Search

Abstract Preschool children with recurrent wheezing are a heterogeneous population with many underlying biological pathways that contribute to clinical presentations. Although the morbidity of recurrent wheezing in preschool children is significant, biological studies in this population remain quite limited. To address this gap, this study performed untargeted plasma metabolomic analyses in 68 preschool children with recurrent wheezing to identify metabolomic endotypes of wheezing. K-means cluster analysis was performed on metabolomic dataset including a total of 1382 named and unnamed metabolites. We identified three metabolomic clusters which differed in symptom severity, exacerbation occurrence, and variables associated with social disadvantage. Metabolites that distinguished the clusters included those involved in fatty acid metabolism, fatty acids (long chain monounsaturated fatty acids, long chain polyunsaturated fatty acids, and long chain saturated fatty acids), lysophospholipids, phosphatidylcholines, and phosphatidylethanolamines. Pathway analyses identified pathways of interest in each cluster, including steroid metabolism, histidine metabolism, sphingomyelins, and sphingosines, among others. This study highlights the biologic complexity of recurrent wheezing in preschool children and offers novel metabolites and pathways that may be amenable to future study and intervention.

OBJECTIVES:. Monocytes are plastic cells that assume different polarization states that can either promote inflammation or tissue repair and inflammation resolution. Polarized monocytes are partially defined by their transcriptional profiles that are influenced by environmental stimuli. The airway monocyte response in pediatric acute respiratory distress syndrome (PARDS) is undefined. To identify differentially expressed genes and networks using a novel transcriptomic reporter assay with donor monocytes exposed to the airway fluid of intubated children with and at-risk for PARDS. To determine differences in gene expression at two time points using the donor monocyte assay exposed to airway fluid from intubated children with PARDS obtained 48–96 hours following initial tracheal aspirate sampling. DESIGN:. In vitro pilot study carried out using airway fluid supernatant. SETTING:. Academic 40-bed PICU. PARTICIPANTS:. Fifty-seven children: 44 children with PARDS and 13 children at-risk for PARDS. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. We performed bulk RNA sequencing using a transcriptomic reporter assay of monocytes exposed to airway fluid from intubated children to discover gene networks differentiating PARDS from at-risk for PARDS and those differentiating mild/moderate from severe PARDS. We also report differences in gene expression in children with PARDS 48–96 hours following initial tracheal aspirate sampling. We found that interleukin (IL)-10, IL-4, and IL-13, cytokine/chemokine signaling, and the senescence-associated secretory phenotype are upregulated in monocytes exposed to airway fluid from intubated children with PARDS compared with those at-risk for PARDS. Signaling by NOTCH, histone deacetylation/acetylation, DNA methylation, chromatin modifications (B-WICH complex), and RNA polymerase I transcription and its associated regulatory apparatus were upregulated in children with PARDS 48–96 hours following initial tracheal aspirate sampling. CONCLUSIONS:. We identified gene networks important to the PARDS airway immune response using bulk RNA sequencing from a monocyte reporter assay that exposed monocytes to airway fluid from intubated children with and at-risk for PARDS. Mechanistic investigations are needed to validate our findings.

Background: The innate mechanisms associated with viral exacerbations in preschool children with recurrent wheezing are not understood. Objective: We sought to assess differential gene expression in blood neutrophils from preschool children with recurrent wheezing, stratified by aeroallergen sensitization, at baseline and after exposure to polyinosinic:polycytidylic acid (poly(I:C)) and also to examine whether poly(I:C)-stimulated blood neutrophils influenced airway epithelial gene expression. Methods: Blood neutrophils were purified and cultured overnight with poly(I:C) and underwent next-generation sequencing with Reactome pathway analysis. Primary human small airway epithelial cells were treated with poly(I:C)-treated neutrophil culture supernatants and were analyzed for type 1 interferon gene expression with a targeted array. Symptoms and exacerbations were assessed in participants over 12 months. Results: A total of 436 genes were differently expressed in neutrophils from children with versus without aeroallergen sensitization at baseline, with significant downregulation of type 1 interferons. These type 1 interferons were significantly upregulated in sensitized children after poly(I:C) stimulation. Confirmatory experiments demonstrated similar upregulation of type 1 interferons in IL-4–treated neutrophils stimulated with poly(I:C). Poly(I:C)-treated neutrophil supernatants from children with aeroallergen sensitization also induced a type 1 interferon response in epithelial cells. Children with aeroallergen sensitization also had higher symptom scores during exacerbations, and these symptom differences persisted for 3 days after prednisolone treatment. Conclusions: Type 1 interferon responses are dysregulated in preschool children with aeroallergen sensitization, which is in turn associated with exacerbation severity. Given the importance of type 1 interferon signaling in viral resolution, additional studies of neutrophil type 1 interferon responses are needed in this population.

OBJECTIVES:. To develop and validate machine learning (ML) models to predict high-flow nasal cannula (HFNC) failure in COVID-19, compare their performance to the respiratory rate-oxygenation (ROX) index, and evaluate model accuracy by self-reported race. DESIGN:. Retrospective cohort study. SETTING:. Four Emory University Hospitals in Atlanta, GA. PATIENTS:. Adult patients hospitalized with COVID-19 between March 2020 and April 2022 who received HFNC therapy within 24 hours of ICU admission were included. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. Four types of supervised ML models were developed for predicting HFNC failure (defined as intubation or death within 7 d of HFNC initiation), using routine clinical variables from the first 24 hours of ICU admission. Models were trained on the first 60% (n = 594) of admissions and validated on the latter 40% (n = 390) of admissions to simulate prospective implementation. Among 984 patients included, 317 patients (32.2%) developed HFNC failure. eXtreme Gradient Boosting (XGB) model had the highest area under the receiver-operator characteristic curve (AUROC) for predicting HFNC failure (0.707), and was the only model with significantly better performance than the ROX index (AUROC 0.616). XGB model had significantly worse performance in Black patients compared with White patients (AUROC 0.663 vs. 0.808, p = 0.02). Racial differences in the XGB model were reduced and no longer statistically significant when restricted to patients with nonmissing arterial blood gas data, and when XGB model was developed to predict mortality (rather than the composite outcome of failure, which could be influenced by biased clinical decisions for intubation). CONCLUSIONS:. Our XGB model had better discrimination for predicting HFNC failure in COVID-19 than the ROX index, but had racial differences in accuracy of predictions. Further studies are needed to understand and mitigate potential sources of biases in clinical ML models and to improve their equitability.

