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

BMC Medical Informatics and Decision Making

Volumn 8, Issue , 2008, Pages

  Verplancke, T ^a   Van Looy, S ^b   Benoit, D ^a   Vansteelandt, S ^b   Depuydt, P ^a   De Turck, F ^b   Decruyenaere, J ^a  

^a GHENT UNIVERSITY HOSPITAL   (Belgium)

^b GHENT UNIVERSITY   (Belgium)

Author keywords

[No Author keywords available]

Indexed keywords

ADULT; AGED; ARTICLE; CANCER PATIENT; CONTROLLED STUDY; CRITICALLY ILL PATIENT; DISCRIMINANT ANALYSIS; FEMALE; HEMATOLOGIC MALIGNANCY; HOSPITAL ADMISSION; HUMAN; INTENSIVE CARE UNIT; INTERMETHOD COMPARISON; MAJOR CLINICAL STUDY; MALE; MEDICAL RECORD REVIEW; MORTALITY; MULTIVARIATE LOGISTIC REGRESSION ANALYSIS; PREDICTION; RECEIVER OPERATING CHARACTERISTIC; ROC CURVE; STATISTICAL MODEL; STATISTICAL SIGNIFICANCE; SUPPORT VECTOR MACHINE; VALIDATION STUDY; ALGORITHM; BLOOD DISEASE; COMPARATIVE STUDY; COMPUTER PROGRAM; CRITICAL ILLNESS; MIDDLE AGED; PREDICTION AND FORECASTING; PROSPECTIVE STUDY;

ALGORITHMS; CRITICAL ILLNESS; FEMALE; HEMATOLOGIC NEOPLASMS; HOSPITAL MORTALITY; HUMANS; INTENSIVE CARE UNITS; LOGISTIC MODELS; MALE; MIDDLE AGED; PREDICTIVE VALUE OF TESTS; PROSPECTIVE STUDIES; ROC CURVE; SOFTWARE;

EID: 58149265688     PISSN: None     EISSN: 14726947     Source Type: Journal    
DOI: 10.1186/1472-6947-8-56     Document Type: Article

References (22)

1. Outcome and early prognostic indicators in patients with a hematologic malignancy admitted to the intensive care unit for a life-threatening complication. DD Benoit KH Vandewoude JM Decruyenaere EA Hoste FA Colardyn, Crit Care Med 2003 31 1 104 112 12545002
2. A training algorithm for optimal margin classifiers. B Boser V Vapnik, Proceedings of the fifth annual workshop on Computational learning theory (Pittsburgh, Pennsylvania, USA) 1992 144 152
3. Support-vector networks. C Cortes V Vapnik, Machine Learning 1995 20 3 273 297
4. Incorporating invariances in support vector learning machines. B Schölkopf C Burges V Vapnik, Proceedings of the 1996 International Conference on Artificial Networks, Bochum, Germany Lecture notes in computer science 1996 1112 47 52
5. A novel approach for prediction of tacrolimus blood concentration in liver transplantation patients in the intensive care unit through support vector regression. S Van Looy T Verplancke D Benoit E Hoste G Van Maele F De Turck J Decruyenaere, Crit Care 2007 11 4 R83 17655766
6. Support vector machine classification applied on weaning trials patients. B Giraldo A Garde C Arizmendi R Jane S Benito I Diaz D Ballesteros, Conf Proc IEEE Eng Med Biol Soc 2006 1 5587 5590 17947151
7. Support vector machine applications in bioinformatics. E Byvatov G Schneider, Appl Bioinformatics 2003 2 2 67 77 15130823
8. Applying Support Vector Machines for Gene Ontology based gene function prediction. A Vinayagam R Konig J Moormann F Schubert R Eils KH Glatting S Suhai, BMC Bioinformatics 2004 5 116 15333146
9. Principles of Data Mining. D Hand P Mannila P Smyth, MIT Press, Cambridge, MA 2001
10. A decision support system to facilitate management of patients with acute gastrointestinal bleeding. A Chu H Ahn B Halwan B Kalmin EL Artifon A Barkun MG Lagoudakis A Kumar, Artif Intell Med 2007 18063351
11. What is a support vector machine? WS Noble, Nat Biotechnol 2006 24 12 1565 1567 17160063
12. Documented and clinically suspected bacterial infection precipitating intensive care unit admission in patients with hematological malignancies: impact on outcome. DD Benoit PO Depuydt RA Peleman FC Offner KH Vandewoude DP Vogelaers SI Blot LA Noens FA Colardyn JM Decruyenaere, Intensive Care Med 2005 31 7 934 942 15782316
13. Acute Physiology and Chronic Health Evaluation (APACHE) IV: hospital mortality assessment for today's critically ill patients. JE Zimmerman AA Kramer DS McNair FM Malila, Crit Care Med 2006 34 5 1297 1310 16540951
14. Multicenter outcome study of cancer patients admitted to the intensive care unit: a probability of mortality model. JS Groeger S Lemeshow K Price DM Nierman P White Jr J Klar S Granovsky D Horak SK Kish, J Clin Oncol 1998 16 2 761 770 9469368
15. 'Feature selection in the prediction of Infliximab dose increase'. S Van Looy J Meeus B Wyns B Vander Cruyssen F De Keyser L Boullart, Proceedings of the 9th IASTED International Conference Artificial Intelligence and Soft Computing 2005
16. Gene selection for cancer classification using support vector machines. I Guyon J Weston S Barnhill V Vapnik, Machine Learning, 46(1-3);389-422,2002 2002 46 1-3 389 422
17. Modeling the severity of illness of ICU patients. A systems update. S Lemeshow JR Le Gall, Jama 1994 272 13 1049 1055 8089888
18. 'Comparing the Areas Under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach'. ER DeLong DM DeLong D Clarke-Pearson, Biometrics 1988 44 837 845 3203132
19. 'Applied Logistic Regression'. D Hosmer S Lemeshow, Wiley Series in Probability and Statistics John Wiley & Sons, Inc second 2000
20. Impact of two different comorbidity measures on the 6-month mortality of critically ill cancer patients. M Soares JI Salluh CG Ferreira RR Luiz N Spector JR Rocco, Intensive Care Med 2005 31 3 408 415 15678310
21. Prognosis in critical care. L Ohno-Machado FS Resnic ME Matheny, Annu Rev Biomed Eng 2006 8 567 599 16834567
22. On time series analysis of public health and biomedical data. SL Zeger R Irizarry RD Peng, Annu Rev Public Health 2006 27 57 79 16533109