Literature DB >> 18804783

In search of the best method to predict acute coronary syndrome using only the electrocardiogram from the emergency department.

Jakob L Forberg1, Michael Green, Jonas Björk, Mattias Ohlsson, Lars Edenbrandt, Hans Ohlin, Ulf Ekelund.   

Abstract

INTRODUCTION: The aim of this study was to compare different methods to predict acute coronary syndrome (ACS) using only data from a single electrocardiogram (ECG) in the emergency department (ED).
METHOD: We compared the ACS prediction abilities of classical ECG criteria, human expert ECG interpretation, a logistic regression model and an artificial neural network ensemble (ANN). The ED ECG and discharge diagnoses were retrieved for 861 patient visits to the ED for chest pain. Cross-validation was used to estimate the generalization performance of the logistic regression and the ANN model.
RESULTS: The logistic regression model had the overall best performance in predicting ACS with an area under the receiver operating characteristic curve of 0.88. The sensitivities of logistic regression, ANN, expert physicians, and classical ECG criteria were 95%, 95%, 82%, and 75%, respectively, and the specificities were 54%, 44%, 63%, and 69%.
CONCLUSION: Our logistic regression model was the best overall method to predict ACS, followed by our ANN. Decision support models have the potential to improve even experienced ECG readers' ability to predict ACS in the ED.

Entities:  

Mesh:

Year:  2008        PMID: 18804783     DOI: 10.1016/j.jelectrocard.2008.07.010

Source DB:  PubMed          Journal:  J Electrocardiol        ISSN: 0022-0736            Impact factor:   1.438


  13 in total

1.  Prehospital 12-lead ST-segment monitoring improves the early diagnosis of acute coronary syndrome.

Authors:  Jessica K Zègre Hemsey; Kathleen Dracup; Kirsten Fleischmann; Claire E Sommargren; Barbara J Drew
Journal:  J Electrocardiol       Date:  2011-11-23       Impact factor: 1.438

2.  A Statewide Assessment of Prehospital Electrocardiography Approaches of Acquisition and Interpretation for ST-Elevation Myocardial Infarction Based on Emergency Medical Services Characteristics.

Authors:  Jessica K Zègre-Hemsey; Mehul D Patel; Antonio R Fernandez; Michele M Pelter; Jane Brice; Wayne Rosamond
Journal:  Prehosp Emerg Care       Date:  2019-10-31       Impact factor: 3.077

3.  Transfer learning enables prediction of myocardial injury from continuous single-lead electrocardiography.

Authors:  Boyang Tom Jin; Raj Palleti; Siyu Shi; Andrew Y Ng; James V Quinn; Pranav Rajpurkar; David Kim
Journal:  J Am Med Inform Assoc       Date:  2022-10-07       Impact factor: 7.942

4.  Electrocardiogram-Based Machine Learning Emulator Model for Predicting Novel Echocardiography-Derived Phenogroups for Cardiac Risk-Stratification: A Prospective Multicenter Cohort Study.

Authors:  Heenaben B Patel; Naveena Yanamala; Brijesh Patel; Sameer Raina; Peter D Farjo; Srinidhi Sunkara; Márton Tokodi; Nobuyuki Kagiyama; Grace Casaclang-Verzosa; Partho P Sengupta
Journal:  J Patient Cent Res Rev       Date:  2022-04-18

5.  Electrocardiographic diagnosis of ST segment elevation myocardial infarction: An evaluation of three automated interpretation algorithms.

Authors:  J Lee Garvey; Jessica Zegre-Hemsey; Richard Gregg; Jonathan R Studnek
Journal:  J Electrocardiol       Date:  2016-05-02       Impact factor: 1.438

6.  External review and validation of the Swedish national inpatient register.

Authors:  Jonas F Ludvigsson; Eva Andersson; Anders Ekbom; Maria Feychting; Jeong-Lim Kim; Christina Reuterwall; Mona Heurgren; Petra Otterblad Olausson
Journal:  BMC Public Health       Date:  2011-06-09       Impact factor: 3.295

7.  An artificial neural network to safely reduce the number of ambulance ECGs transmitted for physician assessment in a system with prehospital detection of ST elevation myocardial infarction.

Authors:  Jakob L Forberg; Ardavan Khoshnood; Michael Green; Mattias Ohlsson; Jonas Björk; Stefan Jovinge; Lars Edenbrandt; Ulf Ekelund
Journal:  Scand J Trauma Resusc Emerg Med       Date:  2012-02-01       Impact factor: 2.953

8.  Estimating the predictive ability of genetic risk models in simulated data based on published results from genome-wide association studies.

Authors:  Suman Kundu; Raluca Mihaescu; Catherina M C Meijer; Rachel Bakker; A Cecile J W Janssens
Journal:  Front Genet       Date:  2014-06-13       Impact factor: 4.599

9.  Development and evaluation of a simple and effective prediction approach for identifying those at high risk of dyslipidemia in rural adult residents.

Authors:  Chong-Jian Wang; Yu-Qian Li; Ling Wang; Lin-Lin Li; Yi-Rui Guo; Ling-Yun Zhang; Mei-Xi Zhang; Rong-Hai Bie
Journal:  PLoS One       Date:  2012-08-28       Impact factor: 3.240

10.  Application of pattern recognition tools for classifying acute coronary syndrome: an integrated medical modeling.

Authors:  Nader Salari; Shamarina Shohaimi; Farid Najafi; Meenakshii Nallappan; Isthrinayagy Karishnarajah
Journal:  Theor Biol Med Model       Date:  2013-09-18       Impact factor: 2.432

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.