Browsing by Author "Bennett, Tellen D."

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    A machine learning-based phenotype for long COVID in children: an EHR-based study from the RECOVER program
    (Cold Spring Harbor Laboratory, 2022-12-26) Lorman, Vitaly; Razzaghi, Hanieh; Song, Xing; Morse, Keith; Utidjian, Levon; Allen, Andrea J.; Rao, Suchitra; Rogerson, Colin; Bennett, Tellen D.; Morizono, Hiroki; Eckrich, Daniel; Jhaveri, Ravi; Huang, Yungui; Ranade, Daksha; Pajor, Nathan; Lee, Grace M.; Forrest, Christopher B.; Bailey, L. Charles; Pediatrics, School of Medicine
    Background: As clinical understanding of pediatric Post-Acute Sequelae of SARS CoV-2 (PASC) develops, and hence the clinical definition evolves, it is desirable to have a method to reliably identify patients who are likely to have post-acute sequelae of SARS CoV-2 (PASC) in health systems data. Methods and findings: In this study, we developed and validated a machine learning algorithm to classify which patients have PASC (distinguishing between Multisystem Inflammatory Syndrome in Children (MIS-C) and non-MIS-C variants) from a cohort of patients with positive SARS-CoV-2 test results in pediatric health systems within the PEDSnet EHR network. Patient features included in the model were selected from conditions, procedures, performance of diagnostic testing, and medications using a tree-based scan statistic approach. We used an XGboost model, with hyperparameters selected through cross-validated grid search, and model performance was assessed using 5-fold cross-validation. Model predictions and feature importance were evaluated using Shapley Additive exPlanation (SHAP) values. Conclusions: The model provides a tool for identifying patients with PASC and an approach to characterizing PASC using diagnosis, medication, laboratory, and procedure features in health systems data. Using appropriate threshold settings, the model can be used to identify PASC patients in health systems data at higher precision for inclusion in studies or at higher recall in screening for clinical trials, especially in settings where PASC diagnosis codes are used less frequently or less reliably. Analysis of how specific features contribute to the classification process may assist in gaining a better understanding of features that are associated with PASC diagnoses.
  • Thumbnail Image
    Item
    Can Multisystem Inflammatory Syndrome in Children Be Managed in the Outpatient Setting? An EHR-Based Cohort Study From the RECOVER Program
    (Oxford University Press, 2023) Jhaveri, Ravi; Webb, Ryan; Razzaghi, Hanieh; Schuchard, Julia; Mejias, Asuncion; Bennett, Tellen D.; Jone, Pei-Ni; Thacker, Deepika; Schulert, Grant S.; Rogerson, Colin; Cogen, Jonathan D.; Bailey, L. Charles; Forrest, Christopher B.; Lee, Grace M.; Rao, Suchitra; RECOVER consortium; Pediatrics, School of Medicine
    Using electronic health record data combined with primary chart review, we identified seven children across nine participant pediatric medical centers with a diagnosis of Multisystem Inflammatory Syndrome in Children (MIS-C) managed exclusively as outpatients. These findings should raise awareness of mild presentations of MIS-C and the option of outpatient management.
  • Thumbnail Image
    Item
    Derivation, Validation, and Clinical Relevance of a Pediatric Sepsis Phenotype With Persistent Hypoxemia, Encephalopathy, and Shock
    (Wolters Kluwer, 2023) Sanchez-Pinto, L. Nelson; Bennett, Tellen D.; Stroup, Emily K.; Luo, Yuan; Atreya, Mihir; Bubeck Wardenburg, Juliane; Chong, Grace; Geva, Alon; Faustino, E. Vincent S.; Farris, Reid W.; Hall, Mark W.; Rogerson, Colin; Shah, Sareen S.; Weiss, Scott L.; Khemani, Robinder G.; Pediatrics, School of Medicine
    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.