Abstract Fluid overload, while common in the ICU and associated with serious sequelae, is hard to predict and may be influenced by ICU medication use. Machine learning (ML) approaches may offer advantages over traditional regression techniques to predict it. We compared the ability of traditional regression techniques and different ML-based modeling approaches to identify clinically meaningful fluid overload predictors. This was a retrospective, observational cohort study of adult patients admitted to an ICU ≥ 72 h between 10/1/2015 and 10/31/2020 with available fluid balance data. Models to predict fluid overload (a positive fluid balance ≥ 10% of the admission body weight) in the 48–72 h after ICU admission were created. Potential patient and medication fluid overload predictor variables (n = 28) were collected at either baseline or 24 h after ICU admission. The optimal traditional logistic regression model was created using backward selection. Supervised, classification-based ML models were trained and optimized, including a meta-modeling approach. Area under the receiver operating characteristic (AUROC), positive predictive value (PPV), and negative predictive value (NPV) were compared between the traditional and ML fluid prediction models. A total of 49 of the 391 (12.5%) patients developed fluid overload. Among the ML models, the XGBoost model had the highest performance (AUROC 0.78, PPV 0.27, NPV 0.94) for fluid overload prediction. The XGBoost model performed similarly to the final traditional logistic regression model (AUROC 0.70; PPV 0.20, NPV 0.94). Feature importance analysis revealed severity of illness scores and medication-related data were the most important predictors of fluid overload. In the context of our study, ML and traditional models appear to perform similarly to predict fluid overload in the ICU. Baseline severity of illness and ICU medication regimen complexity are important predictors of fluid overload.

Abstract Introduction Accurate identification of venous thromboembolism (VTE) is critical to develop replicable epidemiological studies and rigorous predictions models. Traditionally, VTE studies have relied on international classification of diseases (ICD) codes which are inaccurate – leading to misclassification bias. Here, we developed ClotCatcher, a novel deep learning model that uses natural language processing to detect VTE from radiology reports. Methods Radiology reports to detect VTE were obtained from patients admitted to Emory University Hospital (EUH) and Grady Memorial Hospital (GMH). Data augmentation was performed using the Google PEGASUS paraphraser. This data was then used to fine-tune ClotCatcher, a novel deep learning model. ClotCatcher was validated on both the EUH dataset alone and GMH dataset alone. Results The dataset contained 1358 studies from EUH and 915 studies from GMH (n = 2273). The dataset contained 1506 ultrasound studies with 528 (35.1%) studies positive for VTE, and 767 CT studies with 91 (11.9%) positive for VTE. When validated on the EUH dataset, ClotCatcher performed best (AUC = 0.980) when trained on both EUH and GMH dataset without paraphrasing. When validated on the GMH dataset, ClotCatcher performed best (AUC = 0.995) when trained on both EUH and GMH dataset with paraphrasing. Conclusion ClotCatcher, a novel deep learning model with data augmentation rapidly and accurately adjudicated the presence of VTE from radiology reports. Applying ClotCatcher to large databases would allow for rapid and accurate adjudication of incident VTE. This would reduce misclassification bias and form the foundation for future studies to estimate individual risk for patient to develop incident VTE.

Abstract Unsupervised clustering of intensive care unit (ICU) medications may identify unique medication clusters (i.e., pharmacophenotypes) in critically ill adults. We performed an unsupervised analysis with Restricted Boltzmann Machine of 991 medications profiles of patients managed in the ICU to explore pharmacophenotypes that correlated with ICU complications (e.g., mechanical ventilation) and patient-centered outcomes (e.g., length of stay, mortality). Six unique pharmacophenotypes were observed, with unique medication profiles and clinically relevant differences in ICU complications and patient-centered outcomes. While pharmacophenotypes 2 and 4 had no statistically significant difference in ICU length of stay, duration of mechanical ventilation, or duration of vasopressor use, their mortality differed significantly (9.0% vs. 21.9%, p

Abstract Little is known about electrocardiogram (ECG) markers of Parkinson’s disease (PD) during the prodromal stage. The aim of the study was to build a generalizable ECG-based fully automatic artificial intelligence (AI) model to predict PD risk during the prodromal stage, up to 5 years before disease diagnosis. This case–control study included samples from Loyola University Chicago (LUC) and University of Tennessee-Methodist Le Bonheur Healthcare (MLH). Cases and controls were matched according to specific characteristics (date, age, sex and race). Clinical data were available from May, 2014 onward at LUC and from January, 2015 onward at MLH, while the ECG data were available as early as 1990 in both institutes. PD was denoted by at least two primary diagnostic codes (ICD9 332.0; ICD10 G20) at least 30 days apart. PD incidence date was defined as the earliest of first PD diagnostic code or PD-related medication prescription. ECGs obtained at least 6 months before PD incidence date were modeled to predict a subsequent diagnosis of PD within three time windows: 6 months–1 year, 6 months–3 years, and 6 months–5 years. We applied a novel deep neural network using standard 10-s 12-lead ECGs to predict PD risk at the prodromal phase. This model was compared to multiple feature engineering-based models. Subgroup analyses for sex, race and age were also performed. Our primary prediction model was a one-dimensional convolutional neural network (1D-CNN) that was built using 131 cases and 1058 controls from MLH, and externally validated on 29 cases and 165 controls from LUC. The model was trained on 90% of the MLH data, internally validated on the remaining 10% and externally validated on LUC data. The best performing model resulted in an external validation AUC of 0.67 when predicting future PD at any time between 6 months and 5 years after the ECG. Accuracy increased when restricted to ECGs obtained within 6 months to 3 years before PD diagnosis (AUC 0.69) and was highest when predicting future PD within 6 months to 1 year (AUC 0.74). The 1D-CNN model based on raw ECG data outperformed multiple models built using more standard ECG feature engineering approaches. These results demonstrate that a predictive model developed in one cohort using only raw 10-s ECGs can effectively classify individuals with prodromal PD in an independent cohort, particularly closer to disease diagnosis. Standard ECGs may help identify individuals with prodromal PD for cost-effective population-level early detection and inclusion in disease-modifying therapeutic trials.

