An open source knowledge graph ecosystem for the life sciences.

Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoint resources and abstraction algorithms), and benchmarks (e.g., prebuilt KGs). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 different large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability.

Real-world use of nirmatrelvir-ritonavir in COVID-19 outpatients during BQ.1, BQ.1.1., and XBB.1.5 predominant omicron variants in three U.S. health systems: a retrospective cohort study.

Background: Ritonavir-boosted Nirmatrelvir (NMV-r), a protease inhibitor with in vitro activity against SARS-CoV-2, can reduce risk of progression to severe COVID-19 among high-risk individuals infected with earlier variants, but less is known about its effectiveness against omicron variants BQ.1/BQ.1.1/XBB.1.5. We sought to evaluate effectiveness of NMV-r in BQ.1/BQ.1.1/XBB.1.5 omicron variants by comparing hospitalisation rates to NMV-r treated patients during a previous omicron phase and to contemporaneous untreated patients. Methods: We conducted a retrospective observational cohort study of non-hospitalised adult patients with SARS-CoV-2 infection using real-world data from three health systems in Colorado and Utah, and compared hospitalisation rates in NMV-r-treated patients in a BA.2/BA.2.12.1/BA.4/BA.5 variant-predominant (first) phase (April 3, 2022-November 12, 2022), with a BQ.1/BQ.1.1/XBB.1.5 variant-predominant (second) phase (November 13, 2022-March 7, 2023). In the primary analysis, we used Firth logistic regression with a two-segment (phase) linear time model, and pre-specified non-inferiority bounds for the mean change between segments. In a pre-specified secondary analysis, we inferred NMV-r effectiveness in a cohort of treated and untreated patients infected during the second phase. For both analyses, the primary outcome was 28-day all-cause hospitalisation. Subgroup analyses assessed treatment effect heterogeneity. Findings: In the primary analysis, 28-day all-cause hospitalisation rates in NMV-r treated patients in the second phase (n = 12,061) were non-inferior compared to the first phase (n = 25,075) (198 [1.6%] vs. 345 [1.4%], adjusted odds ratio (aOR): 0.76 [95% CI 0.54-1.06]), with consistent results among secondary endpoints and key subgroups. Secondary cohort analyses revealed additional evidence for NMV-r effectiveness, with reduced 28-day hospitalisation rates among treated patients compared to untreated patients during a BQ.1/BQ.1.1/XBB.1.5 predominant phase (198/12,061 [1.6%] vs. 376/10,031 [3.7%], aOR 0.34 [95% CI 0.30-0.38), findings robust to additional sensitivity analyses. Interpretation: Real-world evidence from major US healthcare systems suggests ongoing NMV-r effectiveness in preventing hospitalisation during a BQ.1/BQ.1.1/XBB.1.5-predominant phase in the U.S, supporting its continued use in similar patient populations. Funding: U.S. National Institutes of Health.

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

OBJECTIVES: Identification of children with sepsis-associated multiple organ dysfunction syndrome (MODS) at risk for poor outcomes remains a challenge. We sought to the determine reproducibility of the data-driven "persistent hypoxemia, encephalopathy, and shock" (PHES) phenotype and determine its association with inflammatory and endothelial biomarkers, as well as biomarker-based pediatric risk strata. DESIGN: We retrained and validated a random forest classifier using organ dysfunction subscores in the 2012-2018 electronic health record (EHR) dataset used to derive the PHES phenotype. We used this classifier to assign phenotype membership in a test set consisting of prospectively (2003-2023) enrolled pediatric septic shock patients. We compared profiles of the PERSEVERE family of biomarkers among those with and without the PHES phenotype and determined the association with established biomarker-based mortality and MODS risk strata. SETTING: Twenty-five PICUs across the United States. PATIENTS: EHR data from 15,246 critically ill patients with sepsis-associated MODS split into derivation and validation sets and 1,270 pediatric septic shock patients in the test set of whom 615 had complete biomarker data. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The area under the receiver operator characteristic curve of the modified classifier to predict PHES phenotype membership was 0.91 (95% CI, 0.90-0.92) in the EHR validation set. In the test set, PHES phenotype membership was associated with both increased adjusted odds of complicated course (adjusted odds ratio [aOR] 4.1; 95% CI, 3.2-5.4) and 28-day mortality (aOR of 4.8; 95% CI, 3.11-7.25) after controlling for age, severity of illness, and immunocompromised status. Patients belonging to the PHES phenotype were characterized by greater degree of systemic inflammation and endothelial activation, and were more likely to be stratified as high risk based on PERSEVERE biomarkers predictive of death and persistent MODS. CONCLUSIONS: The PHES trajectory-based phenotype is reproducible, independently associated with poor clinical outcomes, and overlapped with higher risk strata based on prospectively validated biomarker approaches.

