1
|
Dong X, Wong R, Lyu W, Abell-Hart K, Deng J, Liu Y, Hajagos JG, Rosenthal RN, Chen C, Wang F. An integrated LSTM-HeteroRGNN model for interpretable opioid overdose risk prediction. Artif Intell Med 2023; 135:102439. [PMID: 36628797 PMCID: PMC9630306 DOI: 10.1016/j.artmed.2022.102439] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2022] [Revised: 09/27/2022] [Accepted: 10/28/2022] [Indexed: 11/06/2022]
Abstract
Opioid overdose (OD) has become a leading cause of accidental death in the United States, and overdose deaths reached a record high during the COVID-19 pandemic. Combating the opioid crisis requires targeting high-need populations by identifying individuals at risk of OD. While deep learning emerges as a powerful method for building predictive models using large scale electronic health records (EHR), it is challenged by the complex intrinsic relationships among EHR data. Further, its utility is limited by the lack of clinically meaningful explainability, which is necessary for making informed clinical or policy decisions using such models. In this paper, we present LIGHTED, an integrated deep learning model combining long short term memory (LSTM) and graph neural networks (GNN) to predict patients' OD risk. The LIGHTED model can incorporate the temporal effects of disease progression and the knowledge learned from interactions among clinical features. We evaluated the model using Cerner's Health Facts database with over 5 million patients. Our experiments demonstrated that the model outperforms traditional machine learning methods and other deep learning models. We also proposed a novel interpretability method by exploiting embeddings provided by GNNs to cluster patients and EHR features respectively, and conducted qualitative feature cluster analysis for clinical interpretations. Our study shows that LIGHTED can take advantage of longitudinal EHR data and the intrinsic graph structure of EHRs among patients to provide effective and interpretable OD risk predictions that may potentially improve clinical decision support.
Collapse
Affiliation(s)
- Xinyu Dong
- Department of Computer Science, Stony Brook University, Stony Brook, NY, United States of America
| | - Rachel Wong
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States of America
| | - Weimin Lyu
- Department of Computer Science, Stony Brook University, Stony Brook, NY, United States of America
| | - Kayley Abell-Hart
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States of America
| | - Jianyuan Deng
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States of America
| | - Yinan Liu
- Department of Computer Science, Stony Brook University, Stony Brook, NY, United States of America
| | - Janos G. Hajagos
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States of America
| | - Richard N. Rosenthal
- Department of Psychiatry, Renaissance School of Medicine at Stony Brook University, Stony Brook, NY, United States of America
| | - Chao Chen
- Department of Computer Science, Stony Brook University, Stony Brook, NY, United States of America; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States of America.
| | - Fusheng Wang
- Department of Computer Science, Stony Brook University, Stony Brook, NY, United States of America; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, United States of America.
| |
Collapse
|
2
|
Pfaff ER, Girvin AT, Gabriel DL, Kostka K, Morris M, Palchuk MB, Lehmann HP, Amor B, Bissell M, Bradwell KR, Gold S, Hong SS, Loomba J, Manna A, McMurry JA, Niehaus E, Qureshi N, Walden A, Zhang XT, Zhu RL, Moffitt RA, Haendel MA, Chute CG, Adams WG, Al-Shukri S, Anzalone A, Baghal A, Bennett TD, Bernstam EV, Bernstam EV, Bissell MM, Bush B, Campion TR, Castro V, Chang J, Chaudhari DD, Chen W, Chu S, Cimino JJ, Crandall KA, Crooks M, Davies SJD, DiPalazzo J, Dorr D, Eckrich D, Eltinge SE, Fort DG, Golovko G, Gupta S, Haendel MA, Hajagos JG, Hanauer DA, Harnett BM, Horswell R, Huang N, Johnson