Background: Blood transfusions, crucial in managing anemia and coagulopathy in intensive care unit (ICU) settings, require accurate prediction for effective resource allocation and patient risk assessment. However, existing clinical decision support systems have primarily targeted a particular patient demographic with unique medical conditions and focused on a single type of blood transfusion. This study aims to develop an advanced machine learning-based model to predict the probability of transfusion necessity over the next 24 h for a diverse range of non-traumatic ICU patients. Methods: We conducted a retrospective cohort study on 72,072 non-traumatic adult ICU patients admitted to a high-volume US metropolitan academic hospital between 2016 and 2020. We developed a meta-learner and various machine learning models to serve as predictors, training them annually with 4-year data and evaluating on the fifth, unseen year, iteratively over 5 years. Results: The experimental results revealed that the meta-model surpasses the other models in different development scenarios. It achieved notable performance metrics, including an area under the receiver operating characteristic curve of 0.97, an accuracy rate of 0.93, and an F1 score of 0.89 in the best scenario. Conclusion: This study pioneers the use of machine learning models for predicting the likelihood of blood transfusion receipt in a diverse cohort of critically ill patients. The findings of this evaluation confirm that our model not only effectively predicts transfusion reception but also identifies key biomarkers for making transfusion decisions.

Summary: Background: Multiple organ dysfunction syndrome (MODS) disproportionately drives morbidity and mortality among critically ill patients. However, we lack a comprehensive understanding of its pathobiology. Identification of genes associated with a persistent MODS trajectory may shed light on underlying biology and allow for accurate prediction of those at-risk. Methods: Secondary analyses of publicly available gene-expression datasets. Supervised machine learning (ML) was used to identify a parsimonious set of genes associated with a persistent MODS trajectory in a training set of pediatric septic shock. We optimized model parameters and tested risk-prediction capabilities in independent validation and test datasets, respectively. We compared model performance relative to an established gene-set predictive of sepsis mortality. Findings: Patients with a persistent MODS trajectory had 568 differentially expressed genes and characterized by a dysregulated innate immune response. Supervised ML identified 111 genes associated with the outcome of interest on repeated cross-validation, with an AUROC of 0.87 (95% CI: 0.85–0.88) in the training set. The optimized model, limited to 20 genes, achieved AUROCs ranging from 0.74 to 0.79 in the validation and test sets to predict those with persistent MODS, regardless of host age and cause of organ dysfunction. Our classifier demonstrated reproducibility in identifying those with persistent MODS in comparison with a published gene-set predictive of sepsis mortality. Interpretation: We demonstrate the utility of supervised ML driven identification of the genes associated with persistent MODS. Pending validation in enriched cohorts with a high burden of organ dysfunction, such an approach may inform targeted delivery of interventions among at-risk patients. Funding: H.R.W.′s NIH R35GM126943 award supported the work detailed in this manuscript. Upon his death, the award was transferred to M.N.A. M.R.A., N.S.P, and R.K were supported by NIH R21GM151703. R.K. was supported by R01GM139967.

Abstract Background Identifying patterns within ICU medication regimens may help artificial intelligence algorithms to better predict patient outcomes; however, machine learning methods incorporating medications require further development, including standardized terminology. The Common Data Model for Intensive Care Unit (ICU) Medications (CDM-ICURx) may provide important infrastructure to clinicians and researchers to support artificial intelligence analysis of medication-related outcomes and healthcare costs. Using an unsupervised cluster analysis approach in combination with this common data model, the objective of this evaluation was to identify novel patterns of medication clusters (termed ‘pharmacophenotypes’) correlated with ICU adverse events (e.g., fluid overload) and patient-centered outcomes (e.g., mortality). Methods This was a retrospective, observational cohort study of 991 critically ill adults. To identify pharmacophenotypes, unsupervised machine learning analysis with automated feature learning using restricted Boltzmann machine and hierarchical clustering was performed on the medication administration records of each patient during the first 24 h of their ICU stay. Hierarchical agglomerative clustering was applied to identify unique patient clusters. Distributions of medications across pharmacophenotypes were described, and differences among patient clusters were compared using signed rank tests and Fisher's exact tests, as appropriate. Results A total of 30,550 medication orders for the 991 patients were analyzed; five unique patient clusters and six unique pharmacophenotypes were identified. For patient outcomes, compared to patients in Clusters 1 and 3, patients in Cluster 5 had a significantly shorter duration of mechanical ventilation and ICU length of stay (p

Abstract Children with life-threatening asthma exacerbations who are admitted to a pediatric intensive care unit (PICU) are a heterogeneous group with poorly studied inflammatory features. We hypothesized that distinct clusters of children with asthma in a PICU would be identified based on differences in plasma cytokine levels and that these clusters would have differing underlying inflammation and asthma outcomes within 1 year. Plasma cytokines and differential gene expression were measured in neutrophils isolated from children admitted to a PICU for asthma. Participants were clustered by differential plasma cytokine abundance. Gene expression differences were compared by cluster and pathway over-representation analysis was performed. We identified two clusters in 69 children with no clinical differences. Cluster 1 (n = 41) had higher cytokines compared to Cluster 2 (n = 28). Cluster 2 had a hazard ratio of 2.71 (95% CI 1.11–6.64) compared to Cluster 1 for time to subsequent exacerbation. Gene expression pathways that differed by cluster included interleukin-10 signaling; nucleotide-binding domain, leucine rich repeat containing receptor (NLR signaling); and toll-like receptor (TLR) signaling. These observations suggest that a subset of children may have a unique pattern of inflammation during PICU hospitalization that might require alternative treatment approaches.