  • Thumbnail Image
    Item
    External validation and biomarker assessment of a high-risk, data-driven pediatric sepsis phenotype characterized by persistent hypoxemia, encephalopathy, and shock
    (Research Square, 2023-08-02) Atreya, Mihir R.; Bennett, Tellen D.; Geva, Alon; Faustino, E. Vincent S.; Rogerson, Colin M.; Lutfi, Riad; Cvijanovich, Natalie Z.; Bigham, Michael T.; Nowak, Jeffrey; Schwarz, Adam J.; Baines, Torrey; Haileselassie, Bereketeab; Thomas, Neal J.; Luo, Yuan; Sanchez-Pinto, L. Nelson; Novel Data-Driven Sepsis Phenotypes in Children Study and the Genomics of Pediatric Septic Shock Investigators; Pediatrics, School of Medicine
    Objective: Identification of children with sepsis-associated multiple organ dysfunction syndrome (MODS) at risk for poor outcomes remains a challenge. Data-driven phenotyping approaches that leverage electronic health record (EHR) data hold promise given the widespread availability of EHRs. We sought to externally validate the data-driven 'persistent hypoxemia, encephalopathy, and shock' (PHES) phenotype and determine its association with inflammatory and endothelial biomarkers, as well as biomarker-based pediatric risk-strata. Design: We trained and validated a random forest classifier using organ dysfunction subscores in the EHR dataset used to derive the PHES phenotype. We used the classifier to assign phenotype membership in a test set consisting of prospectively enrolled pediatric septic shock patients. We compared biomarker profiles of those with and without the PHES phenotype and determined the association with established biomarker-based mortality and MODS risk-strata. Setting: 25 pediatric intensive care units (PICU) across the U.S. Patients: EHR data from 15,246 critically ill patients sepsis-associated MODS and 1,270 pediatric septic shock patients in the test cohort of whom 615 had biomarker data. Interventions: None. Measurements and main results: The area under the receiver operator characteristic curve (AUROC) of the new classifier to predict PHES phenotype membership was 0.91(95%CI, 0.90-0.92) in the EHR validation set. In the test set, patients with the PHES phenotype were independently associated with both increased odds of complicated course (adjusted odds ratio [aOR] of 4.1, 95%CI: 3.2-5.4) and 28-day mortality (aOR of 4.8, 95%CI: 3.11-7.25) after controlling for age, severity of illness, and immuno-compromised status. Patients belonging to the PHES phenotype were characterized by greater degree of systemic inflammation and endothelial activation, and overlapped with high risk-strata based on PERSEVERE biomarkers predictive of death and persistent MODS. Conclusions: The PHES trajectory-based phenotype is reproducible, independently associated with poor clinical outcomes, and overlap with higher risk-strata based on validated biomarker approaches.
  • Thumbnail Image
    Item
    Pediatric Organ Dysfunction Information Update Mandate (PODIUM) Contemporary Organ Dysfunction Criteria: Executive Summary
    (American Academy of Pediatrics, 2022) Bembea, Melania M.; Agus, Michael; Akcan-Arikan, Ayse; Alexander, Peta; Basu, Rajit; Bennett, Tellen D.; Bohn, Desmond; Brandão, Leonardo R.; Brown, Ann-Marie; Carcillo, Joseph A.; Checchia, Paul; Cholette, Jill; Cheifetz, Ira M.; Cornell, Timothy; Doctor, Allan; Eckerle, Michelle; Erickson, Simon; Farris, Reid W.D.; Faustino, E. Vincent S.; Fitzgerald, Julie C.; Fuhrman, Dana Y.; Giuliano, John S.; Guilliams, Kristin; Gaies, Michael; Gorga, Stephen M.; Hall, Mark; Hanson, Sheila J.; Hartman, Mary; Hassinger, Amanda B.; Irving, Sharon Y.; Jeffries, Howard; Jouvet, Philippe; Kannan, Sujatha; Karam, Oliver; Khemani, Robinder G.; Kissoon, Niranjan; Lacroix, Jacques; Laussen, Peter; Leclerc, Francis; Lee, Jan Hau; Leteurtre, Stephane; Lobner, Katie; McKiernan, Patrick J.; Menon, Kusum; Monagle, Paul; Muszynski, Jennifer A.; Odetola, Folafoluwa; Parker, Robert; Pathan, Nazima; Pierce, Richard W.; Pineda, Jose; Prince, Jose M.; Robinson, Karen A.; Rowan, Courtney M.; Ryerson, Lindsay M.; Sanchez-Pinto, L. Nelson; Schlapbach, Luregn J.; Selewski, David T.; Shekerdemian, Lara S.; Simon, Dennis; Smith, Lincoln S.; Squires, James E.; Squires, Robert H.; Sutherland, Scott M.; Ouellette, Yves; Spaeder, Michael C.; Srinivasan, Vijay; Steiner, Marie E.; Tasker, Robert C.; Thiagarajan, Ravi; Thomas, Neal; Tissieres, Pierre; Traube, Chani; Tucci, Marisa; Typpo, Katri V.; Wainwright, Mark S.; Ward, Shan L.; Watson, R. Scott; Weiss, Scott; Whitney, Jane; Willson, Doug; Wynn, James L.; Yehya, Nadir; Zimmerman, Jerry J.; Pediatrics, School of Medicine
    Prior criteria for organ dysfunction in critically ill children were based mainly on expert opinion. We convened the Pediatric Organ Dysfunction Information Update Mandate (PODIUM) expert panel to summarize data characterizing single and multiple organ dysfunction and to derive contemporary criteria for pediatric organ dysfunction. The panel was composed of 88 members representing 47 institutions and 7 countries. We conducted systematic reviews of the literature to derive evidence-based criteria for single organ dysfunction for neurologic, cardiovascular, respiratory, gastrointestinal, acute liver, renal, hematologic, coagulation, endocrine, endothelial, and immune system dysfunction. We searched PubMed and Embase from January 1992 to January 2020. Study identification was accomplished using a combination of medical subject headings terms and keywords related to concepts of pediatric organ dysfunction. Electronic searches were performed by medical librarians. Studies were eligible for inclusion if the authors reported original data collected in critically ill children; evaluated performance characteristics of scoring tools or clinical assessments for organ dysfunction; and assessed a patient-centered, clinically meaningful outcome. Data were abstracted from each included study into an electronic data extraction form. Risk of bias was assessed using the Quality in Prognosis Studies tool. Consensus was achieved for a final set of 43 criteria for pediatric organ dysfunction through iterative voting and discussion. Although the PODIUM criteria for organ dysfunction were limited by available evidence and will require validation, they provide a contemporary foundation for researchers to identify and study single and multiple organ dysfunction in critically ill children.