SG, Kahn M, Khanipov K, Kieler C, Luzuriaga KRD, Maidlow S, Martinez A, Mathew J, McClay JC, McMahan G, Melancon B, Meystre S, Miele L, Morizono H, Pablo R, Patel L, Phuong J, Popham DJ, Pulgarin C, Santos C, Sarkar IN, Sazo N, Setoguchi S, Soby S, Surampalli S, Suver C, Vangala UMR, Visweswaran S, von Oehsen J, Walters KM, Wiley L, Williams DA, Zai A. Synergies between centralized and federated approaches to data quality: a report from the national COVID cohort collaborative. J Am Med Inform Assoc 2022; 29:609-618. [PMID: 34590684 PMCID: PMC8500110 DOI: 10.1093/jamia/ocab217] [Citation(s) in RCA: 29] [Impact Index Per Article: 14.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2021] [Revised: 08/19/2021] [Accepted: 09/23/2021] [Indexed: 02/01/2023] Open
Abstract
OBJECTIVE In response to COVID-19, the informatics community united to aggregate as much clinical data as possible to characterize this new disease and reduce its impact through collaborative analytics. The National COVID Cohort Collaborative (N3C) is now the largest publicly available HIPAA limited dataset in US history with over 6.4 million patients and is a testament to a partnership of over 100 organizations. MATERIALS AND METHODS We developed a pipeline for ingesting, harmonizing, and centralizing data from 56 contributing data partners using 4 federated Common Data Models. N3C data quality (DQ) review involves both automated and manual procedures. In the process, several DQ heuristics were discovered in our centralized context, both within the pipeline and during downstream project-based analysis. Feedback to the sites led to many local and centralized DQ improvements. RESULTS Beyond well-recognized DQ findings, we discovered 15 heuristics relating to source Common Data Model conformance, demographics, COVID tests, conditions, encounters, measurements, observations, coding completeness, and fitness for use. Of 56 sites, 37 sites (66%) demonstrated issues through these heuristics. These 37 sites demonstrated improvement after receiving feedback. DISCUSSION We encountered site-to-site differences in DQ which would have been challenging to discover using federated checks alone. We have demonstrated that centralized DQ benchmarking reveals unique opportunities for DQ improvement that will support improved research analytics locally and in aggregate. CONCLUSION By combining rapid, continual assessment of DQ with a large volume of multisite data, it is possible to support more nuanced scientific questions with the scale and rigor that they require.
Collapse
Affiliation(s)
- Emily R Pfaff
- Department of Medicine, UNC Chapel Hill School of Medicine, Chapel Hill, North Carolina, USA
| | | | - Davera L Gabriel
- Section of Biomedical Informatics and Data Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Kristin Kostka
- The OHDSI Center at the Roux Institute, Northeastern University, Portland, Maine, USA
| | - Michele Morris
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | | | - Harold P Lehmann
- Department of Medicine, Johns Hopkins School of Medicine, Baltimore, Maryland, USA
| | | | | | | | - Sigfried Gold
- Section of Biomedical Informatics and Data Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Stephanie S Hong
- Section of Biomedical Informatics and Data Science, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | | | - Amin Manna
- Palantir Technologies, Denver, Colorado, USA
| | - Julie A McMurry
- Center for Health AI, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA
| | | | | | - Anita Walden
- Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, Oregon, USA
| | | | - Richard L Zhu
- Johns Hopkins University School of Medicine, Baltimore, Maryland, USA
| | - Richard A Moffitt
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York, USA
| | - Melissa A Haendel
- University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA
| | - Christopher G Chute