Abstract Clinicians frequently observe hemodynamic changes preceding elevated intracranial pressure events. We employed a machine learning approach to identify novel and differentially expressed features associated with elevated intracranial pressure events in children with severe brain injuries. Statistical features from physiologic data streams were derived from non-overlapping 30-min analysis windows prior to 21 elevated intracranial pressure events; 200 records without elevated intracranial pressure events were used as controls. Ten Monte Carlo simulations with training/testing splits provided performance benchmarks for 4 machine learning approaches. XGBoost yielded the best performing predictive models. Shapley Additive Explanations analyses demonstrated that a majority of the top 20 contributing features consistently derived from blood pressure data streams up to 240 min prior to elevated intracranial events. The best performing prediction model was using the 30–60 min analysis window; for this model, the area under the receiver operating characteristic window using XGBoost was 0.82 (95% CI 0.81–0.83); the area under the precision-recall curve was 0.24 (95% CI 0.23–0.25), above the expected baseline of 0.1. We conclude that physiomarkers discernable by machine learning are concentrated within blood pressure and intracranial pressure data up to 4 h prior to elevated intracranial pressure events.

Abstract The host immune response to a viral immune stimulus has not been examined in children during a life-threatening asthma attack. We determined whether we could identify clusters of children with critical asthma by functional immunophenotyping using an intracellular viral analog stimulus. We performed a single-center, prospective, observational cohort study of 43 children ages 6–17 years admitted to a pediatric intensive care unit for an asthma attack between July 2019 to February 2021. Neutrophils were isolated from children, stimulated overnight with LyoVec poly(I:C), and mRNA was analyzed using a targeted Nanostring immunology array. Network analysis of the differentially expressed transcripts for the paired LyoVec poly(I:C) samples was performed. We identified two clusters by functional immunophenotyping that differed by the Asthma Control Test score. Cluster 1 (n = 23) had a higher proportion of children with uncontrolled asthma in the four weeks prior to PICU admission compared with cluster 2 (n = 20). Pathways up-regulated in cluster 1 versus cluster 2 included chemokine receptor/chemokines, interleukin-10 (IL-10), IL-4, and IL-13 signaling. Larger validation studies and clinical phenotyping of children with critical asthma are needed to determine the predictive utility of these clusters in a larger clinical setting.

Background: Asthma exacerbations are highly prevalent in children, but only a few studies have examined the biologic mechanisms underlying exacerbations in this population. Objective: High-resolution metabolomics analyses were performed to understand the differences in metabolites in children with exacerbating asthma who were hospitalized in a pediatric intensive care unit for status asthmaticus. We hypothesized that compared with a similar population of stable outpatients with asthma, children with exacerbating asthma would have differing metabolite abundance patterns with distinct clustering profiles. Methods: A total of 98 children aged 6 through 17 years with exacerbating asthma (n = 69) and stable asthma (n = 29) underwent clinical characterization procedures and submitted plasma samples for metabolomic analyses. High-confidence metabolites were retained and utilized for pathway enrichment analyses to identify the most relevant metabolic pathways that discriminated between groups. Results: In all, 118 and 131 high-confidence metabolites were identified in positive and negative ionization mode, respectively. A total of 103 unique metabolites differed significantly between children with exacerbating asthma and children with stable asthma. In all, 8 significantly enriched pathways that were largely associated with alterations in arginine, phenylalanine, and glycine metabolism were identified. However, other metabolites and pathways of interest were also identified. Conclusion: Metabolomic analyses identified multiple perturbed metabolites and pathways that discriminated children with exacerbating asthma who were hospitalized for status asthmaticus. These results highlight the complex biology of inflammation in children with exacerbating asthma and argue for additional studies of the metabolic determinants of asthma exacerbations in children because many of the identified metabolites of interest may be amenable to targeted interventions.

IMPORTANCE:. CD4+ T cells contribute to lung inflammation in acute respiratory distress syndrome. The CD4+ T-cell response in pediatric acute respiratory distress syndrome (PARDS) is unknown. OBJECTIVES:. To identify differentially expressed genes and networks using a novel transcriptomic reporter assay with donor CD4+ T cells exposed to the airway fluid of intubated children with mild versus severe PARDS. DESIGN:. In vitro pilot study. SETTING:. Laboratory-based study using human airway fluid samples admitted to a 36-bed university-affiliated pediatric intensive care unit. PATIENTS/SUBJECTS:. Seven children with severe PARDS, nine children with mild PARDS, and four intubated children without lung injury as controls. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. We performed bulk RNA sequencing using a transcriptomic reporter assay of CD4+ T cells exposed to airway fluid from intubated children to discover gene networks differentiating severe from mild PARDS. We found that innate immunity pathways, type I (α and β), and type II (γ) interferon response and cytokine/chemokine signaling are downregulated in CD4+ T cells exposed to airway fluid from intubated children with severe PARDS compared with those with mild PARDS. CONCLUSIONS:. We identified gene networks important to the PARDS airway immune response using bulk RNA sequencing from a novel CD4+ T-cell reporter assay that exposed CD4+ T cells to airway fluid from intubated children with severe and mild PARDS. These pathways will help drive mechanistic investigations into PARDS. Validation of our findings using this transcriptomic reporter assay strategy is needed.

