ABSTRACT
OBJECTIVES: The pediatric Sequential Organ Failure Assessment (pSOFA) score summarizes severity of organ dysfunction and can be used to predict in-hospital mortality. Manual calculation of the pSOFA score is time-consuming and prone to human error. An automated method that is open-source, flexible, and scalable for calculating the pSOFA score directly from electronic health record data is desirable. DESIGN: Single-center, retrospective cohort study. SETTING: Quaternary 40-bed PICU. PATIENTS: All patients admitted to the PICU between 2015 and 2021 with ICU stay of at least 24 hours. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We used 77 records to evaluate the automated score. The automated algorithm had an overall accuracy of 97%. The algorithm calculated the respiratory component of two cases incorrectly. An expert human annotator had an initial accuracy of 75% at the patient level and 95% at the component level. An untrained human annotator with general clinical research experience had an overall accuracy of 16% and component-wise accuracy of 67%. Weighted kappa for agreement between the automated method and the expert annotator's initial score was 0.92 (95% CI, 0.88-0.95), and between the untrained human annotator and the automated score was 0.50 (95% CI, 0.36-0.61). Data from 9146 patients (in-hospital mortality 3.6%) were included to validate externally the discriminability of the automated pSOFA score. The admission-day pSOFA score had an area under the receiver operating characteristic curve of 0.79 (95% CI, 0.77-0.82). CONCLUSIONS: The developed automated algorithm calculates pSOFA score with high accuracy and is more accurate than a trained expert rater and nontrained data abstracter. pSOFA's performance for predicting in-hospital mortality was lower in our cohort than it was for the originally derived score.
Subject(s)
Algorithms , Hospital Mortality , Intensive Care Units, Pediatric , Organ Dysfunction Scores , Humans , Retrospective Studies , Male , Female , Child , Child, Preschool , Infant , Adolescent , Electronic Health Records , Multiple Organ Failure/diagnosis , Multiple Organ Failure/mortality , Reproducibility of ResultsABSTRACT
OBJECTIVES: The pediatric Sequential Organ Failure Assessment (pSOFA) score was designed to track illness severity and predict mortality in critically ill children. Most commonly, pSOFA at a point in time is used to assess a static patient condition. However, this approach has a significant drawback because it fails to consider any changes in a patients' condition during their PICU stay and, especially, their response to initial critical care treatment. We aimed to evaluate the performance of longitudinal pSOFA scores for predicting mortality. DESIGN: Single-center, retrospective cohort study. SETTING: Quaternary 40-bed PICU. PATIENTS: All patients admitted to the PICU between 2015 and 2021 with at least 24 hours of ICU stay. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We calculated daily pSOFA scores up to 30 days, or until death or discharge from the PICU, if earlier. We used the joint longitudinal and time-to-event data model for the dynamic prediction of 30-day in-hospital mortality. The dataset, which included 9146 patients with a 30-day in-hospital mortality of 2.6%, was divided randomly into training (75%) and validation (25%) subsets, and subjected to 40 repeated stratified cross-validations. We used dynamic area under the curve (AUC) to evaluate the discriminative performance of the model. Compared with the admission-day pSOFA score, AUC for predicting mortality between days 5 and 30 was improved on average by 6.4% (95% CI, 6.3-6.6%) using longitudinal pSOFA scores from the first 3 days and 9.2% (95% CI, 9.0-9.5%) using scores from the first 5 days. CONCLUSIONS: Compared with admission-day pSOFA score, longitudinal pSOFA scores improved the accuracy of mortality prediction in PICU patients at a single center. The pSOFA score has the potential to be used dynamically for the evaluation of patient conditions.