- Schools of Medicine, Public Health, and Nursing, Johns Hopkins University, Baltimore, Maryland, USA
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
3
|
Martin B, DeWitt PE, Russell S, Anand A, Bradwell KR, Bremer C, Gabriel D, Girvin AT, Hajagos JG, McMurry JA, Neumann AJ, Pfaff ER, Walden A, Wooldridge JT, Yoo YJ, Saltz J, Gersing KR, Chute CG, Haendel MA, Moffitt R, Bennett TD. Characteristics, Outcomes, and Severity Risk Factors Associated With SARS-CoV-2 Infection Among Children in the US National COVID Cohort Collaborative. JAMA Netw Open 2022; 5:e2143151. [PMID: 35133437 PMCID: PMC8826172 DOI: 10.1001/jamanetworkopen.2021.43151] [Citation(s) in RCA: 85] [Impact Index Per Article: 42.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/17/2021] [Accepted: 11/15/2021] [Indexed: 01/20/2023] Open
Abstract
Importance Understanding of SARS-CoV-2 infection in US children has been limited by the lack of large, multicenter studies with granular data. Objective To examine the characteristics, changes over time, outcomes, and severity risk factors of children with SARS-CoV-2 within the National COVID Cohort Collaborative (N3C). Design, Setting, and Participants A prospective cohort study of encounters with end dates before September 24, 2021, was conducted at 56 N3C facilities throughout the US. Participants included children younger than 19 years at initial SARS-CoV-2 testing. Main Outcomes and Measures Case incidence and severity over time, demographic and comorbidity severity risk factors, vital sign and laboratory trajectories, clinical outcomes, and acute COVID-19 vs multisystem inflammatory syndrome in children (MIS-C), and Delta vs pre-Delta variant differences for children with SARS-CoV-2. Results A total of 1 068 410 children were tested for SARS-CoV-2 and 167 262 test results (15.6%) were positive (82 882 [49.6%] girls; median age, 11.9 [IQR, 6.0-16.1] years). Among the 10 245 children (6.1%) who were hospitalized, 1423 (13.9%) met the criteria for severe disease: mechanical ventilation (796 [7.8%]), vasopressor-inotropic support (868 [8.5%]), extracorporeal membrane oxygenation (42 [0.4%]), or death (131 [1.3%]). Male sex (odds ratio [OR], 1.37; 95% CI, 1.21-1.56), Black/African American race (OR, 1.25; 95% CI, 1.06-1.47), obesity (OR, 1.19; 95% CI, 1.01-1.41), and several pediatric complex chronic condition (PCCC) subcategories were associated with higher severity disease. Vital signs and many laboratory test values from the day of admission were predictive of peak disease severity. Variables associated with increased odds for MIS-C vs acute COVID-19 included male sex (OR, 1.59; 95% CI, 1.33-1.90), Black/African American race (OR, 1.44; 95% CI, 1.17-1.77), younger than 12 years (OR, 1.81; 95% CI, 1.51-2.18), obesity (OR, 1.76; 95% CI, 1.40-2.22), and not having a pediatric complex chronic condition (OR, 0.72; 95% CI, 0.65-0.80). The children with MIS-C had a more inflammatory laboratory profile and severe clinical phenotype, with higher rates of invasive ventilation (117 of 707 [16.5%] vs 514 of 8241 [6.2%]; P < .001) and need for vasoactive-inotropic support (191 of 707 [27.0%] vs 426 of 8241 [5.2%]; P < .001) compared with those who had acute COVID-19. Comparing children during the Delta vs pre-Delta eras, there was no significant change in hospitalization rate (1738 [6.0%] vs 8507 [6.2%]; P = .18) and lower odds for severe disease (179 [10.3%] vs 1242 [14.6%]) (decreased by a factor of 0.67; 95% CI, 0.57-0.79; P < .001). Conclusions and Relevance In this cohort study of US children with SARS-CoV-2, there were observed differences in demographic characteristics, preexisting comorbidities, and initial vital sign and laboratory values between severity subgroups. Taken together, these results suggest that early identification of children likely to progress to severe disease could be achieved using readily available data elements from the day of admission. Further work is needed to translate this knowledge into improved outcomes.
