Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room
(2006) In Artificial Intelligence in Medicine 38(3). p.305-318- Abstract
- Summary
Objective
Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations.
Methods and materials
Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating... (More) - Summary
Objective
Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations.
Methods and materials
Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model.
Results
The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models.
Conclusion
Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/593190
- author
- Green, Michael LU ; Björk, Jonas LU ; Forberg, Jakob LU ; Ekelund, Ulf LU ; Edenbrandt, Lars LU and Ohlsson, Mattias LU
- organization
- publishing date
- 2006
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Ensemble methods, Acute coronary syndrome, Acute myocardial infarction, Artificial neural networks, Logistic regression, Clinical decision support
- in
- Artificial Intelligence in Medicine
- volume
- 38
- issue
- 3
- pages
- 14 pages
- publisher
- Elsevier
- external identifiers
-
- wos:000242848700006
- scopus:33750936249
- ISSN
- 1873-2860
- DOI
- 10.1016/j.artmed.2006.07.006
- project
- AIR Lund Chest pain - More efficient and equal emergency care with advanced medical decision support tools
- language
- English
- LU publication?
- yes
- id
- fde44c88-5379-417c-a50f-794c47ed7a73 (old id 593190)
- date added to LUP
- 2016-04-01 11:51:34
- date last changed
- 2024-04-22 19:48:58
@article{fde44c88-5379-417c-a50f-794c47ed7a73, abstract = {{Summary<br/><br> Objective<br/><br> <br/><br> Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations.<br/><br> Methods and materials<br/><br> <br/><br> Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model.<br/><br> Results<br/><br> <br/><br> The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models.<br/><br> Conclusion<br/><br> <br/><br> Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.}}, author = {{Green, Michael and Björk, Jonas and Forberg, Jakob and Ekelund, Ulf and Edenbrandt, Lars and Ohlsson, Mattias}}, issn = {{1873-2860}}, keywords = {{Ensemble methods; Acute coronary syndrome; Acute myocardial infarction; Artificial neural networks; Logistic regression; Clinical decision support}}, language = {{eng}}, number = {{3}}, pages = {{305--318}}, publisher = {{Elsevier}}, series = {{Artificial Intelligence in Medicine}}, title = {{Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room}}, url = {{https://lup.lub.lu.se/search/files/2674506/1034045.pdf}}, doi = {{10.1016/j.artmed.2006.07.006}}, volume = {{38}}, year = {{2006}}, }