BackgroundThere is no generalizable transcriptomics signature of pediatric acute respiratory distress syndrome. Our goal was to identify a whole blood differential gene expression signature for pediatric acute hypoxemic respiratory failure (AHRF) using transcriptomic microarrays within twenty-four hours of diagnosis. We used publicly available human whole-blood gene expression arrays of a Berlin-defined pediatric acute respiratory distress syndrome (GSE147902) cohort and a sepsis-triggered AHRF (GSE66099) cohort within twenty-four hours of diagnosis and compared those children with a PaO2/FiO2

OBJECTIVES:. To investigate the relationship between ICU-acquired weakness (ICUAW) signatures and sepsis-related mortality using gene expression from the blood within 24 hours of sepsis onset. DESIGN:. Observational study using differential gene expression analysis. SETTING:. Publicly available gene expression profile GSE54514, single-center medical and surgical ICU. PATIENTS:. Patients with primary bacteremia- and respiratory-triggered sepsis including 8 nonsurvivors and 13 survivors who were 18 years old and older and admitted to ICU. MEASUREMENTS AND MAIN RESULTS:. Among validated 526 ICUAW gene signatures, differential gene expression analysis controlling for age identified 38 significantly expressed genes between nonsurvivors and survivors. Functional enrichment analysis of differentially expressed ICUAW genes identified impaired cadherin binding, sarcomere formation, and energy metabolism among nonsurvivors. CONCLUSIONS:. Our findings demonstrated a biological association between sepsis-related mortality and ICUAW signatures in the early phase of sepsis. Defects in energy metabolism and muscle fiber formation were associated with sepsis-related mortality.

Abstract Hierarchal clustering of amino acid metabolites may identify a metabolic signature in children with pediatric acute hypoxemic respiratory failure. Seventy-four immunocompetent children, 41 (55.4%) with pediatric acute respiratory distress syndrome (PARDS), who were between 2 days to 18 years of age and within 72 h of intubation for acute hypoxemic respiratory failure, were enrolled. We used hierarchal clustering and partial least squares-discriminant analysis to profile the tracheal aspirate airway fluid using quantitative LC–MS/MS to explore clusters of metabolites that correlated with acute hypoxemia severity and ventilator-free days. Three clusters of children that differed by severity of hypoxemia and ventilator-free days were identified. Quantitative pathway enrichment analysis showed that cysteine and methionine metabolism, selenocompound metabolism, glycine, serine and threonine metabolism, arginine biosynthesis, and valine, leucine, and isoleucine biosynthesis were the top five enriched, impactful pathways. We identified three clusters of amino acid metabolites found in the airway fluid of intubated children important to acute hypoxemia severity that correlated with ventilator-free days

Acute Respiratory Distress Syndrome (ARDS) is a severe lung injury with high mortality, primarily characterized by bilateral pulmonary opacities on chest radiographs and hypoxemia. In this work, we trained a convolutional neural network (CNN) model that can reliably identify bilateral opacities on routine chest X-ray images of critically ill patients. We propose this model as a tool to generate predictive alerts for possible ARDS cases, enabling early diagnosis. Our team created a unique dataset of 7800 single-view chest-X-ray images labeled for the presence of bilateral or unilateral pulmonary opacities, or ‘equivocal’ images, by three blinded clinicians. We used a novel training technique that enables the CNN to explicitly predict the ‘equivocal’ class using an uncertainty-aware label smoothing loss. We achieved an Area under the Receiver Operating Characteristic Curve (AUROC) of 0.82 (95% CI: 0.80, 0.85), a precision of 0.75 (95% CI: 0.73, 0.78), and a sensitivity of 0.76 (95% CI: 0.73, 0.78) on the internal test set while achieving an (AUROC) of 0.84 (95% CI: 0.81, 0.86), a precision of 0.73 (95% CI: 0.63, 0.69), and a sensitivity of 0.73 (95% CI: 0.70, 0.75) on an external validation set. Further, our results show that this approach improves the model calibration and diagnostic odds ratio of the hypothesized alert tool, making it ideal for clinical decision support systems.

Introduction: Intimate partner violence (IPV) is defined as sexual, physical, psychological, or economic violence that occurs between current or former intimate partners. Victims of IPV may seek care for violence-related injuries in healthcare settings, which makes recognition and intervention in these facilities critical. In this study our goal was to develop an algorithm using natural language processing (NLP) to identify cases of IPV within emergency department (ED) settings. Methods: In this observational cohort study, we extracted unstructured physician and advanced practice provider, nursing, and social worker notes from hospital electronic health records (EHR). The recorded clinical notes and patient narratives were screened for a set of 23 situational terms, derived from the literature on IPV (ie, assault by spouse), along with an additional set of 49 extended situational terms, extracted from known IPV cases (ie, attack by spouse). We compared the effectiveness of the proposed model with detection of IPV-related International Classification of Diseases, 10th Revision, codes. Results: We included in the analysis a total of 1,064,735 patient encounters (405,303 patients who visited the ED of a Level I trauma center) from January 2012–August 2020. The outcome was identification of an IPV-related encounter. In this study we used information embedded in unstructured EHR data to develop a NLP algorithm that employs clinical notes to identify IPV visits to the ED. Using a set of 23 situational terms along with 49 extended situational terms, the algorithm successfully identified 7,399 IPV-related encounters representing 5,975 patients; the algorithm achieved 99.5% precision in detecting positive cases in our sample of 1,064,735 ED encounters. Conclusion: Using a set of pre-defined IPV-related terms, we successfully developed a novel natural language processing algorithm capable of identifying intimate partner violence.