Collapse
Affiliation(s)
- Blake Martin
- Section of Critical Care Medicine, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
| | - Peter E. DeWitt
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
| | - Seth Russell
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
| | - Adit Anand
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | | | - Carolyn Bremer
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | - Davera Gabriel
- Johns Hopkins University School of Medicine, Baltimore, Maryland
| | | | - Janos G. Hajagos
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | - Julie A. McMurry
- Translational and Integrative Sciences Center, University of Colorado, Aurora
- Center for Health AI, University of Colorado, Aurora
| | - Andrew J. Neumann
- Translational and Integrative Sciences Center, University of Colorado, Aurora
- Center for Health AI, University of Colorado, Aurora
| | - Emily R. Pfaff
- North Carolina Translational and Clinical Sciences Institute), University of North Carolina at Chapel Hill, Chapel Hill
| | - Anita Walden
- Center for Health AI, University of Colorado, Aurora
| | - Jacob T. Wooldridge
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | - Yun Jae Yoo
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | - Joel Saltz
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | - Ken R. Gersing
- National Center for Advancing Translational Sciences, National Institutes of Health, Bethesda, Maryland
| | - Christopher G. Chute
- Johns Hopkins University School of Medicine, Baltimore, Maryland
- Schools of Public Health, and Nursing, Johns Hopkins University, Baltimore, Maryland
| | | | - Richard Moffitt
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | - Tellen D. Bennett
- Section of Critical Care Medicine, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
| |
Collapse
|
4
|
Martin B, DeWitt PE, Russell S, Anand A, Bradwell KR, Bremer C, Gabriel D, Girvin AT, Hajagos JG, McMurry JA, Neumann AJ, Pfaff ER, Walden A, Wooldridge JT, Yoo YJ, Saltz J, Gersing KR, Chute CG, Haendel MA, Moffitt R, Bennett TD. Children with SARS-CoV-2 in the National COVID Cohort Collaborative (N3C). medRxiv 2021:2021.07.19.21260767. [PMID: 34341796 PMCID: PMC8328064 DOI: 10.1101/2021.07.19.21260767] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/20/2023]
Abstract
IMPORTANCE SARS-CoV-2. OBJECTIVE To determine the characteristics, changes over time, outcomes, and severity risk factors of SARS-CoV-2 affected children within the National COVID Cohort Collaborative (N3C). DESIGN Prospective cohort study of patient encounters with end dates before May 27th, 2021. SETTING 45 N3C institutions. PARTICIPANTS Children <19-years-old at initial SARS-CoV-2 testing. MAIN OUTCOMES AND MEASURES Case incidence and severity over time, demographic and comorbidity severity risk factors, vital sign and laboratory trajectories, clinical outcomes, and acute COVID-19 vs MIS-C contrasts for children infected with SARS-CoV-2. RESULTS 728,047 children in the N3C were tested for SARS-CoV-2; of these, 91,865 (12.6%) were positive. Among the 5,213 (6%) hospitalized children, 685 (13%) met criteria for severe disease: mechanical ventilation (7%), vasopressor/inotropic support (7%), ECMO (0.6%), or death/discharge to hospice (1.1%). Male gender, African American race, older age, and several pediatric complex chronic condition (PCCC) subcategories were associated with higher clinical severity (p ≤ 0.05). Vital signs (all p≤0.002) and many laboratory tests from the first day of hospitalization were predictive of peak disease severity. Children with severe (vs moderate) disease were more likely to receive antimicrobials (71% vs 32%, p<0.001) and immunomodulatory medications (53% vs 16%, p<0.001). Compared to those with acute COVID-19, children with MIS-C were more likely to be male, Black/African American, 1-to-12-years-old, and less likely to have asthma, diabetes, or a PCCC (p < 0.04). MIS-C cases demonstrated a more inflammatory laboratory profile and more severe clinical phenotype with higher rates of invasive ventilation (12% vs 6%) and need for vasoactive-inotropic support (31% vs 6%) compared to acute COVID-19 cases, respectively (p<0.03). CONCLUSIONS In the largest U.S. SARS-CoV-2-positive pediatric cohort to date, we observed differences in demographics, pre-existing comorbidities, and initial vital sign and laboratory test values between severity subgroups. Taken together, these results suggest that early identification of children likely to progress to severe disease could be achieved using readily available data elements from the day of admission. Further work is needed to translate this knowledge into improved outcomes.