Association between monoclonal antibody therapy, vaccination, and longer-term symptom resolution after acute COVID-19.

Effective therapies for reducing post-acute sequelae of COVID-19 (PASC) symptoms are lacking. Evaluate the association between monoclonal antibody (mAb) treatment or COVID-19 vaccination with symptom recovery in COVID-19 participants. The longitudinal survey-based cohort study was conducted from April 2021 to January 2022 across a multihospital Colorado health system. Adults ≥18 years with a positive SARS-CoV-2 test were included. Primary exposures were mAb treatment and COVID-19 vaccination. The primary outcome was time to symptom resolution after SARS-CoV-2 positive test date. The secondary outcome was hospitalization within 28 days of a positive SARS-CoV-2 test. Analysis included 1612 participants, 539 mAb treated, and 486 with ≥2 vaccinations. Time to symptom resolution was similar between mAb treated versus untreated patients (adjusted hazard ratio (aHR): 0.90, 95% CI: 0.77-1.04). Time to symptom resolution was shorter for patients who received ≥2 vaccinations compared to those unvaccinated (aHR: 1.56, 95% CI: 1.31-1.88). 28-day hospitalization risk was lower for patients receiving mAb therapy (adjusted odds ratio [aOR]: 0.31, 95% CI: 0.19-0.50) and ≥2 vaccinations (aOR: 0.33, 95% CI: 0.20-0.55), compared with untreated or unvaccinated status. Analysis included 1612 participants, 539 mAb treated, and 486 with ≥2 vaccinations. Time to symptom resolution was similar between mAb treated versus untreated patients (adjusted hazard ratio (aHR): 0.90, 95% CI: 0.77-1.04). Time to symptom resolution was shorter for patients who received ≥2 vaccinations compared to those unvaccinated (aHR: 1.56, 95% CI: 1.31-1.88). 28-day hospitalization risk was lower for patients receiving mAb therapy (adjusted odds ratio [aOR]: 0.31, 95% CI: 0.19-0.50) and ≥2 vaccinations (aOR: 0.33, 95% CI: 0.20-0.55), compared with untreated or unvaccinated status. COVID-19 vaccination, but not mAb therapy, was associated with a shorter time to symptom resolution. Both were associated with lower 28-day hospitalization.

Effectiveness of subcutaneous monoclonal antibody treatment in emergency department outpatients with COVID-19.

Objectives: To evaluate whether subcutaneous neutralizing monoclonal antibody (mAb) treatment given in the emergency department (ED) setting was associated with reduced hospitalizations, mortality, and severity of disease when compared to nontreatment among mAb-eligible patients with coronavirus disease 2019 (COVID-19). Methods: This retrospective observational cohort study of ED patients utilized a propensity score-matched analysis to compare patients who received subcutaneous casirivimab and imdevimab mAb to nontreated COVID-19 control patients in November-December 2021. The primary outcome was all-cause hospitalization within 28 days, and secondary outcomes were 90-day hospitalization, 28- and 90-day mortality, and ED length of stay (LOS). Results: Of 1340 patients included in the analysis, 490 received subcutaneous casirivimab and imdevimab, and 850 did not received them. There was no difference observed for 28-day hospitalization (8.4% vs. 10.6%; adjusted odds ratio [aOR] 0.79, 95% confidence intervals [CI] 0.53-1.17) or 90-day hospitalization (11.6% vs. 12.5%; aOR 0.93, 95% CI 0.65-1.31). However, mortality at both the 28-day and 90-day timepoints was substantially lower in the treated group (28-day 0.6% vs. 3.1%; aOR 0.18, 95% CI 0.08-0.41; 90-day 0.6% vs. 3.9%; aOR 0.14, 95% CI 0.06-0.36). Among hospitalized patients, treated patients had shorter hospital LOS (5.7 vs. 11.4 days; adjusted rate ratio [aRR] 0.47, 95% CI 0.33-0.69), shorter intensive care unit LOS (3.8 vs. 10.2 days; aRR 0.22, 95% CI 0.14-0.35), and the severity of hospitalization was lower (aOR 0.45, 95% CI 0.21-0.97) compared to untreated. Conclusions: Among ED patients who presented for symptomatic COVID-19 during the Delta variant phase, ED subcutaneous casirivimab/imdevimab treatment was not associated with a decrease in hospitalizations. However, treatment was associated with lower mortality at 28 and 90 days, hospital LOS, and overall severity of illness.