Subject(s)
Critical Illness , Hospital Mortality , Intensive Care Units, Pediatric , Organ Dysfunction Scores , Humans , Intensive Care Units, Pediatric/statistics & numerical data , Retrospective Studies , Male , Female , Child , Child, Preschool , Infant , Critical Illness/mortality , Adolescent , Longitudinal Studies , ROC Curve , PrognosisABSTRACT
OBJECTIVES: Generative language models (LMs) are being evaluated in a variety of tasks in healthcare, but pediatric critical care studies are scant. Our objective was to evaluate the utility of generative LMs in the pediatric critical care setting and to determine whether domain-adapted LMs can outperform much larger general-domain LMs in generating a differential diagnosis from the admission notes of PICU patients. DESIGN: Single-center retrospective cohort study. SETTING: Quaternary 40-bed PICU. PATIENTS: Notes from all patients admitted to the PICU between January 2012 and April 2023 were used for model development. One hundred thirty randomly selected admission notes were used for evaluation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Five experts in critical care used a 5-point Likert scale to independently evaluate the overall quality of differential diagnoses: 1) written by the clinician in the original notes, 2) generated by two general LMs (BioGPT-Large and LLaMa-65B), and 3) generated by two fine-tuned models (fine-tuned BioGPT-Large and fine-tuned LLaMa-7B). Differences among differential diagnoses were compared using mixed methods regression models. We used 1,916,538 notes from 32,454 unique patients for model development and validation. The mean quality scores of the differential diagnoses generated by the clinicians and fine-tuned LLaMa-7B, the best-performing LM, were 3.43 and 2.88, respectively (absolute difference 0.54 units [95% CI, 0.37-0.72], p < 0.001). Fine-tuned LLaMa-7B performed better than LLaMa-65B (absolute difference 0.23 unit [95% CI, 0.06-0.41], p = 0.009) and BioGPT-Large (absolute difference 0.86 unit [95% CI, 0.69-1.0], p < 0.001). The differential diagnosis generated by clinicians and fine-tuned LLaMa-7B were ranked as the highest quality in 144 (55%) and 74 cases (29%), respectively. CONCLUSIONS: A smaller LM fine-tuned using notes of PICU patients outperformed much larger models trained on general-domain data. Currently, LMs remain inferior but may serve as an adjunct to human clinicians in real-world tasks using real-world data.
Subject(s)
Artificial Intelligence , Intensive Care Units, Pediatric , Humans , Retrospective Studies , Diagnosis, Differential , Child , Male , Female , Child, Preschool , Infant , Critical Care/methods , AdolescentABSTRACT
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.
Subject(s)
Biomarkers , Hypoxia , Phenotype , Shock, Septic , Humans , Biomarkers/blood , Female , Male , Child , Child, Preschool , Infant , Shock, Septic/blood , Shock, Septic/mortality , Shock, Septic/diagnosis , Hypoxia/diagnosis , Hypoxia/blood , Intensive Care Units, Pediatric , Multiple Organ Failure/diagnosis , Multiple Organ Failure/mortality , Multiple Organ Failure/blood , Adolescent , Sepsis/diagnosis , Sepsis/complications , Sepsis/blood , Sepsis/mortality , Reproducibility of Results , Risk Assessment/methods , Prospective Studies , Sepsis-Associated Encephalopathy/blood , Sepsis-Associated Encephalopathy/diagnosis , ROC Curve , Organ Dysfunction ScoresABSTRACT
BACKGROUND: Real-time surveillance of emerging infectious diseases necessitates a dynamically evolving, computable case definition, which frequently incorporates symptom-related criteria. For symptom detection, both population health monitoring platforms and research initiatives primarily depend on structured data extracted from electronic health records. OBJECTIVE: This study sought to validate and test an artificial intelligence (AI)-based natural language processing (NLP) pipeline for detecting COVID-19 symptoms from physician notes in pediatric patients. We specifically study patients presenting to the emergency department (ED) who can be sentinel cases in an outbreak. METHODS: Subjects in this retrospective cohort study are patients who are 21 years of age and younger, who presented to a pediatric ED at a large academic children's hospital between March 1, 2020, and May 31, 2022. The ED notes for all patients were processed with an NLP pipeline tuned to detect the mention of 11 COVID-19 symptoms based on Centers for Disease Control and Prevention (CDC) criteria. For a gold standard, 3 subject matter experts labeled 226 ED notes and had strong agreement (F1-score=0.986; positive predictive value [PPV]=0.972; and sensitivity=1.0). F1-score, PPV, and sensitivity were used to compare the performance of both NLP and the International Classification of Diseases, 10th Revision (ICD-10) coding to the gold standard chart review. As a formative use case, variations in symptom patterns were measured across SARS-CoV-2 variant eras. RESULTS: There were 85,678 ED encounters during the study period, including 4% (n=3420) with patients with COVID-19. NLP was more accurate at identifying encounters with patients that had any of the COVID-19 symptoms (F1-score=0.796) than ICD-10 codes (F1-score =0.451). NLP accuracy was higher for positive symptoms (sensitivity=0.930) than ICD-10 (sensitivity=0.300). However, ICD-10 accuracy was higher for negative symptoms (specificity=0.994) than NLP (specificity=0.917). Congestion or runny nose showed the highest accuracy difference (NLP: F1-score=0.828 and ICD-10: F1-score=0.042). For encounters with patients with COVID-19, prevalence estimates of each NLP symptom differed across variant eras. Patients with COVID-19 were more likely to have each NLP symptom detected than patients without this disease. Effect sizes (odds ratios) varied across pandemic eras. CONCLUSIONS: This study establishes the value of AI-based NLP as a highly effective tool for real-time COVID-19 symptom detection in pediatric patients, outperforming traditional ICD-10 methods. It also reveals the evolving nature of symptom prevalence across different virus variants, underscoring the need for dynamic, technology-driven approaches in infectious disease surveillance.