Collapse
Affiliation(s)
- Blake Martin
- Section of Critical Care Medicine, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA
| | - Peter E. DeWitt
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA
| | - Seth Russell
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA
| | - Adit Anand
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | | | - Carolyn Bremer
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | - Davera Gabriel
- Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | | | - Janos G. Hajagos
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | - Julie A. McMurry
- Translational and Integrative Sciences Center, University of Colorado, Aurora, CO, USA,Center for Health AI, University of Colorado, Aurora, CO, USA
| | - Andrew J. Neumann
- Translational and Integrative Sciences Center, University of Colorado, Aurora, CO, USA,Center for Health AI, University of Colorado, Aurora, CO, USA
| | - Emily R. Pfaff
- North Carolina Translational and Clinical Sciences Institute (NC TraCS), University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
| | - Anita Walden
- Center for Health AI, University of Colorado, Aurora, CO, USA
| | - Jacob T. Wooldridge
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | - Yun Jae Yoo
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | - Joel Saltz
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | - Ken R. Gersing
- National Center for Advancing Translational Sciences, National Institutes of Health, Bethesda, MD, USA
| | - Christopher G. Chute
- Johns Hopkins University School of Medicine, Baltimore, MD, USA,Schools of Public Health, and Nursing, Johns Hopkins University, Baltimore, MD, USA
| | | | - Richard Moffitt
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | - Tellen D. Bennett
- Section of Critical Care Medicine, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA,Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA
| |
Collapse
|
5
|
Bennett TD, Moffitt RA, Hajagos JG, Amor B, Anand A, Bissell MM, Bradwell KR, Bremer C, Byrd JB, Denham A, DeWitt PE, Gabriel D, Garibaldi BT, Girvin AT, Guinney J, Hill EL, Hong SS, Jimenez H, Kavuluru R, Kostka K, Lehmann HP, Levitt E, Mallipattu SK, Manna A, McMurry JA, Morris M, Muschelli J, Neumann AJ, Palchuk MB, Pfaff ER, Qian Z, Qureshi N, Russell S, Spratt H, Walden A, Williams AE, Wooldridge JT, Yoo YJ, Zhang XT, Zhu RL, Austin CP, Saltz JH, Gersing KR, Haendel MA, Chute CG. Clinical Characterization and Prediction of Clinical Severity of SARS-CoV-2 Infection Among US Adults Using Data From the US National COVID Cohort Collaborative. JAMA Netw Open 2021; 4:e2116901. [PMID: 34255046 PMCID: PMC8278272 DOI: 10.1001/jamanetworkopen.2021.16901] [Citation(s) in RCA: 146] [Impact Index Per Article: 48.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/26/2021] [Accepted: 05/03/2021] [Indexed: 12/15/2022] Open
Abstract
Importance The National COVID Cohort Collaborative (N3C) is a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative COVID-19 cohort to date. This multicenter data set can support robust evidence-based development of predictive and diagnostic tools and inform clinical care and policy. Objectives To evaluate COVID-19 severity and risk factors over time and assess the use of machine learning to predict clinical severity. Design, Setting, and Participants In a retrospective cohort study of 1 926 526 US adults with SARS-CoV-2 infection (polymerase chain reaction >99% or antigen <1%) and adult patients without SARS-CoV-2 infection who served as controls from 34 medical centers nationwide between January 1, 2020, and December 7, 2020, patients were stratified using a World Health Organization COVID-19 severity scale and demographic characteristics. Differences between groups over time were evaluated using multivariable logistic regression. Random forest and XGBoost models were used to predict severe clinical course (death, discharge to hospice, invasive ventilatory support, or extracorporeal membrane oxygenation). Main Outcomes and Measures Patient demographic characteristics and COVID-19 severity using the World Health Organization COVID-19 severity scale and differences between groups over time using multivariable logistic regression. Results The cohort included 174 568 adults who tested positive for SARS-CoV-2 (mean [SD] age, 44.4 [18.6] years; 53.2% female) and 1 133 848 adult controls who tested negative for SARS-CoV-2 (mean [SD] age, 49.5 [19.2] years; 57.1% female). Of the 174 568 adults with SARS-CoV-2, 32 472 (18.6%) were hospitalized, and 6565 (20.2%) of those had a severe clinical course (invasive ventilatory support, extracorporeal membrane oxygenation, death, or discharge to hospice). Of the hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March to April 2020 to 8.6% in September to October 2020 (P = .002 for monthly trend). Using 64 inputs available on the first hospital day, this study predicted a severe clinical course using random forest and XGBoost models (area under the receiver operating curve = 0.87 for both) that were stable over time. The factor most strongly associated with clinical severity was pH; this result was consistent across machine learning methods. In a separate multivariable logistic regression model built for inference, age (odds ratio [OR], 1.03 per year; 95% CI, 1.03-1.04), male sex (OR, 1.60; 95% CI, 1.51-1.69), liver disease (OR, 1.20; 95% CI, 1.08-1.34), dementia (OR, 1.26; 95% CI, 1.13-1.41), African American (OR, 1.12; 95% CI, 1.05-1.20) and Asian (OR, 1.33; 95% CI, 1.12-1.57) race, and obesity (OR, 1.36; 95% CI, 1.27-1.46) were independently associated with higher clinical severity. Conclusions and Relevance This cohort study found that COVID-19 mortality decreased over time during 2020 and that patient demographic characteristics and comorbidities were associated with higher clinical severity. The machine learning models accurately predicted ultimate clinical severity using commonly collected clinical data from the first 24 hours of a hospital admission.
