPIDS) internal validation cohort. An external validation cohort was assembled from RNA sequencing gene expression count data from the observational European Childhood Life-threatening Infectious Disease Study (EUCLIDS), which recruited children with severe infection in nine European countries between 2012 and 2016. Feature selection approaches were applied to derive novel gene signatures for disease class (bacterial vs viral infection) and disease severity (presence vs absence of organ dysfunction 24 h post-sampling). The primary endpoint was the presence of organ dysfunction 24 h after blood sampling in the presence of confirmed bacterial versus viral infection. Gene signature performance is reported as area under the receiver operating characteristic curves (AUCs) and 95% CI.

FINDINGS

Between Sept 25, 2017, and Oct 27, 2021, 907 patients were enrolled. Blood samples from 595 patients were included in the discovery cohort, and samples from 312 children were included in the RAPIDS validation cohort. We derived a ten-gene disease class signature that achieved an AUC of 94·1% (95% CI 90·6-97·7) in distinguishing bacterial from viral infections in the RAPIDS validation cohort. A ten-gene disease severity signature achieved an AUC of 82·2% (95% CI 76·3-88·1) in predicting organ dysfunction within 24 h of sampling in the RAPIDS validation cohort. Used in tandem, the disease class and disease severity signatures predicted organ dysfunction within 24 h of sampling with an AUC of 90·5% (95% CI 83·3-97·6) for patients with predicted bacterial infection and 94·7% (87·8-100·0) for patients with predicted viral infection. In the external EUCLIDS validation dataset (n=362), the disease class and disease severity predicted organ dysfunction at time of sampling with an AUC of 70·1% (95% CI 44·1-96·2) for patients with predicted bacterial infection and 69·6% (53·1-86·0) for patients with predicted viral infection.

INTERPRETATION

In children evaluated for sepsis, novel host transcriptomic signatures specific for bacterial and viral infection can identify dysregulated host response leading to organ dysfunction.

FUNDING

Australian Government Medical Research Future Fund Genomic Health Futures Mission, Children's Hospital Foundation Queensland, Brisbane Diamantina Health Partners, Emergency Medicine Foundation, Gold Coast Hospital Foundation, Far North Queensland Foundation, Townsville Hospital and Health Services SERTA Grant, and Australian Infectious Diseases Research Centre.

Pediatric Sepsis Phenotypes and Outcome: 5-Year Retrospective Cohort Study in a Single Center in India (2017-2022)

OBJECTIVES

To describe mortality associated with different clinical phenotypes of sepsis in children.

DESIGN

Retrospective study.

SETTING

PICU of a tertiary care center in India from 2017 to 2022.

PATIENTS

Six hundred twelve children (from 2 mo to 17 yr old) with a retrospectively applied diagnosis of sepsis using 2020 guidance.

METHODS

The main outcome was mortality associated with sepsis subtypes. Other analyses included assessment of risk factors, requirement for organ support, and PICU resources used by sepsis phenotype. Clinical data were recorded on a predesigned proforma.

INTERVENTIONS

None.

MEASUREMENTS AND RESULTS

Of the 612 children identified, there were 382 (62%) with sepsis but no multiple organ failure (NoMOF), 48 (8%) with thrombocytopenia-associated MOF (TAMOF), 140 (23%) with MOF without thrombocytopenia, and 40 (6.5%) with sequential MOF (SMOF). Mortality was higher in the SMOF (20/40 [50%]), MOF (62/140 [44%]) and TAMOF (20/48 [42%]) groups, compared with NoMOF group (82/382 [21%] [ p < 0.001]). The requirement for organ support and PICU resources was higher in all phenotypes with MOF as compared with those without MOF. On multivariable analysis elevated lactate and having MOF were associated with greater odds of mortality.

CONCLUSIONS

In this single-center experience of sepsis in India, we found that sepsis phenotypes having MOF were associated with mortality and the requirement of PICU resources. Prospective studies in different regions of the world will help identify a classification of pediatric sepsis that is more widely applicable.

The Pediatric Data Science and Analytics Subgroup of the Pediatric Acute Lung Injury and Sepsis Investigators Network: Use of Supervised Machine Learning Applications in Pediatric Critical Care Medicine Research

OBJECTIVE

Perform a scoping review of supervised machine learning in pediatric critical care to identify published applications, methodologies, and implementation frequency to inform best practices for the development, validation, and reporting of predictive models in pediatric critical care.

DESIGN

Scoping review and expert opinion.

SETTING

We queried CINAHL Plus with Full Text (EBSCO), Cochrane Library (Wiley), Embase (Elsevier), Ovid Medline, and PubMed for articles published between 2000 and 2022 related to machine learning concepts and pediatric critical illness. Articles were excluded if the majority of patients were adults or neonates, if unsupervised machine learning was the primary methodology, or if information related to the development, validation, and/or implementation of the model was not reported. Article selection and data extraction were performed using dual review in the Covidence tool, with discrepancies resolved by consensus.

SUBJECTS

Articles reporting on the development, validation, or implementation of supervised machine learning models in the field of pediatric critical care medicine.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Of 5075 identified studies, 141 articles were included. Studies were primarily (57%) performed at a single site. The majority took place in the United States (70%). Most were retrospective observational cohort studies. More than three-quarters of the articles were published between 2018 and 2022. The most common algorithms included logistic regression and random forest. Predicted events were most commonly death, transfer to ICU, and sepsis. Only 14% of articles reported external validation, and only a single model was implemented at publication. Reporting of validation methods, performance assessments, and implementation varied widely. Follow-up with authors suggests that implementation remains uncommon after model publication.

