Michael Green, Jonas Björk, Jakob Forberg, Ulf Ekelund, Lars Edenbrandt and Mattias Ohlsson
Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room
Artificial Intelligence in Medicine 38, 305-318 (2006)
Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogenous 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. Artificial neural network (ANN) ensembles and easily interpretable 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. 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 clinically acceptable 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 performance. The logistic model were slightly better in terms of model calibration and intra-method variations, but had a worse performance in terms of ROC area. Clinically, a prediction model of the present type, combined with the judgment of trained ED personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.
LU TP 05-45