Collapse
Affiliation(s)
- Tellen D. Bennett
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
| | - Richard A. Moffitt
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | | | | | - Adit Anand
- Stony Brook University, Stony Brook, New York
| | | | | | | | - James Brian Byrd
- Department of Internal Medicine, The University of Michigan at Ann Arbor, Ann Arbor
| | - Alina Denham
- Department of Public Health Sciences, University of Rochester Medical Center, Rochester, New York
| | - Peter E. DeWitt
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
| | - Davera Gabriel
- Institute for Clinical and Translational Research, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Brian T. Garibaldi
- Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | | | | | - Elaine L. Hill
- Department of Public Health Sciences, University of Rochester Medical Center, Rochester, New York
| | - Stephanie S. Hong
- Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | | | - Ramakanth Kavuluru
- Division of Biomedical Informatics, Department of Internal Medicine, University of Kentucky, Lexington
| | - Kristin Kostka
- Real World Solutions, IQVIA, Cambridge, Massachusetts
- Observational Health Data Sciences and Informatics, New York, New York
| | - Harold P. Lehmann
- Division of Health Science Informatics, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Eli Levitt
- Department of Orthopaedic Surgery, University of Alabama at Birmingham, Birmingham
| | | | | | - Julie A. McMurry
- Translational and Integrative Sciences Center, Oregon State University, Corvallis
| | - Michele Morris
- Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, Pennsylvania
| | - John Muschelli
- Department of Biostatistics, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Andrew J. Neumann
- Translational and Integrative Sciences Center, Oregon State University, Corvallis
| | | | - Emily R. Pfaff
- North Carolina Translational and Clinical Sciences Institute, University of North Carolina at Chapel Hill, Chapel Hill
| | - Zhenglong Qian
- Department of biomedical informatics, Stony Brook University, Stony Brook, New York
| | | | - Seth Russell
- Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora
| | - Heidi Spratt
- Department of Preventive Medicine and Public Health, University of Texas Medical Branch, Galveston
| | - Anita Walden
- Sage Bionetworks, Seattle, Washington
- Oregon Clinical and Translational Research Institute, Oregon Health & Science University, Portland
| | - Andrew E. Williams
- Tufts Medical Center Clinical and Translational Science Institute, Tufts Medical Center, Boston, Massachusetts
| | | | - Yun Jae Yoo
- Stony Brook University, Stony Brook, New York
| | - Xiaohan Tanner Zhang
- Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Richard L. Zhu
- Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - Christopher P. Austin
- National Center for Advancing Translational Sciences, National Institutes of Health, Bethesda, Maryland
| | - Joel H. Saltz
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, New York
| | - Ken R. Gersing
- National Center for Advancing Translational Sciences, National Institutes of Health, Bethesda, Maryland
| | - Melissa A. Haendel
- TriNetX, Cambridge, Massachusetts
- Center for Health AI, University of Colorado, Aurora
| | - Christopher G. Chute
- Department of Health Policy and Management, Johns Hopkins University School of Medicine, Baltimore, Maryland
- Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland
- Department of Nursing, Johns Hopkins University School of Medicine, Baltimore, Maryland
| |
Collapse
|
6
|
Bennett TD, Moffitt RA, Hajagos JG, Amor B, Anand A, Bissell MM, Bradwell KR, Bremer C, Byrd JB, Denham A, DeWitt PE, Gabriel D, Garibaldi BT, Girvin AT, Guinney J, Hill EL, Hong SS, Jimenez H, Kavuluru R, Kostka K, Lehmann HP, Levitt E, Mallipattu SK, Manna A, McMurry JA, Morris M, Muschelli J, Neumann AJ, Palchuk MB, Pfaff ER, Qian Z, Qureshi N, Russell S, Spratt H, Walden A, Williams AE, Wooldridge JT, Yoo YJ, Zhang XT, Zhu RL, Austin CP, Saltz JH, Gersing KR, Haendel MA, Chute CG. The National COVID Cohort Collaborative: Clinical Characterization and Early Severity Prediction. medRxiv 2021. [PMID: 33469592 PMCID: PMC7814838 DOI: 10.1101/2021.01.12.21249511] [Citation(s) in RCA: 28] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Background: The majority of U.S. reports of COVID-19 clinical characteristics, disease