Subject(s)
Biosurveillance , COVID-19 , Physicians , SARS-CoV-2 , United States , Humans , Child , Artificial Intelligence , Retrospective Studies , COVID-19/diagnosis , COVID-19/epidemiologyABSTRACT
OBJECTIVES: To examine whether escalating antimicrobial treatment in pediatric oncology and hematopoietic cell transplantation (HSCT) patients admitted to the PICU is supported by culture data or affects patient outcomes. DESIGN: Retrospective cross-sectional study. SETTING: Quaternary care PICU. PATIENTS: Patients younger than 18 years old who were admitted to the PICU at Boston Children's Hospital from 2012 to 2017 with a diagnosis of cancer or who had received HSCT and who had suspected sepsis at the time of PICU admission. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Of 791 PICU admissions for 544 patients that met inclusion criteria, 71 (9%) had escalation of antimicrobial therapy. Median Pediatric Logistic Organ Dysfunction (PELOD) score was higher in the escalation group (4 vs 3; p = 0.01). There were 14 admissions (20%) with a positive culture in the escalation group and 110 (15%) in the no escalation group ( p = 0.31). In the escalation group, there were only 2 (3%) cultures with organisms resistant to the initial antimicrobial regimen, compared with 28 (4%) cultures with resistant organisms in the no escalation group ( p = 1). Mortality in the escalation group was higher (17%) compared with the nonescalation group (5%; p < 0.001). The escalation group had more acute kidney injury (AKI) (25%) during treatment compared with the no escalation group (15%; p = 0.04), although this difference was not statistically significant when controlling for age, neutropenia, and PELOD-2 score (odds ratio, 1.75; 95% CI, 0.95-3.08; p = 0.06). CONCLUSIONS: Few patients who had escalation of antimicrobials proved on culture data to have an organism resistant to the initial antimicrobials, and more patients developed AKI during escalated treatment. While the escalation group likely represents a sicker population, whether some of these patients would be safer without escalation of antimicrobial therapy warrants further study.
Subject(s)
Acute Kidney Injury , Anti-Infective Agents , Hematopoietic Stem Cell Transplantation , Neoplasms , Child , Humans , Infant , Adolescent , Retrospective Studies , Cross-Sectional Studies , Neoplasms/drug therapy , Anti-Infective Agents/therapeutic use , Hematopoietic Stem Cell Transplantation/adverse effects , Intensive Care Units, PediatricABSTRACT
OBJECTIVES: "Cumulative excess oxygen exposure" (CEOE)-previously defined as the mean hourly administered Fio2 above 0.21 when the corresponding hourly Spo2 was 95% or above-was previously shown to be associated with mortality. The objective of this study was to examine the relationship among Fio2, Spo2, and mortality in an independent cohort of mechanically ventilated children. DESIGN: Retrospective cross-sectional study. SETTING: Quaternary-care PICU. PATIENTS: All patients admitted to the PICU between 2012 and 2021 and mechanically ventilated via endotracheal tube for at least 24 hours. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Among 3,354 patients, 260 (8%) died. Higher CEOE quartile was associated with increased mortality (p = 0.001). The highest CEOE quartile had an 87% increased risk of mortality (95% CI, 7-236) compared with the first CEOE quartile. The hazard ratio for extended CEOE exposure, which included mechanical ventilation data from throughout the patients' mechanical ventilation time rather than only from the first 24 hours of mechanical ventilation, was 1.03 (95% CI, 1.02-1.03). CONCLUSIONS: Potentially excess oxygen exposure in patients whose oxygen saturation was at least 95% was associated with increased mortality.