  • Thumbnail Image
    Item
    Semantic integration of clinical laboratory tests from electronic health records for deep phenotyping and biomarker discovery
    (Springer Nature, 2019) Zhang, Xingmin Aaron; Yates, Amy; Vasilevsky, Nicole; Gourdine, J. P.; Callahan, Tiffany J.; Carmody, Leigh C.; Danis, Daniel; Joachimiak, Marcin P.; Ravanmehr, Vida; Pfaff, Emily R.; Champion, James; Robasky, Kimberly; Xu, Hao; Fecho, Karamarie; Walton, Nephi A.; Zhu, Richard L.; Ramsdill, Justin; Mungall, Christopher J.; Köhler, Sebastian; Haendel, Melissa A.; McDonald, Clement J.; Vreeman, Daniel J.; Peden, David B.; Bennett, Tellen D.; Feinstein, James A.; Martin, Blake; Stefanski, Adrianne L.; Hunter, Lawrence E.; Chute, Christopher G.; Robinson, Peter N.; Medicine, School of Medicine
    Electronic Health Record (EHR) systems typically define laboratory test results using the Laboratory Observation Identifier Names and Codes (LOINC) and can transmit them using Fast Healthcare Interoperability Resource (FHIR) standards. LOINC has not yet been semantically integrated with computational resources for phenotype analysis. Here, we provide a method for mapping LOINC-encoded laboratory test results transmitted in FHIR standards to Human Phenotype Ontology (HPO) terms. We annotated the medical implications of 2923 commonly used laboratory tests with HPO terms. Using these annotations, our software assesses laboratory test results and converts each result into an HPO term. We validated our approach with EHR data from 15,681 patients with respiratory complaints and identified known biomarkers for asthma. Finally, we provide a freely available SMART on FHIR application that can be used within EHR systems. Our approach allows readily available laboratory tests in EHR to be reused for deep phenotyping and exploits the hierarchical structure of HPO to integrate distinct tests that have comparable medical interpretations for association studies.
  • Thumbnail Image
    Item
    The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment
    (Oxford University Press, 2021) Haendel, Melissa A.; Chute, Christopher G.; Bennett, Tellen D.; Eichmann, David A.; Guinney, Justin; Kibbe, Warren A.; Payne, Philip R. O.; Pfaff, Emily R.; Robinson, Peter N.; Saltz, Joel H.; Spratt, Heidi; Suver, Christine; Wilbanks, John; Wilcox, Adam B.; Williams, Andrew E.; Wu, Chunlei; Blacketer, Clair; Bradford, Robert L.; Cimino, James J.; Clark, Marshall; Colmenares, Evan W.; Francis, Patricia A.; Gabriel, Davera; Graves, Alexis; Hemadri, Raju; Hong, Stephanie S.; Hripscak, George; Jiao, Dazhi; Klann, Jeffrey G.; Kostka, Kristin; Lee, Adam M.; Lehmann, Harold P.; Lingrey, Lora; Miller, Robert T.; Morris, Michele; Murphy, Shawn N.; Natarajan, Karthik; Palchuk, Matvey B.; Sheikh, Usman; Solbrig, Harold; Visweswaran, Shyam; Walden, Anita; Walters, Kellie M.; Weber, Griffin M.; Zhang, Xiaohan Tanner; Zhu, Richard L.; Amor, Benjamin; Girvin, Andrew T.; Manna, Amin; Qureshi, Nabeel; Kurilla, Michael G.; Michael, Sam G.; Portilla, Lili M.; Rutter, Joni L.; Austin, Christopher P.; Gersing, Ken R.; Biomedical Engineering and Informatics, Luddy School of Informatics, Computing, and Engineering
    Objective: Coronavirus disease 2019 (COVID-19) poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers. Materials and methods: The Clinical and Translational Science Award Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics. Results: Organized in inclusive workstreams, we created legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access. Conclusions: The N3C has demonstrated that a multisite collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multiorganizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19.