Background: Atrial fibrillation (AF) is one of the most common cardiovascular problems, and its asymptomatic tendency makes AF detection challenging. Machine and deep learning methods are commonly used in AF detection. Objective: The purpose of this study was to evaluate the information provided by convolutional neural network (CNN) and random forest (RF) machine learning models for AF classification. Methods: We manually extracted 166 time–frequency domains and linear and nonlinear features to classify single-lead electrocardiograms (ECGs) as normal, AF, other, or noisy sinus rhythms. We selected a subset of 56 robust features using a genetic algorithm that was used in the RF model. In a separate study, a 1-dimensional, 12-layer CNN was designed on the raw ECG rhythms. Four features from the output layer and 128 features from the fully connected layer of CNN were explored independently for classification. The models were trained and internally validated on 8,528 ECGs and externally validated on a hidden dataset containing 3,658 ECGs. Next,we analyzed the correlation between engineered and CNN-learned features. Results: An RF classifier trained with 56-engineered features resulted in an F1 score of 0.91, 0.78, and 0.72 for normal, AF, and other rhythms, respectively. However, an ensemble of support vector machine and the CNN model resulted in an F1 score of 0.92, 0.87, and 0.80, respectively. Conclusion: We explored various features and machine learning models to identify AF rhythms using short (9–61 seconds) single-lead ECG recordings. Our results showed that the proposed CNN model abstracted distinctive features for AF classification.

Established guidelines describe minimum requirements for reporting algorithms in healthcare; it is equally important to objectify the characteristics of ideal algorithms that confer maximum potential benefits to patients, clinicians, and investigators. We propose a framework for ideal algorithms, including 6 desiderata: explainable (convey the relative importance of features in determining outputs), dynamic (capture temporal changes in physiologic signals and clinical events), precise (use high-resolution, multimodal data and aptly complex architecture), autonomous (learn with minimal supervision and execute without human input), fair (evaluate and mitigate implicit bias and social inequity), and reproducible (validated externally and prospectively and shared with academic communities). We present an ideal algorithms checklist and apply it to highly cited algorithms. Strategies and tools such as the predictive, descriptive, relevant (PDR) framework, the Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence (SPIRIT-AI) extension, sparse regression methods, and minimizing concept drift can help healthcare algorithms achieve these objectives, toward ideal algorithms in healthcare.

Summary: The SARS-CoV-2 virus has caused tremendous healthcare burden worldwide. Our focus was to develop a practical and easy-to-deploy system to predict the severe manifestation of disease in patients with COVID-19 with an aim to assist clinicians in triage and treatment decisions. Our proposed predictive algorithm is a trained artificial intelligence-based network using 8,427 COVID-19 patient records from four healthcare systems. The model provides a severity risk score along with likelihoods of various clinical outcomes, namely ventilator use and mortality. The trained model using patient age and nine laboratory markers has the prediction accuracy with an area under the curve (AUC) of 0.78, 95% CI: 0.77–0.82, and the negative predictive value NPV of 0.86, 95% CI: 0.84–0.88 for the need to use a ventilator and has an accuracy with AUC of 0.85, 95% CI: 0.84–0.86, and the NPV of 0.94, 95% CI: 0.92–0.96 for predicting in-hospital 30-day mortality.

IMPORTANCE:. Altered heart rate variability has been associated with autonomic dysfunction in a number of disease profiles, in this work we elucidate differences in the biomarker among patients with all-cause sepsis and coronavirus disease 2019. OBJECTIVES:. To measure heart rate variability metrics in critically ill coronavirus disease 2019 patients with comparison to all-cause critically ill sepsis patients. DESIGN, SETTING, AND PARTICIPANTS:. Retrospective analysis of coronavirus disease 2019 patients admitted to an ICU for at least 24 hours at any of Emory Healthcare ICUs between March 2020 and April 2020 up to 5 days of ICU stay. The comparison group was a cohort of all-cause sepsis patients prior to coronavirus disease 2019 pandemic. MAIN OUTCOMES AND MEASURES:. Continuous waveforms were captured from the patient monitor. The electrocardiogram was then analyzed for each patient over a 300 seconds observational window that was shifted by 30 seconds in each iteration from admission till discharge. A total of 23 heart rate variability metrics were extracted in each iteration. We use the Kruskal-Wallis and Steel-Dwass tests (p < 0.05) for statistical analysis and interpretations of heart rate variability multiple measures. RESULTS:. A total of 141 critically ill coronavirus disease 2019 patients met inclusion criteria, who were compared with 208 patients with all-cause sepsis. Three nonlinear markers, including the ratio of standard deviation derived from the Poincaré plot, sample entropy, and approximate entropy and four linear features, including mode of beat-to-beat interval, acceleration capacity, deceleration capacity, and the proportion of consecutive RR intervals that differ by more than 50 ms, were all statistically significant (p < 0.05) between the coronavirus disease 2019 and all-cause sepsis cohorts. The three nonlinear features and acceleration capacity, deceleration capacity, and beat-to-beat interval (mode) were statistically significant (p < 0.05) when comparing pairwise analysis among the combinations of survivors and nonsurvivors between the coronavirus disease 2019 and sepsis cohorts. Temporal analysis of the main markers showed low variability across the 5 days of analysis compared with sepsis patients. CONCLUSIONS AND RELEVANCE:. In this descriptive statistical study, heart rate variability measures were found to be statistically different across critically ill patients infected with severe acute respiratory syndrome coronavirus 2 and distinct from bacterial sepsis.

Background: Sepsis, post-liver transplantation, is a frequent challenge that impacts patient outcomes. We aimed to develop an artificial intelligence method to predict the onset of post-operative sepsis earlier.Methods: This pilot study aimed to identify “physiomarkers” in continuous minute-by-minute physiologic data streams, such as heart rate, respiratory rate, oxygen saturation (SpO2), and blood pressure, to predict the onset of sepsis. The model was derived from a cohort of 5,748 transplant and non-transplant patients across intensive care units (ICUs) over 36 months, with 92 post-liver transplant patients who developed sepsis.Results: Using an alert timestamp generated with the Third International Consensus Definition of Sepsis (Sepsis-3) definition as a reference point, we studied up to 24 h of continuous physiologic data prior to the event, totaling to 8.35 million data points. One hundred fifty-five features were generated using signal processing and statistical methods. Feature selection identified 52 highly ranked features, many of which included blood pressures. An eXtreme Gradient Boost (XGB) classifier was then trained on the ranked features by 5-fold cross validation on all patients (n = 5,748). We identified that the average sensitivity, specificity, positive predictive value (PPV), and area under the receiver-operator curve (AUC) of the model after 100 iterations was 0.94 ± 0.02, 0.9 ± 0.02, 0.89 ± 0.01, respectively, and 0.97 ± 0.01 for predicting sepsis 12 h before meeting criteria.Conclusion: The data suggest that machine learning/deep learning can be applied to continuous streaming data in the transplant ICU to monitor patients and possibly predict sepsis.

Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI*), among pediatric patients with Central Venous Lines (CVLs).Design: Retrospective cohort study.Setting: Single academic children's hospital.Patients: All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h.Measurements and Main Results: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI* during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI* by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence.Conclusion: A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.

OBJECTIVE:. Specific factors affecting generalizability of clinical prediction models are poorly understood. Our main objective was to investigate how measurement indicator variables affect external validity in clinical prediction models for predicting onset of vasopressor therapy. DESIGN:. We fit logistic regressions on retrospective cohorts to predict vasopressor onset using two classes of variables: seemingly objective clinical variables (vital signs and laboratory measurements) and more subjective variables denoting recency of measurements. SETTING:. Three cohorts from two tertiary-care academic hospitals in geographically distinct regions, spanning general inpatient and critical care settings. PATIENTS:. Each cohort consisted of adult patients (age greater than or equal to 18 yr at time of hospitalization), with lengths of stay between 6 and 600 hours, and who did not receive vasopressors in the first 6 hours of hospitalization or ICU admission. Models were developed on each of the three derivation cohorts and validated internally on the derivation cohort and externally on the other two cohorts. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. The prevalence of vasopressors was 0.9% in the general inpatient cohort and 12.4% and 11.5% in the two critical care cohorts. Models utilizing both classes of variables performed the best in-sample, with C-statistics for predicting vasopressor onset in 4 hours of 0.862 (95% CI, 0.844–0.879), 0.822 (95% CI, 0.793–0.852), and 0.889 (95% CI, 0.880–0.898). Models solely using the subjective variables denoting measurement recency had poor external validity. However, these practice-driven variables helped adjust for differences between the two hospitals and led to more generalizable models using clinical variables. CONCLUSIONS:. We developed and externally validated models for predicting the onset of vasopressors. We found that practice-specific features denoting measurement recency improved local performance and also led to more generalizable models if they are adjusted for during model development but discarded at validation. The role of practice-specific features such as measurement indicators in clinical prediction modeling should be carefully considered if the goal is to develop generalizable models.

Objectives:. To identify differentially expressed genes and networks from the airway cells within 72 hours of intubation of children with and without pediatric acute respiratory distress syndrome. To test the use of a neutrophil transcription reporter assay to identify immunogenic responses to airway fluid from children with and without pediatric acute respiratory distress syndrome. Design:. Prospective cohort study. SETTING:. Thirty-six bed academic PICU. PATIENTS:. Fifty-four immunocompetent children, 28 with pediatric acute respiratory distress syndrome, who were between 2 days to 18 years old within 72 hours of intubation for acute hypoxemic respiratory failure. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. We applied machine learning methods to a Nanostring transcriptomics on primary airway cells and a neutrophil reporter assay to discover gene networks differentiating pediatric acute respiratory distress syndrome from no pediatric acute respiratory distress syndrome. An analysis of moderate or severe pediatric acute respiratory distress syndrome versus no or mild pediatric acute respiratory distress syndrome was performed. Pathway network visualization was used to map pathways from 62 genes selected by ElasticNet associated with pediatric acute respiratory distress syndrome. The Janus kinase/signal transducer and activator of transcription pathway emerged. Support vector machine performed best for the primary airway cells and the neutrophil reporter assay using a leave-one-out cross-validation with an area under the operating curve and 95% CI of 0.75 (0.63–0.87) and 0.80 (0.70–1.0), respectively. CONCLUSIONS:. We identified gene networks important to the pediatric acute respiratory distress syndrome airway immune response using semitargeted transcriptomics from primary airway cells and a neutrophil reporter assay. These pathways will drive mechanistic investigations into pediatric acute respiratory distress syndrome. Further studies are needed to validate our findings and to test our models.

Background:. Acute respiratory failure occurs frequently in hospitalized patients and often begins outside the ICU, associated with increased length of stay, cost, and mortality. Delays in decompensation recognition are associated with worse outcomes. Objectives:. The objective of this study is to predict acute respiratory failure requiring any advanced respiratory support (including noninvasive ventilation). With the advent of the coronavirus disease pandemic, concern regarding acute respiratory failure has increased. Derivation Cohort:. All admission encounters from January 2014 to June 2017 from three hospitals in the Emory Healthcare network (82,699). Validation Cohort:. External validation cohort: all admission encounters from January 2014 to June 2017 from a fourth hospital in the Emory Healthcare network (40,143). Temporal validation cohort: all admission encounters from February to April 2020 from four hospitals in the Emory Healthcare network coronavirus disease tested (2,564) and coronavirus disease positive (389). Prediction Model:. All admission encounters had vital signs, laboratory, and demographic data extracted. Exclusion criteria included invasive mechanical ventilation started within the operating room or advanced respiratory support within the first 8 hours of admission. Encounters were discretized into hour intervals from 8 hours after admission to discharge or advanced respiratory support initiation and binary labeled for advanced respiratory support. Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment, our eXtreme Gradient Boosting-based algorithm, was compared against Modified Early Warning Score. Results:. Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment had significantly better discrimination than Modified Early Warning Score (area under the receiver operating characteristic curve 0.85 vs 0.57 [test], 0.84 vs 0.61 [external validation]). Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment maintained a positive predictive value (0.31–0.21) similar to that of Modified Early Warning Score greater than 4 (0.29–0.25) while identifying 6.62 (validation) to 9.58 (test) times more true positives. Furthermore, Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment performed more effectively in temporal validation (area under the receiver operating characteristic curve 0.86 [coronavirus disease tested], 0.93 [coronavirus disease positive]), while achieving identifying 4.25–4.51× more true positives. Conclusions:. Prediction of Acute Respiratory Failure requiring advanced respiratory support in Advance of Interventions and Treatment is more effective than Modified Early Warning Score in predicting respiratory failure requiring advanced respiratory support at external validation and in coronavirus disease 2019 patients. Silent prospective validation necessary before local deployment.