Subject(s)
Hospitalization , Respiration, Artificial , Humans , Child , Cross-Sectional Studies , Respiration, Artificial/adverse effects , Retrospective Studies , OxygenABSTRACT
OBJECTIVES: Untangling the heterogeneity of sepsis in children and identifying clinically relevant phenotypes could lead to the development of targeted therapies. Our aim was to analyze the organ dysfunction trajectories of children with sepsis-associated multiple organ dysfunction syndrome (MODS) to identify reproducible and clinically relevant sepsis phenotypes and determine if they are associated with heterogeneity of treatment effect (HTE) to common therapies. DESIGN: Multicenter observational cohort study. SETTING: Thirteen PICUs in the United States. PATIENTS: Patients admitted with suspected infections to the PICU between 2012 and 2018. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We used subgraph-augmented nonnegative matrix factorization to identify candidate trajectory-based phenotypes based on the type, severity, and progression of organ dysfunction in the first 72 hours. We analyzed the candidate phenotypes to determine reproducibility as well as prognostic, therapeutic, and biological relevance. Overall, 38,732 children had suspected infection, of which 15,246 (39.4%) had sepsis-associated MODS with an in-hospital mortality of 10.1%. We identified an organ dysfunction trajectory-based phenotype (which we termed persistent hypoxemia, encephalopathy, and shock) that was highly reproducible, had features of systemic inflammation and coagulopathy, and was independently associated with higher mortality. In a propensity score-matched analysis, patients with persistent hypoxemia, encephalopathy, and shock phenotype appeared to have HTE and benefit from adjuvant therapy with hydrocortisone and albumin. When compared with other high-risk clinical syndromes, the persistent hypoxemia, encephalopathy, and shock phenotype only overlapped with 50%-60% of patients with septic shock, moderate-to-severe pediatric acute respiratory distress syndrome, or those in the top tier of organ dysfunction burden, suggesting that it represents a nonsynonymous clinical phenotype of sepsis-associated MODS. CONCLUSIONS: We derived and validated the persistent hypoxemia, encephalopathy, and shock phenotype, which is highly reproducible, clinically relevant, and associated with HTE to common adjuvant therapies in children with sepsis.
Subject(s)
Brain Diseases , Sepsis , Shock, Septic , Child , Humans , Multiple Organ Failure/etiology , Clinical Relevance , Reproducibility of Results , Phenotype , Brain Diseases/complications , Hypoxia/etiologyABSTRACT
OBJECTIVE: Electronic Health Record (EHR) based phenotyping is a crucial yet challenging problem in the biomedical field. Though clinicians typically determine patient-level diagnoses via manual chart review, the sheer volume and heterogeneity of EHR data renders such tasks challenging, time-consuming, and prohibitively expensive, thus leading to a scarcity of clinical annotations in EHRs. Weakly supervised learning algorithms have been successfully applied to various EHR phenotyping problems, due to their ability to leverage information from large quantities of unlabeled samples to better inform predictions based on a far smaller number of patients. However, most weakly supervised methods are subject to the challenge to choose the right cutoff value to generate an optimal classifier. Furthermore, since they only utilize the most informative features (i.e., main ICD and NLP counts) they may fail for episodic phenotypes that cannot be consistently detected via ICD and NLP data. In this paper, we propose a label-efficient, weakly semi-supervised deep learning algorithm for EHR phenotyping (WSS-DL), which overcomes the limitations above. MATERIALS AND METHODS: WSS-DL classifies patient-level disease status through a series of learning stages: 1) generating silver standard labels, 2) deriving enhanced-silver-standard labels by fitting a weakly supervised deep learning model to data with silver standard labels as outcomes and high dimensional EHR features as input, and 3) obtaining the final prediction score and classifier by fitting a supervised learning model to data with a minimal number of gold standard labels as the outcome, and the enhanced-silver-standard labels and a minimal set of most informative EHR features as input. To assess the generalizability of WSS-DL across different phenotypes and medical institutions, we apply WSS-DL to classify a total of 17 diseases, including both acute and chronic conditions, using EHR data from three healthcare systems. Additionally, we determine the minimum quantity of training labels required by WSS-DL to outperform existing supervised and semi-supervised phenotyping methods. RESULTS: The proposed method, in combining the strengths of deep learning and weakly semi-supervised learning, successfully leverages the crucial phenotyping information contained in EHR features from unlabeled samples. Indeed, the deep learning model's ability to handle high-dimensional EHR features allows it to generate strong phenotype status predictions from silver standard labels. These predictions, in turn, provide highly effective features in the final logistic regression stage, leading to high phenotyping accuracy in notably small subsets of labeled data (e.g. n = 40 labeled samples). CONCLUSION: Our method's high performance in EHR datasets with very small numbers of labels indicates its potential value in aiding doctors to diagnose rare diseases as well as conditions susceptible to misdiagnosis.
