D R Vinson1, J E Morley2, J Huang3, V Liu4, M L Anderson5, C E Drenten6, R P Radecki7, D K Nishijima2, M E Reed3. 1. The Permanente Medical Group , Oakland, California ; Department of Emergency Medicine, Kaiser Permanente Roseville Medical Center , Roseville, California ; Kaiser Permanente Division of Research , Oakland, California. 2. Department of Emergency Medicine, University of California Davis School of Medicine , Sacramento, California. 3. Kaiser Permanente Division of Research , Oakland, California. 4. The Permanente Medical Group , Oakland, California ; Kaiser Permanente Division of Research , Oakland, California ; Department of Pulmonary and Critical Care Medicine, Kaiser Permanente Santa Clara Medical Center , Santa Clara, California. 5. The Permanente Medical Group , Oakland, California ; Department of Emergency Medicine, Kaiser Permanente Roseville Medical Center , Roseville, California. 6. Department of Emergency Medicine, Sutter General Medical Center , Sacramento, California. 7. Department of Emergency Medicine, The University of Texas Medical School , Houston, Texas.
Abstract
BACKGROUND: The Pulmonary Embolism (PE) Severity Index identifies emergency department (ED) patients with acute PE that can be safely managed without hospitalization. However, the Index comprises 11 weighted variables, complexity that can impede its integration into contextual workflow. OBJECTIVE: We designed a computerized version of the PE Severity Index (e-Index) to automatically extract the required variables from discrete fields in the electronic health record (EHR). We tested the e-Index on the study population to determine its accuracy compared with a gold standard generated by physician abstraction of the EHR on manual chart review. METHODS: This retrospective cohort study included adults with objectively-confirmed acute PE in four community EDs from 2010-2012. Outcomes included performance characteristics of the e-Index for individual values, the number of cases requiring physician editing, and the accuracy of the e-Index risk category (low vs. higher). RESULTS: For the 593 eligible patients, there were 6,523 values automatically extracted. Fifty one of these needed physician editing, yielding an accuracy at the value-level of 99.2% (95% confidence interval [CI], 99.0%-99.4%). Sensitivity was 96.9% (95% CI, 96.0%-97.9%) and specificity was 99.8% (95% CI, 99.7%-99.9%). The 51 corrected values were distributed among 47 cases: 43 cases required the correction of one variable and four cases required the correction of two. At the risk-category level, the e-Index had an accuracy of 96.8% (95% CI, 95.0%-98.0%), under-classifying 16 higher-risk cases (2.7%) and over-classifying 3 low-risk cases (0.5%). CONCLUSION: Our automated extraction of variables from the EHR for the e-Index demonstrates substantial accuracy, requiring a minimum of physician editing. This should increase user acceptability and implementation success of a computerized clinical decision support system built around the e-Index, and may serve as a model to automate other complex risk stratification instruments.
BACKGROUND: The Pulmonary Embolism (PE) Severity Index identifies emergency department (ED) patients with acute PE that can be safely managed without hospitalization. However, the Index comprises 11 weighted variables, complexity that can impede its integration into contextual workflow. OBJECTIVE: We designed a computerized version of the PE Severity Index (e-Index) to automatically extract the required variables from discrete fields in the electronic health record (EHR). We tested the e-Index on the study population to determine its accuracy compared with a gold standard generated by physician abstraction of the EHR on manual chart review. METHODS: This retrospective cohort study included adults with objectively-confirmed acute PE in four community EDs from 2010-2012. Outcomes included performance characteristics of the e-Index for individual values, the number of cases requiring physician editing, and the accuracy of the e-Index risk category (low vs. higher). RESULTS: For the 593 eligible patients, there were 6,523 values automatically extracted. Fifty one of these needed physician editing, yielding an accuracy at the value-level of 99.2% (95% confidence interval [CI], 99.0%-99.4%). Sensitivity was 96.9% (95% CI, 96.0%-97.9%) and specificity was 99.8% (95% CI, 99.7%-99.9%). The 51 corrected values were distributed among 47 cases: 43 cases required the correction of one variable and four cases required the correction of two. At the risk-category level, the e-Index had an accuracy of 96.8% (95% CI, 95.0%-98.0%), under-classifying 16 higher-risk cases (2.7%) and over-classifying 3 low-risk cases (0.5%). CONCLUSION: Our automated extraction of variables from the EHR for the e-Index demonstrates substantial accuracy, requiring a minimum of physician editing. This should increase user acceptability and implementation success of a computerized clinical decision support system built around the e-Index, and may serve as a model to automate other complex risk stratification instruments.