Association of an In-Hospital Desirability of Outcomes Ranking Scale With Postdischarge Health-Related Quality of Life: A Secondary Analysis of the Life After Pediatric Sepsis Evaluation.

OBJECTIVES: To develop a desirability of outcome ranking (DOOR) scale for use in children with septic shock and determine its correlation with a decrease in 3-month postadmission health-related quality of life (HRQL) or death. DESIGN: Secondary analysis of the Life After Pediatric Sepsis Evaluation prospective study. SETTING: Twelve U.S. PICUs, 2013-2017. PATIENTS: Children (1 mo-18 yr) with septic shock. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We applied a 7-point pediatric critical care (PCC) DOOR scale: 7: death; 6: extracorporeal life support; 5: supported by life-sustaining therapies (continuous renal replacement therapy, vasoactive, or invasive ventilation); 4: hospitalized with or 3: without organ dysfunction; 2: discharged with or 1: without new morbidity to patients by assigning the highest applicable score on specific days post-PICU admission. We analyzed Spearman rank-order correlations (95% CIs) between proximal outcomes (PCC-DOOR scale on days 7, 14, and 21, ventilator-free days, cumulative 28-day Pediatric Logistic Organ Dysfunction-2 (PELOD-2) scores, and PICU-free days) and 3-month decrease in HRQL or death. HRQL was measured by Pediatric Quality of Life Inventory 4.0 or Functional Status II-R for patients with developmental delay. Patients who died were assigned the worst possible HRQL score. PCC-DOOR scores were applied to 385 patients, median age 6 years (interquartile range 2, 13) and 177 (46%) with a complex chronic condition(s). Three-month outcomes were available for 245 patients (64%) and 42 patients (17%) died. PCC-DOOR scale on days 7, 14, and 21 demonstrated fair correlation with the primary outcome (-0.42 [-0.52, -0.31], -0.47 [-0.56, -0.36], and -0.52 [-0.61, -0.42]), similar to the correlations for cumulative 28-day PELOD-2 scores (-0.51 [-0.59, -0.41]), ventilator-free days (0.43 [0.32, 0.53]), and PICU-free days (0.46 [0.35, 0.55]). CONCLUSIONS: The PCC-DOOR scale is a feasible, practical outcome for pediatric sepsis trials and demonstrates fair correlation with decrease in HRQL or death at 3 months.

Open source and reproducible and inexpensive infrastructure for data challenges and education.

Data sharing is necessary to maximize the actionable knowledge generated from research data. Data challenges can encourage secondary analyses of datasets. Data challenges in biomedicine often rely on advanced cloud-based computing infrastructure and expensive industry partnerships. Examples include challenges that use Google Cloud virtual machines and the Sage Bionetworks Dream Challenges platform. Such robust infrastructures can be financially prohibitive for investigators without substantial resources. Given the potential to develop scientific and clinical knowledge and the NIH emphasis on data sharing and reuse, there is a need for inexpensive and computationally lightweight methods for data sharing and hosting data challenges. To fill that gap, we developed a workflow that allows for reproducible model training, testing, and evaluation. We leveraged public GitHub repositories, open-source computational languages, and Docker technology. In addition, we conducted a data challenge using the infrastructure we developed. In this manuscript, we report on the infrastructure, workflow, and data challenge results. The infrastructure and workflow are likely to be useful for data challenges and education.

Intracranial pressure-flow relationships in traumatic brain injury patients expose gaps in the tenets of models and pressure-oriented management.

Background: The protocols and therapeutic guidance established for treating traumatic brain injuries (TBI) in neurointensive care focus on managing cerebral blood flow (CBF) and brain tissue oxygenation based on pressure signals. The decision support process relies on assumed relationships between cerebral perfusion pressure (CPP) and blood flow, pressure-flow relationships (PFRs), and shares this framework of assumptions with mathematical intracranial hemodynamic models. These foundational assumptions are difficult to verify, and their violation can impact clinical decision-making and model validity. Method: A hypothesis- and model-driven method for verifying and understanding the foundational intracranial hemodynamic PFRs is developed and applied to a novel multi-modality monitoring dataset. Results: Model analysis of joint observations of CPP and CBF validates the standard PFR when autoregulatory processes are impaired as well as unmodelable cases dominated by autoregulation. However, it also identifies a dynamical regime -or behavior pattern- where the PFR assumptions are wrong in a precise, data-inferable way due to negative CPP-CBF coordination over long timescales. This regime is of both clinical and research interest: its dynamics are modelable under modified assumptions while its causal direction and mechanistic pathway remain unclear. Conclusions: Motivated by the understanding of mathematical physiology, the validity of the standard PFR can be assessed a) directly by analyzing pressure reactivity and mean flow indices (PRx and Mx) or b) indirectly through the relationship between CBF and other clinical observables. This approach could potentially help personalize TBI care by considering intracranial pressure and CPP in relation to other data, particularly CBF. The analysis suggests a threshold using clinical indices of autoregulation jointly generalizes independently set indicators to assess CA functionality. These results support the use of increasingly data-rich environments to develop more robust hybrid physiological-machine learning models.