Subject(s)
Electronic Health Records , Supervised Machine Learning , Algorithms , Logistic Models , PhenotypeABSTRACT
OBJECTIVE: Accurately assigning phenotype information to individual patients via computational phenotyping using Electronic Health Records (EHRs) has been seen as the first step towards enabling EHRs for precision medicine research. Chart review labels annotated by clinical experts, also known as "gold standard" labels, are essential for the development and validation of computational phenotyping algorithms. However, given the complexity of EHR systems, the process of chart review is both labor intensive and time consuming. We propose a fully automated algorithm, referred to as pGUESS, to rank EHR notes according to their relevance to a given phenotype. By identifying the most relevant notes, pGUESS can greatly improve the efficiency and accuracy of chart reviews. METHOD: pGUESS uses prior guided semantic similarity to measure the informativeness of a clinical note to a given phenotype. We first select candidate clinical concepts from a pool of comprehensive medical concepts using public knowledge sources and then derive the semantic embedding vector (SEV) for a reference article (SEVref) and each note (SEVnote). The algorithm scores the relevance of a note as the cosine similarity between SEVnote and SEVref. RESULTS: The algorithm was validated against four sets of 200 notes that were manually annotated by clinical experts to assess their informativeness to one of three disease phenotypes. pGUESS algorithm substantially outperforms existing unsupervised approaches for classifying the relevance status with respect to both accuracy and scalability across phenotypes. Averaging over the three phenotypes, the rank correlation between the algorithm ranking and gold standard label was 0.64 for pGUESS, but only 0.47 and 0.35 for the next two best performing algorithms. pGUESS is also much more computationally scalable compared to existing algorithms. CONCLUSION: pGUESS algorithm can substantially reduce the burden of chart review and holds potential in improving the efficiency and accuracy of human annotation.
Subject(s)
Algorithms , Semantics , Electronic Health Records , Humans , Natural Language Processing , Phenotype , Precision MedicineABSTRACT
OBJECTIVES: To characterize the prevalence, associations, management, and outcomes of supraventricular tachycardia (SVT) in neonates with congenital diaphragmatic hernia (CDH). DESIGN: Retrospective chart and cardiology code review within a cohort of patients with CDH was used to define a subpopulation with atrial arrhythmia. SVT mechanisms were confirmed by electrocardiogram analysis. Cox proportional hazard regression identified risk factors for SVT and association with clinical outcomes. SETTING: Medical Surgical ICU in a single, tertiary center, Boston Children's Hospital. PATIENTS: Eligible patients included neonates presenting with classic Bochdalek posterolateral CDH between 2005 and 2017, excluding newborns with Morgagni hernia or late diagnoses of CDH (>28 d). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: SVT arose in 25 of 232 neonates with CDH, (11%); 14 of 25 infants (56%) had recurrent SVT; atrioventricular node-dependent tachycardia was the most frequent mechanism (32%). The majority (71%) of SVT episodes received intervention. Nine patients (36%) received preventative antiarrhythmic medications. SVT was associated with lower Apgar score at 1 min, structural heart disease, larger defect size, extracorporeal membrane oxygenation (ECMO) support, and prostaglandin therapy for ductal patency as well as hospital stay greater than or equal to 8 weeks and use of supplemental oxygen at discharge. CONCLUSIONS: SVT can occur in neonates with CDH and frequently requires treatment. Odds of occurrence are increased with greater CDH disease severity, ECMO, and prostaglandin use. In unadjusted logistic regression analysis, SVT was associated with adverse hospital outcomes, underscoring the importance of recognition and management in this vulnerable population.