CONCLUSIONS

Publication of supervised machine learning models to address clinical challenges in pediatric critical care medicine has increased dramatically in the last 5 years. While these approaches have the potential to benefit children with critical illness, the literature demonstrates incomplete reporting, absence of external validation, and infrequent clinical implementation.

Biomarker Assessment of a High-Risk, Data-Driven Pediatric Sepsis Phenotype Characterized by Persistent Hypoxemia, Encephalopathy, and Shock

OBJECTIVES

Identification of children with sepsis-associated multiple organ dysfunction syndrome (MODS) at risk for poor outcomes remains a challenge. We sought to the determine reproducibility of the data-driven "persistent hypoxemia, encephalopathy, and shock" (PHES) phenotype and determine its association with inflammatory and endothelial biomarkers, as well as biomarker-based pediatric risk strata.

DESIGN

We retrained and validated a random forest classifier using organ dysfunction subscores in the 2012-2018 electronic health record (EHR) dataset used to derive the PHES phenotype. We used this classifier to assign phenotype membership in a test set consisting of prospectively (2003-2023) enrolled pediatric septic shock patients. We compared profiles of the PERSEVERE family of biomarkers among those with and without the PHES phenotype and determined the association with established biomarker-based mortality and MODS risk strata.

SETTING

Twenty-five PICUs across the United States.

PATIENTS

EHR data from 15,246 critically ill patients with sepsis-associated MODS split into derivation and validation sets and 1,270 pediatric septic shock patients in the test set of whom 615 had complete biomarker data.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

The area under the receiver operator characteristic curve of the modified classifier to predict PHES phenotype membership was 0.91 (95% CI, 0.90-0.92) in the EHR validation set. In the test set, PHES phenotype membership was associated with both increased adjusted odds of complicated course (adjusted odds ratio [aOR] 4.1; 95% CI, 3.2-5.4) and 28-day mortality (aOR of 4.8; 95% CI, 3.11-7.25) after controlling for age, severity of illness, and immunocompromised status. Patients belonging to the PHES phenotype were characterized by greater degree of systemic inflammation and endothelial activation, and were more likely to be stratified as high risk based on PERSEVERE biomarkers predictive of death and persistent MODS.

CONCLUSIONS

The PHES trajectory-based phenotype is reproducible, independently associated with poor clinical outcomes, and overlapped with higher risk strata based on prospectively validated biomarker approaches.

Editor's Choice Articles for September

The September 2023 issue and this year has already proven to be important for improving our understanding of pediatric acute respiratory distress syndrome (PARDS); Pediatric Critical Care Medicine (PCCM) has published 16 articles so far. Therefore, my three Editor's Choice articles this month highlight yet more PCCM material about PARDS by covering the use of noninvasive ventilation (NIV), the trajectory in cytokine profile during illness, and a new look at lung mechanics. The PCCM Connections for Readers give us the opportunity to focus on some clinical biomarkers of severity and mortality risk during critical illness.

External validation and biomarker assessment of a high-risk, data-driven pediatric sepsis phenotype characterized by persistent hypoxemia, encephalopathy, and shock

Objective

Identification of children with sepsis-associated multiple organ dysfunction syndrome (MODS) at risk for poor outcomes remains a challenge. Data-driven phenotyping approaches that leverage electronic health record (EHR) data hold promise given the widespread availability of EHRs. We sought to externally validate the data-driven 'persistent hypoxemia, encephalopathy, and shock' (PHES) phenotype and determine its association with inflammatory and endothelial biomarkers, as well as biomarker-based pediatric risk-strata.

Design

We trained and validated a random forest classifier using organ dysfunction subscores in the EHR dataset used to derive the PHES phenotype. We used the classifier to assign phenotype membership in a test set consisting of prospectively enrolled pediatric septic shock patients. We compared biomarker profiles of those with and without the PHES phenotype and determined the association with established biomarker-based mortality and MODS risk-strata.

Setting

25 pediatric intensive care units (PICU) across the U.S.

Patients

EHR data from 15,246 critically ill patients sepsis-associated MODS and 1,270 pediatric septic shock patients in the test cohort of whom 615 had biomarker data.

Interventions

None.

Measurements and Main Results

The area under the receiver operator characteristic curve (AUROC) of the new classifier to predict PHES phenotype membership was 0.91(95%CI, 0.90-0.92) in the EHR validation set. In the test set, patients with the PHES phenotype were independently associated with both increased odds of complicated course (adjusted odds ratio [aOR] of 4.1, 95%CI: 3.2-5.4) and 28-day mortality (aOR of 4.8, 95%CI: 3.11-7.25) after controlling for age, severity of illness, and immuno-compromised status. Patients belonging to the PHES phenotype were characterized by greater degree of systemic inflammation and endothelial activation, and overlapped with high risk-strata based on PERSEVERE biomarkers predictive of death and persistent MODS.

Conclusions

The PHES trajectory-based phenotype is reproducible, independently associated with poor clinical outcomes, and overlap with higher risk-strata based on validated biomarker approaches.