Recovery Trajectories in Children Requiring 3 or More Days of Invasive Ventilation.

OBJECTIVES: To characterize health-related quality of life (HRQL) and functional recovery trajectories and risk factors for prolonged impairments among critically ill children receiving greater than or equal to 3 days of invasive ventilation. DESIGN: Prospective cohort study. SETTING: Quaternary children's hospital PICU. PATIENTS: Children without a preexisting tracheostomy who received greater than or equal to 3 days of invasive ventilation, survived hospitalization, and completed greater than or equal to 1 postdischarge data collection. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We evaluated 144 children measuring HRQL using proxy-report Pediatric Quality of Life Inventory and functional status using the Functional Status Scale (FSS) reflecting preillness baseline, PICU and hospital discharge, and 1, 3, 6, and 12 months after hospital discharge. They had a median age of 5.3 years (interquartile range, 1.1-13.0 yr), 58 (40%) were female, 45 (31%) had a complex chronic condition, and 110 (76%) had normal preillness FSS scores. Respiratory failure etiologies included lung disease ( n = 49; 34%), neurologic failure ( n = 23; 16%), and septic shock ( n = 22; 15%). At 1-month postdischarge, 68 of 122 (56%) reported worsened HRQL and 35 (29%) had a new functional impairment compared with preillness baseline. This improved at 3 months to 54 (46%) and 24 (20%), respectively, and remained stable through the remaining 9 months of follow-up. We used interaction forests to evaluate relative variable importance including pairwise interactions and found that therapy consultation within 3 days of intubation was associated with better HRQL recovery in older patients and those with better preillness physical HRQL. During the postdischarge year, 76 patients (53%) had an emergency department visit or hospitalization, and 62 (43%) newly received physical, occupational, or speech therapy. CONCLUSIONS: Impairments in HRQL and functional status as well as health resource use were common among children with acute respiratory failure. Early therapy consultation was a modifiable characteristic associated with shorter duration of worsened HRQL in older patients.

International Consensus Criteria for Pediatric Sepsis and Septic Shock.

Importance: Sepsis is a leading cause of death among children worldwide. Current pediatric-specific criteria for sepsis were published in 2005 based on expert opinion. In 2016, the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) defined sepsis as life-threatening organ dysfunction caused by a dysregulated host response to infection, but it excluded children. Objective: To update and evaluate criteria for sepsis and septic shock in children. Evidence Review: The Society of Critical Care Medicine (SCCM) convened a task force of 35 pediatric experts in critical care, emergency medicine, infectious diseases, general pediatrics, nursing, public health, and neonatology from 6 continents. Using evidence from an international survey, systematic review and meta-analysis, and a new organ dysfunction score developed based on more than 3 million electronic health record encounters from 10 sites on 4 continents, a modified Delphi consensus process was employed to develop criteria. Findings: Based on survey data, most pediatric clinicians used sepsis to refer to infection with life-threatening organ dysfunction, which differed from prior pediatric sepsis criteria that used systemic inflammatory response syndrome (SIRS) criteria, which have poor predictive properties, and included the redundant term, severe sepsis. The SCCM task force recommends that sepsis in children be identified by a Phoenix Sepsis Score of at least 2 points in children with suspected infection, which indicates potentially life-threatening dysfunction of the respiratory, cardiovascular, coagulation, and/or neurological systems. Children with a Phoenix Sepsis Score of at least 2 points had in-hospital mortality of 7.1% in higher-resource settings and 28.5% in lower-resource settings, more than 8 times that of children with suspected infection not meeting these criteria. Mortality was higher in children who had organ dysfunction in at least 1 of 4-respiratory, cardiovascular, coagulation, and/or neurological-organ systems that was not the primary site of infection. Septic shock was defined as children with sepsis who had cardiovascular dysfunction, indicated by at least 1 cardiovascular point in the Phoenix Sepsis Score, which included severe hypotension for age, blood lactate exceeding 5 mmol/L, or need for vasoactive medication. Children with septic shock had an in-hospital mortality rate of 10.8% and 33.5% in higher- and lower-resource settings, respectively. Conclusions and Relevance: The Phoenix sepsis criteria for sepsis and septic shock in children were derived and validated by the international SCCM Pediatric Sepsis Definition Task Force using a large international database and survey, systematic review and meta-analysis, and modified Delphi consensus approach. A Phoenix Sepsis Score of at least 2 identified potentially life-threatening organ dysfunction in children younger than 18 years with infection, and its use has the potential to improve clinical care, epidemiological assessment, and research in pediatric sepsis and septic shock around the world.