Subject(s)
Hernias, Diaphragmatic, Congenital , Tachycardia, Supraventricular , Child , Hernias, Diaphragmatic, Congenital/complications , Hernias, Diaphragmatic, Congenital/therapy , Humans , Infant , Infant, Newborn , Prevalence , Prostaglandins , Retrospective Studies , Tachycardia, Supraventricular/epidemiology , Tachycardia, Supraventricular/etiology , Tachycardia, Supraventricular/therapyABSTRACT
BACKGROUND: The purpose of this study was to describe and analyze clinical characteristics and outcomes in children with acute catastrophic brain injury (CBI). METHODS: This was a single-center, 13-year (2008-2020) retrospective cohort study of children in the pediatric and cardiac intensive care units with CBI, defined as (1) acute neurologic injury based on clinical and/or imaging findings, (2) the need for life-sustaining intensive care unit therapies, and (3) death or survival with a Glasgow Coma Scale score < 13 at discharge. Patients were excluded if they were discharged directly to home < 14 days from admission or had a chronic neurologic condition with a baseline Glasgow Coma Scale score < 13. The association between the primary outcome of death and clinical variables was analyzed by using Kaplan-Meier estimates and multivariable Cox proportional hazard models. Outcomes assessed after discharge were technology dependence, neurologic deficits, and Functional Status Score. Improved functional status was defined as a change in total Functional Status Score [Formula: see text] 2. RESULTS: Of 106 patients (58% boys, median age 3.9 years) with CBI, 86 (81%) died. Withdrawal of life-sustaining therapies was the most common cause of death (60 of 86, 70%). In our multivariable analysis, each unit increase in admission pediatric sequential organ failure assessment score was associated with 10% greater hazard of death (hazard ratio 1.10, 95% confidence interval 1.04-1.17, p < .01). After controlling for admission pediatric sequential organ failure assessment scores, compared with those of patients with traumatic brain injury, all other etiologies of CBI were associated with a greater hazard of death (p = .02; hazard ratio 3.76-10). The median survival time for the cohort was 22 days (95% confidence interval 14-37 days). Of 23 survivors to hospital discharge, 20 were still alive after a median of 2 years (interquartile range 1-3 years), 6 of 20 (30%) did not have any technology dependence, 12 of 20 (60%) regained normal levels of alertness and responsiveness, and 15 of 20 (75%) had improved functional status. CONCLUSIONS: Most children with acute CBI died within 1 month of hospitalization. Having traumatic brain injury as the etiology of CBI was associated with greater survival, whereas increased organ dysfunction score on admission was associated with a higher hazard of mortality. Of the survivors, some recovered consciousness and functional status and did not require permanent technology dependence. Larger prospective studies are needed to improve prediction of CBI among critically ill children, understand factors guiding clinician and family decisions on the continuation or withdrawal of life-sustaining treatments, and characterize the natural history and long-term outcomes among CBI survivors.
Subject(s)
Brain Injuries, Traumatic , Brain Injuries , Brain Injuries/therapy , Brain Injuries, Traumatic/therapy , Child , Child, Preschool , Cohort Studies , Female , Glasgow Coma Scale , Humans , Male , Retrospective StudiesABSTRACT
OBJECTIVES: Anticoagulation plays a key role in the management of children supported with extracorporeal membrane oxygenation. However, the ideal strategy for monitoring anticoagulation remains unclear. Our objective was to evaluate the utility of laboratory measures of anticoagulation in pediatric extracorporeal membrane oxygenation. DESIGN: Retrospective cohort study. SETTING: Quaternary care academic children's hospital. PATIENTS: Children in a noncardiac PICU cannulated to extracorporeal membrane oxygenation in 2010-2016. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Demographic data, laboratory values, and heparin doses were extracted from the enterprise data warehouse. Primary diagnoses, indications for cannulation, hemorrhagic and thrombotic complications, and survival outcomes were abstracted from the local registry used for Extracorporeal Life Support Organization reporting. Statistical models accounting for repeated measures using generalized estimating equations were constructed to evaluate correlations between heparin doses and laboratory values; among laboratory values; and between heparin dose or laboratory values and clinical outcomes. One hundred thirty-three unique patients-78 neonates and 55 older patients-were included in the study. There was no significant association between antifactor Xa level, activated partial thromboplastin time, activated clotting time, or heparin dose with hemorrhage or thrombosis (odds ratio â 1 for all associations). There was weak-to-moderate correlation between antifactor Xa, activated partial thromboplastin time, and activated clotting time in both neonates and older pediatric patients (R2 < 0.001 to 0.456). Heparin dose correlated poorly with laboratory measurements in both age groups (R2 = 0.010-0.063). CONCLUSIONS: In children supported with extracorporeal membrane oxygenation, heparin dose correlates poorly with common laboratory measures of anticoagulation, and these laboratory measures correlate poorly with each other. Neither heparin dose nor laboratory measures correlate with hemorrhage or thrombosis. Further work is needed to identify better measures of anticoagulation in order to minimize morbidity and mortality associated with extracorporeal membrane oxygenation.
