Literature DB >> 31605488

Derivation and validation of a machine learning record linkage algorithm between emergency medical services and the emergency department.

Colby Redfield1, Abdulhakim Tlimat1,2, Yoni Halpern3, David W Schoenfeld1, Edward Ullman1, David A Sontag4,5, Larry A Nathanson1,2, Steven Horng1,2,6.   

Abstract

OBJECTIVE: Linking emergency medical services (EMS) electronic patient care reports (ePCRs) to emergency department (ED) records can provide clinicians access to vital information that can alter management. It can also create rich databases for research and quality improvement. Unfortunately, previous attempts at ePCR and ED record linkage have had limited success. In this study, we use supervised machine learning to derive and validate an automated record linkage algorithm between EMS ePCRs and ED records.
MATERIALS AND METHODS: All consecutive ePCRs from a single EMS provider between June 2013 and June 2015 were included. A primary reviewer matched ePCRs to a list of ED patients to create a gold standard. Age, gender, last name, first name, social security number, and date of birth were extracted. Data were randomly split into 80% training and 20% test datasets. We derived missing indicators, identical indicators, edit distances, and percent differences. A multivariate logistic regression model was trained using 5-fold cross-validation, using label k-fold, L2 regularization, and class reweighting.
RESULTS: A total of 14 032 ePCRs were included in the study. Interrater reliability between the primary and secondary reviewer had a kappa of 0.9. The algorithm had a sensitivity of 99.4%, a positive predictive value of 99.9%, and an area under the receiver-operating characteristic curve of 0.99 in both the training and test datasets. Date-of-birth match had the highest odds ratio of 16.9, followed by last name match (10.6). Social security number match had an odds ratio of 3.8.
CONCLUSIONS: We were able to successfully derive and validate a record linkage algorithm from a single EMS ePCR provider to our hospital EMR.
© The Author(s) 2019. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  clinical informatics; electronic patient care records; emergency medical services; machine learning; patient matching; prehospital care; record linkage

Mesh:

Year:  2020        PMID: 31605488      PMCID: PMC7647245          DOI: 10.1093/jamia/ocz176

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   4.497


  13 in total

1.  Hospital performance reports: impact on quality, market share, and reputation.

Authors:  Judith H Hibbard; Jean Stockard; Martin Tusler
Journal:  Health Aff (Millwood)       Date:  2005 Jul-Aug       Impact factor: 6.301

2.  Airway management and out-of-hospital cardiac arrest outcome in the CARES registry.

Authors:  Jason McMullan; Ryan Gerecht; Jordan Bonomo; Rachel Robb; Bryan McNally; John Donnelly; Henry E Wang
Journal:  Resuscitation       Date:  2014-02-18       Impact factor: 5.262

3.  Probabilistic linkage of large public health data files.

Authors:  M A Jaro
Journal:  Stat Med       Date:  1995 Mar 15-Apr 15       Impact factor: 2.373

4.  Emergency medical dispatch codes association with emergency department outcomes.

Authors:  A Zachary Hettinger; Jeremy T Cushman; Manish N Shah; Katia Noyes
Journal:  Prehosp Emerg Care       Date:  2012-11-09       Impact factor: 3.077

5.  Lack of emergency medical services documentation is associated with poor patient outcomes: a validation of audit filters for prehospital trauma care.

Authors:  Dann J Laudermilch; Melissa A Schiff; Avery B Nathens; Matthew R Rosengart
Journal:  J Am Coll Surg       Date:  2009-12-04       Impact factor: 6.113

6.  Evaluating the use of existing data sources, probabilistic linkage, and multiple imputation to build population-based injury databases across phases of trauma care.

Authors:  Craig Newgard; Susan Malveau; Kristan Staudenmayer; N Ewen Wang; Renee Y Hsia; N Clay Mann; James F Holmes; Nathan Kuppermann; Jason S Haukoos; Eileen M Bulger; Mengtao Dai; Lawrence J Cook
Journal:  Acad Emerg Med       Date:  2012-04       Impact factor: 3.451

7.  Linking large administrative databases: a method for conducting emergency medical services cohort studies using existing data.

Authors:  S A Waien
Journal:  Acad Emerg Med       Date:  1997-11       Impact factor: 3.451

8.  Association of prehospital advanced airway management with neurologic outcome and survival in patients with out-of-hospital cardiac arrest.

Authors:  Kohei Hasegawa; Atsushi Hiraide; Yuchiao Chang; David F M Brown
Journal:  JAMA       Date:  2013-01-16       Impact factor: 56.272

9.  Prehospital system delay in ST-segment elevation myocardial infarction care: a novel linkage of emergency medicine services and in hospital registry data.

Authors:  Emil L Fosbøl; Christopher B Granger; Eric D Peterson; Li Lin; Barbara L Lytle; Frances S Shofer; Chad Lohmeier; Greg D Mears; J Lee Garvey; Claire C Corbett; James G Jollis; Seth W Glickman
Journal:  Am Heart J       Date:  2013-01-22       Impact factor: 4.749

10.  Prehospital electronic patient care report systems: early experiences from emergency medical services agency leaders.

Authors:  Adam B Landman; Christopher H Lee; Comilla Sasson; Carin M Van Gelder; Leslie A Curry
Journal:  PLoS One       Date:  2012-03-05       Impact factor: 3.240

View more
  3 in total

1.  Influence of artificial intelligence on the work design of emergency department clinicians a systematic literature review.

Authors:  Albert Boonstra; Mente Laven
Journal:  BMC Health Serv Res       Date:  2022-05-18       Impact factor: 2.908

2.  Artificial intelligence in emergency medicine: A scoping review.

Authors:  Abirami Kirubarajan; Ahmed Taher; Shawn Khan; Sameer Masood
Journal:  J Am Coll Emerg Physicians Open       Date:  2020-11-07

3.  Linking Emergency Medical Services and Emergency Department Data to Improve Overdose Surveillance in North Carolina.

Authors:  Jonathan Fix; Amy I Ising; Scott K Proescholdbell; Dennis M Falls; Catherine S Wolff; Antonio R Fernandez; Anna E Waller
Journal:  Public Health Rep       Date:  2021 Nov-Dec       Impact factor: 2.792

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.