Development and Validation of the Phoenix Criteria for Pediatric Sepsis and Septic Shock.

Importance: The Society of Critical Care Medicine Pediatric Sepsis Definition Task Force sought to develop and validate new clinical criteria for pediatric sepsis and septic shock using measures of organ dysfunction through a data-driven approach. Objective: To derive and validate novel criteria for pediatric sepsis and septic shock across differently resourced settings. Design, Setting, and Participants: Multicenter, international, retrospective cohort study in 10 health systems in the US, Colombia, Bangladesh, China, and Kenya, 3 of which were used as external validation sites. Data were collected from emergency and inpatient encounters for children (aged <18 years) from 2010 to 2019: 3 049 699 in the development (including derivation and internal validation) set and 581 317 in the external validation set. Exposure: Stacked regression models to predict mortality in children with suspected infection were derived and validated using the best-performing organ dysfunction subscores from 8 existing scores. The final model was then translated into an integer-based score used to establish binary criteria for sepsis and septic shock. Main Outcomes and Measures: The primary outcome for all analyses was in-hospital mortality. Model- and integer-based score performance measures included the area under the precision recall curve (AUPRC; primary) and area under the receiver operating characteristic curve (AUROC; secondary). For binary criteria, primary performance measures were positive predictive value and sensitivity. Results: Among the 172 984 children with suspected infection in the first 24 hours (development set; 1.2% mortality), a 4-organ-system model performed best. The integer version of that model, the Phoenix Sepsis Score, had AUPRCs of 0.23 to 0.38 (95% CI range, 0.20-0.39) and AUROCs of 0.71 to 0.92 (95% CI range, 0.70-0.92) to predict mortality in the validation sets. Using a Phoenix Sepsis Score of 2 points or higher in children with suspected infection as criteria for sepsis and sepsis plus 1 or more cardiovascular point as criteria for septic shock resulted in a higher positive predictive value and higher or similar sensitivity compared with the 2005 International Pediatric Sepsis Consensus Conference (IPSCC) criteria across differently resourced settings. Conclusions and Relevance: The novel Phoenix sepsis criteria, which were derived and validated using data from higher- and lower-resource settings, had improved performance for the diagnosis of pediatric sepsis and septic shock compared with the existing IPSCC criteria.

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

OBJECTIVE: Perform a scoping review of supervised machine learning in pediatric critical care to identify published applications, methodologies, and implementation frequency to inform best practices for the development, validation, and reporting of predictive models in pediatric critical care. DESIGN: Scoping review and expert opinion. SETTING: We queried CINAHL Plus with Full Text (EBSCO), Cochrane Library (Wiley), Embase (Elsevier), Ovid Medline, and PubMed for articles published between 2000 and 2022 related to machine learning concepts and pediatric critical illness. Articles were excluded if the majority of patients were adults or neonates, if unsupervised machine learning was the primary methodology, or if information related to the development, validation, and/or implementation of the model was not reported. Article selection and data extraction were performed using dual review in the Covidence tool, with discrepancies resolved by consensus. SUBJECTS: Articles reporting on the development, validation, or implementation of supervised machine learning models in the field of pediatric critical care medicine. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Of 5075 identified studies, 141 articles were included. Studies were primarily (57%) performed at a single site. The majority took place in the United States (70%). Most were retrospective observational cohort studies. More than three-quarters of the articles were published between 2018 and 2022. The most common algorithms included logistic regression and random forest. Predicted events were most commonly death, transfer to ICU, and sepsis. Only 14% of articles reported external validation, and only a single model was implemented at publication. Reporting of validation methods, performance assessments, and implementation varied widely. Follow-up with authors suggests that implementation remains uncommon after model publication. CONCLUSIONS: Publication of supervised machine learning models to address clinical challenges in pediatric critical care medicine has increased dramatically in the last 5 years. While these approaches have the potential to benefit children with critical illness, the literature demonstrates incomplete reporting, absence of external validation, and infrequent clinical implementation.