Entities:
Keywords:
Clinical decision support systems; data completeness; electronic health record; emergency medicine; pulmonary embolism; risk assessment
Authors: W S Lim; M M van der Eerden; R Laing; W G Boersma; N Karalus; G I Town; S A Lewis; J T Macfarlane Journal: Thorax Date: 2003-05 Impact factor: 9.139
Authors: Ron Pisters; Deirdre A Lane; Robby Nieuwlaat; Cees B de Vos; Harry J G M Crijns; Gregory Y H Lip Journal: Chest Date: 2010-03-18 Impact factor: 9.410
Authors: Drahomir Aujesky; Pierre-Marie Roy; Franck Verschuren; Marc Righini; Joseph Osterwalder; Michael Egloff; Bertrand Renaud; Peter Verhamme; Roslyn A Stone; Catherine Legall; Olivier Sanchez; Nathan A Pugh; Alfred N'gako; Jacques Cornuz; Olivier Hugli; Hans-Jürg Beer; Arnaud Perrier; Michael J Fine; Donald M Yealy Journal: Lancet Date: 2011-06-22 Impact factor: 79.321
Authors: M J Fine; T E Auble; D M Yealy; B H Hanusa; L A Weissfeld; D E Singer; C M Coley; T J Marrie; W N Kapoor Journal: N Engl J Med Date: 1997-01-23 Impact factor: 91.245
Authors: David Jiménez; Drahomir Aujesky; Lisa Moores; Vicente Gómez; José Luis Lobo; Fernando Uresandi; Remedios Otero; Manuel Monreal; Alfonso Muriel; Roger D Yusen Journal: Arch Intern Med Date: 2010-08-09
Authors: Andrea S Gershon; Chengning Wang; Jun Guan; Jovonka Vasilevska-Ristovska; Lisa Cicutto; Teresa To Journal: Can Respir J Date: 2009 Nov-Dec Impact factor: 2.409
Authors: Jonas Bjerring Olesen; Gregory Y H Lip; Morten Lock Hansen; Peter Riis Hansen; Janne Schurmann Tolstrup; Jesper Lindhardsen; Christian Selmer; Ole Ahlehoff; Anne-Marie Schjerning Olsen; Gunnar Hilmar Gislason; Christian Torp-Pedersen Journal: BMJ Date: 2011-01-31
Authors: Laura E Simon; Adina S Rauchwerger; Uli K Chettipally; Leon Babakhanian; David R Vinson; E Margaret Warton; Mary E Reed; Anupam B Kharbanda; Elyse O Kharbanda; Dustin W Ballard Journal: J Am Med Inform Assoc Date: 2019-11-01 Impact factor: 4.497
Authors: Steffani R Bailey; John D Heintzman; Miguel Marino; Megan J Hoopes; Brigit A Hatch; Rachel Gold; Stuart C Cowburn; Christine A Nelson; Heather E Angier; Jennifer E DeVoe Journal: Am J Prev Med Date: 2016-08-10 Impact factor: 5.043
Authors: Juliessa M Pavon; Richard J Sloane; Carl F Pieper; Cathleen S Colón-Emeric; Harvey J Cohen; David Gallagher; Miriam C Morey; Midori McCarty; Thomas L Ortel; Susan N Hastings Journal: Appl Clin Inform Date: 2018-09-26 Impact factor: 2.342
Authors: Christian A Koziatek; Emma Simon; Leora I Horwitz; Danil V Makarov; Silas W Smith; Simon Jones; Soterios Gyftopoulos; Jordan L Swartz Journal: Acad Emerg Med Date: 2018-05-25 Impact factor: 3.451
Authors: David R Vinson; E Margaret Warton; Dustin G Mark; Dustin W Ballard; Mary E Reed; Uli K Chettipally; Nimmie Singh; Sean Z Bouvet; Bory Kea; Patricia C Ramos; David S Glaser; Alan S Go Journal: West J Emerg Med Date: 2018-02-12
Authors: Safiya Richardson; Nasen Jonathan Zhang; Philippe Rameau; Marsophia Julemis; Yan Liu; Jeffrey Solomon; Sundas Khan; Thomas McGinn Journal: JMIR Form Res Date: 2022-02-28