Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignanciesReport as inadecuate




Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies - Download this document for free, or read online. Document in PDF available to download.

BMC Medical Informatics and Decision Making

, 8:56

First Online: 05 December 2008Received: 11 July 2008Accepted: 05 December 2008

Abstract

BackgroundSeveral models for mortality prediction have been constructed for critically ill patients with haematological malignancies in recent years. These models have proven to be equally or more accurate in predicting hospital mortality in patients with haematological malignancies than ICU severity of illness scores such as the APACHE II or SAPS II 1. The objective of this study is to compare the accuracy of predicting hospital mortality in patients with haematological malignancies admitted to the ICU between models based on multiple logistic regression MLR and support vector machine SVM based models.

Methods352 patients with haematological malignancies admitted to the ICU between 1997 and 2006 for a life-threatening complication were included. 252 patient records were used for training of the models and 100 were used for validation. In a first model 12 input variables were included for comparison between MLR and SVM. In a second more complex model 17 input variables were used. MLR and SVM analysis were performed independently from each other. Discrimination was evaluated using the area under the receiver operating characteristic ROC curves ± SE.

ResultsThe area under ROC curve for the MLR and SVM in the validation data set were 0.768 ± 0.04 vs. 0.802 ± 0.04 in the first model p = 0.19 and 0.781 ± 0.05 vs. 0.808 ± 0.04 in the second more complex model p = 0.44. SVM needed only 4 variables to make its prediction in both models, whereas MLR needed 7 and 8 variables in the first and second model respectively.

ConclusionThe discriminative power of both the MLR and SVM models was good. No statistically significant differences were found in discriminative power between MLR and SVM for prediction of hospital mortality in critically ill patients with haematological malignancies.

AbbreviationsACCaccuracy

APACHE scoreAcute Physiology and Chronic Health Evaluation score

AUCArea Under the Receiver Operating Characteristic curve

CSSIscore Cancer Specific Severity of Illness score

ICUIntensive Care Unit

LRlogistic regression

MLRMultiple Logistic Regression

NPVnegative predictive value

PPVpositive predictive value

ROCReceiver Operating Characteristic curve

SAPSSimplified Acute Physiology Score

SNsensitivity

SPspecificity

SVMSupport Vector Machine.

Electronic supplementary materialThe online version of this article doi:10.1186-1472-6947-8-56 contains supplementary material, which is available to authorized users.

Download fulltext PDF



Author: T Verplancke - S Van Looy - D Benoit - S Vansteelandt - P Depuydt - F De Turck - J Decruyenaere

Source: https://link.springer.com/



DOWNLOAD PDF




Related documents