course, and treatments are from single health systems or focused on one domain. Here we report the creation of the National COVID Cohort Collaborative (N3C), a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative U.S. cohort of COVID-19 cases and controls to date. This multi-center dataset supports robust evidence-based development of predictive and diagnostic tools and informs critical care and policy. Methods and Findings: In a retrospective cohort study of 1,926,526 patients from 34 medical centers nationwide, we stratified patients using a World Health Organization COVID-19 severity scale and demographics; we then evaluated differences between groups over time using multivariable logistic regression. We established vital signs and laboratory values among COVID-19 patients with different severities, providing the foundation for predictive analytics. The cohort included 174,568 adults with severe acute respiratory syndrome associated with SARS-CoV-2 (PCR >99% or antigen <1%) as well as 1,133,848 adult patients that served as lab-negative controls. Among 32,472 hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March/April 2020 to 8.6% in September/October 2020 (p = 0.002 monthly trend). In a multivariable logistic regression model, age, male sex, liver disease, dementia, African-American and Asian race, and obesity were independently associated with higher clinical severity. To demonstrate the utility of the N3C cohort for analytics, we used machine learning (ML) to predict clinical severity and risk factors over time. Using 64 inputs available on the first hospital day, we predicted a severe clinical course (death, discharge to hospice, invasive ventilation, or extracorporeal membrane oxygenation) using random forest and XGBoost models (AUROC 0.86 and 0.87 respectively) that were stable over time. The most powerful predictors in these models are patient age and widely available vital sign and laboratory values. The established expected trajectories for many vital signs and laboratory values among patients with different clinical severities validates observations from smaller studies, and provides comprehensive insight into COVID-19 characterization in U.S. patients. Conclusions: This is the first description of an ongoing longitudinal observational study of patients seen in diverse clinical settings and geographical regions and is the largest COVID-19 cohort in the United States. Such data are the foundation for ML models that can be the basis for generalizable clinical decision support tools. The N3C Data Enclave is unique in providing transparent, reproducible, easily shared, versioned, and fully auditable data and analytic provenance for national-scale patient-level EHR data. The N3C is built for intensive ML analyses by academic, industry, and citizen scientists internationally. Many observational correlations can inform trial designs and care guidelines for this new disease.
Collapse
|
7
|
Torniai C, Essaid S, Barnes C, Conlon M, Williams S, Hajagos JG, Bremer E, Corson-Rikert J, Haendel M. From EHRs to Linked Data: representing and mining encounter data for clinical expertise evaluation. AMIA Jt Summits Transl Sci Proc 2013; 2013:165. [PMID: 24303330] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Subscribe] [Scholar Register] [Indexed: 06/02/2023]
Abstract
Translational science, today, involves multidisciplinary teams of scientists rather than single scientists. Teams facilitate biologically meaningful and clinically consequential breakthroughs. There are a myriad of sources of data about investigators, physicians, research resources, clinical encounters, and expertise to promote team interaction; however, much of this information is not connected and is left siloed. Large amounts of data have been published as Linked Data (LD), but there still remains a significant gap in the representation and connection of research resources and clinical expertise data. The CTSAconnect project addresses the problem of fragmentation and incompatible coding of information by creating a Semantic Framework that facilitates the production and consumption of LD about biomedical research resources, clinical activities, as well as investigator and physician expertise.
Collapse
Affiliation(s)
- Carlo Torniai
- OHSU Library and Department of Medical Informatics, Oregon Health & Science University, Portland, OR
| | | | | | | | | | | | | | | | | |
Collapse
|