A methodology of phenotyping ICU patients from EHR data: High-fidelity, personalized, and interpretable phenotypes estimation.

OBJECTIVE: Computing phenotypes that provide high-fidelity, time-dependent characterizations and yield personalized interpretations is challenging, especially given the complexity of physiological and healthcare systems and clinical data quality. This paper develops a methodological pipeline to estimate unmeasured physiological parameters and produce high-fidelity, personalized phenotypes anchored to physiological mechanics from electronic health record (EHR). METHODS: A methodological phenotyping pipeline is developed that computes new phenotypes defined with unmeasurable computational biomarkers quantifying specific physiological properties in real time. Working within the inverse problem framework, this pipeline is applied to the glucose-insulin system for ICU patients using data assimilation to estimate an established mathematical physiological model with stochastic optimization. This produces physiological model parameter vectors of clinically unmeasured endocrine properties, here insulin secretion, clearance, and resistance, estimated for individual patient. These physiological parameter vectors are used as inputs to unsupervised machine learning methods to produce phenotypic labels and discrete physiological phenotypes. These phenotypes are inherently interpretable because they are based on parametric physiological descriptors. To establish potential clinical utility, the computed phenotypes are evaluated with external EHR data for consistency and reliability and with clinician face validation. RESULTS: The phenotype computation was performed on a cohort of 109 ICU patients who received no or short-acting insulin therapy, rendering continuous and discrete physiological phenotypes as specific computational biomarkers of unmeasured insulin secretion, clearance, and resistance on time windows of three days. Six, six, and five discrete phenotypes were found in the first, middle, and last three-day periods of ICU stays, respectively. Computed phenotypic labels were predictive with an average accuracy of 89%. External validation of discrete phenotypes showed coherence and consistency in clinically observable differences based on laboratory measurements and ICD 9/10 codes and clinical concordance from face validity. A particularly clinically impactful parameter, insulin secretion, had a concordance accuracy of 83%±27%. CONCLUSION: The new physiological phenotypes computed with individual patient ICU data and defined by estimates of mechanistic model parameters have high physiological fidelity, are continuous, time-specific, personalized, interpretable, and predictive. This methodology is generalizable to other clinical and physiological settings and opens the door for discovering deeper physiological information to personalize medical care.

Sustained Effect of Clinical Decision Support for Heart Failure: A Natural Experiment Using Implementation Science.

OBJECTIVES: In a randomized controlled trial, we found that applying implementation science (IS) methods and best practices in clinical decision support (CDS) design to create a locally customized, "enhanced" CDS significantly improved evidence-based prescribing of ß blockers (BB) for heart failure compared with an unmodified commercially available CDS. At trial conclusion, the enhanced CDS was expanded to all sites. The purpose of this study was to evaluate the real-world sustained effect of the enhanced CDS compared with the commercial CDS. METHODS: In this natural experiment of 28 primary care clinics, we compared clinics exposed to the commercial CDS (preperiod) to clinics exposed to the enhanced CDS (both periods). The primary effectiveness outcome was the proportion of alerts resulting in a BB prescription. Secondary outcomes included patient reach and clinician adoption (dismissals). RESULTS: There were 367 alerts for 183 unique patients and 171 unique clinicians (pre: March 2019-August 2019; post: October 2019-March 2020). The enhanced CDS increased prescribing by 26.1% compared with the commercial (95% confidence interval [CI]: 17.0-35.1%), which is consistent with the 24% increase in the previous study. The odds of adopting the enhanced CDS was 81% compared with 29% with the commercial (odds ratio: 4.17, 95% CI: 1.96-8.85). The enhanced CDS adoption and effectiveness rates were 62 and 14% in the preperiod and 92 and 10% in the postperiod. CONCLUSION: Applying IS methods with CDS best practices was associated with improved and sustained clinician adoption and effectiveness compared with a commercially available CDS tool.

Distinct clinical phenotypes in paediatric cancer patients with sepsis are associated with different outcomes-an international multicentre retrospective study.