Subject(s)
Extracorporeal Membrane Oxygenation , Anticoagulants/adverse effects , Child , Extracorporeal Membrane Oxygenation/adverse effects , Heparin/adverse effects , Humans , Infant, Newborn , Partial Thromboplastin Time , Retrospective StudiesABSTRACT
OBJECTIVES: Examine the association of a revised analgesia-sedation protocol with midazolam usage in the PICU. DESIGN: A single-center nonrandomized before-after study. SETTING: PICU at a quaternary pediatric hospital (Boston Children's Hospital, Boston, MA). PATIENTS: Children admitted to the PICU who were mechanically ventilated for greater than 24 hours. The preimplementation cohort included 190 eligible patients admitted between July 29, 2017, and February 28, 2018, and the postimplementation cohort included 144 patients admitted between July 29, 2019, and February 28, 2020. INTERVENTIONS: Implementation of a revised analgesia-sedation protocol. MEASUREMENTS AND MAIN RESULTS: Our primary outcome, total dose of IV midazolam administered in mechanically ventilated patients up to day 14 of ventilation, decreased by 72% (95% CI [61-80%]; p < 0.001) in the postimplementation cohort. Dexmedetomidine usage increased 230% (95% CI [145-344%]) in the postimplementation cohort. Opioid usage, our balancing metric, was not significantly different between the two cohorts. There were no significant differences in ventilator-free days, PICU length of stay, rate of unplanned extubations, failed extubations, cardiorespiratory arrest events, and 24-hour readmissions to the PICU. CONCLUSIONS: We successfully implemented an analgesia-sedation protocol that primarily uses dexmedetomidine and intermittent opioids, and it was associated with significant decrease in overall midazolam usage in mechanically ventilated patients in the PICU. The intervention was not associated with changes in opioid usage or prevalence of adverse events.
Subject(s)
Analgesia , Midazolam , Child , Humans , Hypnotics and Sedatives/adverse effects , Intensive Care Units, Pediatric , Midazolam/adverse effects , Respiration, ArtificialABSTRACT
OBJECTIVES: Design, implement, and evaluate a rounding checklist with deeply embedded, dynamic electronic health record integration. DESIGN: Before-after quality-improvement study. SETTING: Quaternary PICU in an academic, free-standing children's hospital. PATIENTS: All patients in the PICU during daily morning rounds. INTERVENTIONS: Implementation of an updated dynamic checklist (eSIMPLER) providing clinical decision support prompts with display of relevant data automatically pulled from the electronic health record. MEASUREMENTS AND MAIN RESULTS: The prior daily rounding checklist, eSIMPLE, was implemented for 49,709 patient-days (7,779 patients) between October 30, 2011, and October 7, 2018. eSIMPLER was implemented for 5,306 patient-days (971 patients) over 6 months. Checklist completion rates were similar (eSIMPLE: 95% [95% CI, 88-98%] vs eSIMPLER: 98% [95% CI, 92-100%] of patient-days; p = 0.40). eSIMPLER required less time per patient (28 ± 1 vs 47 ± 24 s; p < 0.001). Users reported improved satisfaction with eSIMPLER (p = 0.009). Several checklist-driven process measures-discordance between electronic health record orders for stress ulcer prophylaxis and user-recorded indication for stress ulcer prophylaxis, rate of venous thromboembolism prophylaxis prescribing, and recognition of reduced renal function-improved during the eSIMPLER phase. CONCLUSIONS: eSIMPLER, a dynamic, electronic health record-informed checklist, required less time to complete and improved certain care processes compared with a prior, static checklist with limited electronic health record data. By focusing on the "Five Rights" of clinical decision support, we created a well-accepted clinical decision support tool that was integrated efficiently into daily rounds. Generalizability of eSIMPLER's effectiveness and its impact on patient outcomes need to be examined.
Subject(s)
Decision Support Systems, Clinical , Teaching Rounds , Checklist , Child , Electronic Health Records , Humans , Intensive Care Units, PediatricABSTRACT
RATIONALE: Pediatric pulmonary hypertension (PH) is a heterogeneous condition with varying natural history and therapeutic response. Precise classification of PH subtypes is, therefore, crucial for individualizing care. However, gaps remain in our understanding of the spectrum of PH in children. OBJECTIVE: We seek to study the manifestations of PH in children and to assess the feasibility of applying a network-based approach to discern disease subtypes from comorbidity data recorded in longitudinal data sets. METHODS AND RESULTS: A retrospective cohort study comprising 6 943 263 children (<18 years of age) enrolled in a commercial health insurance plan in the United States, between January 2010 and May 2013. A total of 1583 (0.02%) children met the criteria for PH. We identified comorbidities significantly associated with PH compared with the general population of children without PH. A Bayesian comorbidity network was constructed to model the interdependencies of these comorbidities, and network-clustering analysis was applied to derive disease subtypes comprising subgraphs of highly connected comorbid conditions. A total of 186 comorbidities were found to be significantly associated with PH. Network analysis of comorbidity patterns captured most of the major PH subtypes with known pathological basis defined by the World Health Organization and Panama classifications. The analysis further identified many subtypes documented in only a few case studies, including rare subtypes associated with several well-described genetic syndromes. CONCLUSIONS: Application of network science to model comorbidity patterns recorded in longitudinal data sets can facilitate the discovery of disease subtypes. Our analysis relearned established subtypes, thus validating the approach, and identified rare subtypes that are difficult to discern through clinical observations, providing impetus for deeper investigation of the disease subtypes that will enrich current disease classifications.