A complicated clinical course for critically ill patients admitted to the intensive care unit (ICU) usually includes multiorgan dysfunction and subsequent death. Owing to the heterogeneity, complexity, and unpredictability of the disease progression, ICU patient care is challenging. Identifying the predictors of complicated courses and subsequent mortality at the early stages of the disease and recognizing the trajectory of the disease from the vast array of longitudinal quantitative clinical data is difficult. Therefore, we attempted to perform a meta-analysis of previously published gene expression datasets to identify novel early biomarkers and train the artificial intelligence systems to recognize the disease trajectories and subsequent clinical outcomes. Using the gene expression profile of peripheral blood cells obtained within 24 h of pediatric ICU (PICU) admission and numerous clinical data from 228 septic patients from pediatric ICU, we identified 20 differentially expressed genes predictive of complicated course outcomes and developed a new machine learning model. After 5-fold cross-validation with 10 iterations, the overall mean area under the curve reached 0.82. Using a subset of the same set of genes, we further achieved an overall area under the curve of 0.72, 0.96, 0.83, and 0.82, respectively, on four independent external validation sets. This model was highly effective in identifying the clinical trajectories of the patients and mortality. Artificial intelligence systems identified eight out of twenty novel genetic markers (SDC4, CLEC5A, TCN1, MS4A3, HCAR3, OLAH, PLCB1, and NLRP1) that help predict sepsis severity or mortality. While these genes have been previously associated with sepsis mortality, in this work, we show that these genes are also implicated in complex disease courses, even among survivors. The discovery of eight novel genetic biomarkers related to the overactive innate immune system, including neutrophil function, and a new predictive machine learning method provides options to effectively recognize sepsis trajectories, modify real-time treatment options, improve prognosis, and patient survival.

We present an interpretable machine learning algorithm called 'eARDS' for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner® Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88-0.90), sensitivity of 0.77 (95% CI = 0.75-0.78), specificity 0.85 (95% CI = 085-0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81-0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO2), standard deviation of the systolic blood pressure (SBP), O2 flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18-40) (AUROC = 0.93 [0.92-0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81-0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.

Point-of-care screening tools are essential to expedite patient care and decrease reliance on slow diagnostic tools (e.g., microbial cultures) to identify pathogens and their associated antibiotic resistance. Analysis of volatile organic compounds (VOC) emitted from biological media has seen increased attention in recent years as a potential non-invasive diagnostic procedure. This work explores the use of solid phase micro-extraction (SPME) and ambient plasma ionization mass spectrometry (MS) to rapidly acquire VOC signatures of bacteria and fungi. The MS spectrum of each pathogen goes through a preprocessing and feature extraction pipeline. Various supervised and unsupervised machine learning (ML) classification algorithms are trained and evaluated on the extracted feature set. These are able to classify the type of pathogen as bacteria or fungi with high accuracy, while marked progress is also made in identifying specific strains of bacteria. This study presents a new approach for the identification of pathogens from VOC signatures collected using SPME and ambient ionization MS by training classifiers on just a few samples of data. This ambient plasma ionization and ML approach is robust, rapid, precise, and can potentially be used as a non-invasive clinical diagnostic tool for point-of-care applications.

Acute respiratory failure (ARF) is a common problem in medicine that utilizes significant healthcare resources and is associated with high morbidity and mortality. Classification of acute respiratory failure is complicated, and it is often determined by the level of mechanical support that is required, or the discrepancy between oxygen supply and uptake. These phenotypes make acute respiratory failure a continuum of syndromes, rather than one homogenous disease process. Early recognition of the risk factors for new or worsening acute respiratory failure may prevent that process from occurring. Predictive analytical methods using machine learning leverage clinical data to provide an early warning for impending acute respiratory failure or its sequelae. The aims of this review are to summarize the current literature on ARF prediction, to describe accepted procedures and common machine learning tools for predictive tasks through the lens of ARF prediction, and to demonstrate the challenges and potential solutions for ARF prediction that can improve patient outcomes.

Heart failure (HF) exacerbations, characterized by pulmonary congestion and breathlessness, require frequent hospitalizations, often resulting in poor outcomes. Current methods for tracking lung fluid and respiratory distress are unable to produce continuous, holistic measures of cardiopulmonary health. We present a multimodal sensing system that captures bioimpedance spectroscopy (BIS), multi-channel lung sounds from four contact microphones, multi-frequency impedance pneumography (IP), temperature, and kinematics to track changes in cardiopulmonary status. We first validated the system on healthy subjects (n = 10) and then conducted a feasibility study on patients (n = 14) with HF in clinical settings. Three measurements were taken throughout the course of hospitalization, and parameters relevant to lung fluid status—the ratio of the resistances at 5 kHz to those at 150 kHz (K)—and respiratory timings (e.g., respiratory rate) were extracted. We found a statistically significant increase in K (p < 0.05) from admission to discharge and observed respiratory timings in physiologically plausible ranges. The IP-derived respiratory signals and lung sounds were sensitive enough to detect abnormal respiratory patterns (Cheyne–Stokes) and inspiratory crackles from patient recordings, respectively. We demonstrated that the proposed system is suitable for detecting changes in pulmonary fluid status and capturing high-quality respiratory signals and lung sounds in a clinical setting.