Background: Identifying phenotypes in sepsis patients may enable precision medicine approaches. However, the generalisability of these phenotypes to specific patient populations is unclear. Given that paediatric cancer patients with sepsis have different host response and pathogen profiles and higher mortality rates when compared to non-cancer patients, we determined whether unique, reproducible, and clinically-relevant sepsis phenotypes exist in this specific patient population. Methods: We studied patients with underlying malignancies admitted with sepsis to one of 25 paediatric intensive care units (PICUs) participating in two large, multi-centre, observational cohorts from the European SCOTER study (n = 383 patients; study period between January 1, 2018 and January 1, 2020) and the U.S. Novel Data-Driven Sepsis Phenotypes in Children study (n = 1898 patients; study period between January 1, 2012 and January 1, 2018). We independently used latent class analysis (LCA) in both cohorts to identify phenotypes using demographic, clinical, and laboratory data from the first 24 h of PICU admission. We then tested the association of the phenotypes with clinical outcomes in both cohorts. Findings: LCA identified two distinct phenotypes that were comparable across both cohorts. Phenotype 1 was characterised by lower serum bicarbonate and albumin, markedly increased lactate and hepatic, renal, and coagulation abnormalities when compared to phenotype 2. Patients with phenotype 1 had a higher 90-day mortality (European cohort 29.2% versus 13.4%, U.S. cohort 27.3% versus 11.4%, p < 0.001) and received more vasopressor and renal replacement therapy than patients with phenotype 2. After adjusting for severity of organ dysfunction, haematological cancer, prior stem cell transplantation and age, phenotype 1 was associated with an adjusted OR of death at 90-day of 1.9 (1.04-3.34) in the European cohort and 1.6 (1.2-2.2) in the U.S. cohort. Interpretation: We identified two clinically-relevant sepsis phenotypes in paediatric cancer patients that are reproducible across two international, multicentre cohorts with prognostic implications. These results may guide further research regarding therapeutic approaches for these specific phenotypes. Funding: Part of this study is funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development.

Clinical decision support tools for paediatric sepsis in resource-poor settings: an international qualitative study.

OBJECTIVE: New paediatric sepsis criteria are being developed by an international task force. However, it remains unknown what type of clinical decision support (CDS) tools will be most useful for dissemination of those criteria in resource-poor settings. We sought to design effective CDS tools by identifying the paediatric sepsis-related decisional needs of multidisciplinary clinicians and health system administrators in resource-poor settings. DESIGN: Semistructured qualitative focus groups and interviews with 35 clinicians (8 nurses, 27 physicians) and 5 administrators at health systems that regularly provide care for children with sepsis, April-May 2022. SETTING: Health systems in Africa, Asia and Latin America, where sepsis has a large impact on child health and healthcare resources may be limited. PARTICIPANTS: Participants had a mean age of 45 years, a mean of 15 years of experience, and were 45% female. RESULTS: Emergent themes were related to the decisional needs of clinicians caring for children with sepsis and to the needs of health system administrators as they make decisions about which CDS tools to implement. Themes included variation across regions and institutions in infectious aetiologies of sepsis and available clinical resources, the need for CDS tools to be flexible and customisable in order for implementation to be successful, and proposed features and format of an ideal paediatric sepsis CDS tool. CONCLUSION: Findings from this study will directly contribute to the design and implementation of CDS tools to increase the uptake and impact of the new paediatric sepsis criteria in resource-poor settings.

Risk factors associated with post-acute sequelae of SARS-CoV-2: an N3C and NIH RECOVER study.

BACKGROUND: More than one-third of individuals experience post-acute sequelae of SARS-CoV-2 infection (PASC, which includes long-COVID). The objective is to identify risk factors associated with PASC/long-COVID diagnosis. METHODS: This was a retrospective case-control study including 31 health systems in the United States from the National COVID Cohort Collaborative (N3C). 8,325 individuals with PASC (defined by the presence of the International Classification of Diseases, version 10 code U09.9 or a long-COVID clinic visit) matched to 41,625 controls within the same health system and COVID index date within ± 45 days of the corresponding case's earliest COVID index date. Measurements of risk factors included demographics, comorbidities, treatment and acute characteristics related to COVID-19. Multivariable logistic regression, random forest, and XGBoost were used to determine the associations between risk factors and PASC. RESULTS: Among 8,325 individuals with PASC, the majority were > 50 years of age (56.6%), female (62.8%), and non-Hispanic White (68.6%). In logistic regression, middle-age categories (40 to 69 years; OR ranging from 2.32 to 2.58), female sex (OR 1.4, 95% CI 1.33-1.48), hospitalization associated with COVID-19 (OR 3.8, 95% CI 3.05-4.73), long (8-30 days, OR 1.69, 95% CI 1.31-2.17) or extended hospital stay (30 + days, OR 3.38, 95% CI 2.45-4.67), receipt of mechanical ventilation (OR 1.44, 95% CI 1.18-1.74), and several comorbidities including depression (OR 1.50, 95% CI 1.40-1.60), chronic lung disease (OR 1.63, 95% CI 1.53-1.74), and obesity (OR 1.23, 95% CI 1.16-1.3) were associated with increased likelihood of PASC diagnosis or care at a long-COVID clinic. Characteristics associated with a lower likelihood of PASC diagnosis or care at a long-COVID clinic included younger age (18 to 29 years), male sex, non-Hispanic Black race, and comorbidities such as substance abuse, cardiomyopathy, psychosis, and dementia. More doctors per capita in the county of residence was associated with an increased likelihood of PASC diagnosis or care at a long-COVID clinic. Our findings were consistent in sensitivity analyses using a variety of analytic techniques and approaches to select controls. CONCLUSIONS: This national study identified important risk factors for PASC diagnosis such as middle age, severe COVID-19 disease, and specific comorbidities. Further clinical and epidemiological research is needed to better understand underlying mechanisms and the potential role of vaccines and therapeutics in altering PASC course.