Subject(s)
Bayes Theorem , Hypertension, Pulmonary/classification , Hypertension, Pulmonary/epidemiology , Insurance, Health/classification , Child , Child, Preschool , Classification , Cohort Studies , Comorbidity , Humans , Hypertension, Pulmonary/diagnosis , Insurance, Health/statistics & numerical data , Retrospective StudiesABSTRACT
OBJECTIVE: Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data. METHODS: SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm. RESULTS: SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn's disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors. CONCLUSION: SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping.
Subject(s)
Electronic Health Records , Phenotype , Semantics , Algorithms , HumansABSTRACT
OBJECTIVE: Despite widespread adoption of in-house call for ICU attendings, there is a paucity of research on optimal scheduling of intensivists to provide continuous on-site coverage. Overnight call duties have traditionally been added onto 7 days of continuous daytime clinical service. We designed an alternative ICU staffing model to increase continuity of attending physician care for patients while also decreasing interruptions to attendings' nonclinical weeks. DESIGN: Computer-based simulation of a 1-year schedule. SETTING: A simulated ICU divided into two daytime teams each covered by a different attending and both covered by one overnight on-call attending. SUBJECTS: Simulated patients were randomly admitted on different service days to assess continuity of care. INTERVENTIONS: A "shared service schedule" was compared to a standard "7 days on schedule." For the 7 days on schedule, an attending covered a team for 7 consecutive days and off-service attendings cross-covered each night. For the shared schedule, four attendings shared the majority of daytime and nighttime service for two teams over 2 weeks, with recovery periods built into the scheduled service time. MEASUREMENTS AND MAIN RESULTS: Continuity of care as measured by the Continuity of Attending Physician Index increased by 9% with the shared schedule. Annually, the shared service schedule was predicted to increase free weekends by 3.4 full weekends and 1.3 weekends with either Saturday or Sunday off. Full weeks without clinical obligations increased by 4 weeks. Mean time between clinical obligations increased by 5.8 days. CONCLUSIONS: A shared service schedule is predicted to improve continuity of care while increasing free weekends and continuity of uninterrupted nonclinical weeks for attendings. Computer-based simulation allows assessment of benefits and tradeoffs of the alternative schedule without disturbing existing clinical systems.
Subject(s)
Burnout, Professional/prevention & control , Continuity of Patient Care/organization & administration , Intensive Care Units/organization & administration , Medical Staff, Hospital/organization & administration , Personnel Staffing and Scheduling/organization & administration , Computer Simulation , Humans , Random AllocationABSTRACT
OBJECTIVES: To compare registry and electronic health record (EHR) data mining approaches for cohort ascertainment in patients with pediatric pulmonary hypertension (PH) in an effort to overcome some of the limitations of registry enrollment alone in identifying patients with particular disease phenotypes. STUDY DESIGN: This study was a single-center retrospective analysis of EHR and registry data at Boston Children's Hospital. The local Informatics for Integrating Biology and the Bedside (i2b2) data warehouse was queried for billing codes, prescriptions, and narrative data related to pediatric PH. Computable phenotype algorithms were developed by fitting penalized logistic regression models to a physician-annotated training set. Algorithms were applied to a candidate patient cohort, and performance was evaluated using a separate set of 136 records and 179 registry patients. We compared clinical and demographic characteristics of patients identified by computable phenotype and the registry. RESULTS: The computable phenotype had an area under the receiver operating characteristics curve of 90% (95% CI, 85%-95%), a positive predictive value of 85% (95% CI, 77%-93%), and identified 413 patients (an additional 231%) with pediatric PH who were not enrolled in the registry. Patients identified by the computable phenotype were clinically distinct from registry patients, with a greater prevalence of diagnoses related to perinatal distress and left heart disease. CONCLUSIONS: Mining of EHRs using computable phenotypes identified a large cohort of patients not recruited using a classic registry. Fusion of EHR and registry data can improve cohort ascertainment for the study of rare diseases. TRIAL REGISTRATION: ClinicalTrials.gov: NCT02249923.