A methodology of phenotyping ICU patients from EHR data: high-fidelity, personalized, and interpretable phenotypes estimation.

Objective: Computing phenotypes that provide high-fidelity, time-dependent characterizations and yield personalized interpretations is challenging, especially given the complexity of physiological and healthcare systems and clinical data quality. This paper develops a methodological pipeline to estimate unmeasured physiological parameters and produce high-fidelity, personalized phenotypes anchored to physiological mechanics from electronic health record (EHR). Methods: A methodological phenotyping pipeline is developed that computes new phenotypes defined with unmeasurable computational biomarkers quantifying specific physiological properties in real time. Working within the inverse problem framework, this pipeline is applied to the glucose-insulin system for ICU patients using data assimilation to estimate an established mathematical physiological model with stochastic optimization. This produces physiological model parameter vectors of clinically unmeasured endocrine properties, here insulin secretion, clearance, and resistance, estimated for individual patient. These physiological parameter vectors are used as inputs to unsupervised machine learning methods to produce phenotypic labels and discrete physiological phenotypes. These phenotypes are inherently interpretable because they are based on parametric physiological descriptors. To establish potential clinical utility, the computed phenotypes are evaluated with external EHR data for consistency and reliability and with clinician face validation. Results: The phenotype computation was performed on a cohort of 109 ICU patients who received no or short-acting insulin therapy, rendering continuous and discrete physiological phenotypes as specific computational biomarkers of unmeasured insulin secretion, clearance, and resistance on time windows of three days. Six, six, and five discrete phenotypes were found in the first, middle, and last three-day periods of ICU stays, respectively. Computed phenotypic labels were predictive with an average accuracy of 89%. External validation of discrete phenotypes showed coherence and consistency in clinically observable differences based on laboratory measurements and ICD 9/10 codes and clinical concordance from face validity. A particularly clinically impactful parameter, insulin secretion, had a concordance accuracy of 83% ± 27%. Conclusion: The new physiological phenotypes computed with individual patient ICU data and defined by estimates of mechanistic model parameters have high physiological fidelity, are continuous, time-specific, personalized, interpretable, and predictive. This methodology is generalizable to other clinical and physiological settings and opens the door for discovering deeper physiological information to personalize medical care.

A framework for future national pediatric pandemic respiratory disease severity triage: The HHS pediatric COVID-19 data challenge.

Introduction: With persistent incidence, incomplete vaccination rates, confounding respiratory illnesses, and few therapeutic interventions available, COVID-19 continues to be a burden on the pediatric population. During a surge, it is difficult for hospitals to direct limited healthcare resources effectively. While the overwhelming majority of pediatric infections are mild, there have been life-threatening exceptions that illuminated the need to proactively identify pediatric patients at risk of severe COVID-19 and other respiratory infectious diseases. However, a nationwide capability for developing validated computational tools to identify pediatric patients at risk using real-world data does not exist. Methods: HHS ASPR BARDA sought, through the power of competition in a challenge, to create computational models to address two clinically important questions using the National COVID Cohort Collaborative: (1) Of pediatric patients who test positive for COVID-19 in an outpatient setting, who are at risk for hospitalization? (2) Of pediatric patients who test positive for COVID-19 and are hospitalized, who are at risk for needing mechanical ventilation or cardiovascular interventions? Results: This challenge was the first, multi-agency, coordinated computational challenge carried out by the federal government as a response to a public health emergency. Fifty-five computational models were evaluated across both tasks and two winners and three honorable mentions were selected. Conclusion: This challenge serves as a framework for how the government, research communities, and large data repositories can be brought together to source solutions when resources are strapped during a pandemic.