Predicting the probability of survival in intensive care unit patients from a small number of variables and training examples

Artificial Intelligence in Medicine

Volumn 45, Issue 1, 2009, Pages 63-76

  Luaces, Oscar ^a   Taboada, Francisco ^b   Albaiceta, Guillermo M ^b   Domínguez, Luis A ^c   Enríquez, Pedro ^c   Bahamonde, Antonio ^a  

^a UNIVERSITY OF OVIEDO   (Spain)

^b HOSPITAL UNIVERSITARIO CENTRAL DE ASTURIAS   (Spain)

^c HOSPITAL UNIVERSITARIO RÍO HORTEGA   (Spain)

Author keywords

Intensive care; Mortality risk prediction; Reduced number of variables and cases; Support vector machines

Indexed keywords

ACUTE PHYSIOLOGY AND CHRONIC HEALTH EVALUATIONS; CLINICAL ROUTINES; CORONARY DISEASE; CRITICALLY-ILL PATIENTS; DATA SETS; DIAGNOSTIC FEATURES; INTENSIVE CARE; LEARNING METHODS; LOGISTIC REGRESSIONS; MONITORING DEVICES; MORTALITY RISK PREDICTION; PREDICTION PERFORMANCE; PREDICTION SYSTEMS; PROBABILITY OF SURVIVALS; RE CALIBRATIONS; REDUCED NUMBER OF VARIABLES AND CASES; SCORING FUNCTIONS; SCORING SYSTEMS; SECOND LEVELS; SURVIVAL PROBABILITIES; TRAINING EXAMPLES;

FORECASTING; FUNCTIONS; HEALTH RISKS; IMAGE RETRIEVAL; INTENSIVE CARE UNITS; PROBABILITY DENSITY FUNCTION;

SUPPORT VECTOR MACHINES;

ARTICLE; CORONARY CARE UNIT; CRITICALLY ILL PATIENT; DEMOGRAPHY; HUMAN; INTENSIVE CARE; INTENSIVE CARE UNIT; INTERMETHOD COMPARISON; MACHINE LEARNING; MAJOR CLINICAL STUDY; PREDICTOR VARIABLE; PRIORITY JOURNAL; PROBABILITY; SCORING SYSTEM; SUPPORT VECTOR MACHINE; SURVIVAL; SURVIVAL RATE; TRAINING;

HUMANS; INTENSIVE CARE UNITS; LEARNING; MODELS, THEORETICAL; PROBABILITY; SURVIVAL;

EID: 60349126981     PISSN: 09333657     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.artmed.2008.11.005     Document Type: Article

References (26)

1. Provonost P., and Angus D. Economics of end-life-care in the intensive care unit. Crit Care Med 29 Suppl (2001) 46-51
2. Lemeshow S., Teres D., Klar J., Avrunin J.S., Gehlbach S.H., and Rapoport J. Mortality probability models (MPM II) based on an international cohort of intensive care unit patients. J Am Med Assoc 270 20 (1993) 2478-2486
3. Abu-Hanna A., and Lucas P. Prognostic models in medicine-AI and statistical approaches. Methods Inform Med 40 (2001) 1-5
4. Ohno-Machado L., Resnic F., and Matheny M. Prognosis in critical care. Annu Rev Biomed Eng 8 (2006) 567-599
5. Knaus W., Draper E., Wagner D., Zimmerman J., Bergner M., Bastos P., et al. The APACHE III prognostic system. Risk prediction of hospital mortality for critically ill hospitalized adults. Chest 100 (1991) 1619-1636
6. Le Gall J., Loirat P., Alperovitch A., Glaser P., Granthil C., Mathieu D., et al. A simplified acute physiology score for ICU patients. Crit Care Med 12 (1984) 975-977
7. Render M, Welsh D, Kollef M, Lott III J, Hui S, Weinberger M, et al. Automated computerized intensive care unit severity of illness measure in the Department of Veterans Affairs: preliminary results. Crit Care Med 2000;28(10):3540-6.
8. Render M, Deddens J, Freyberg R, Almenoff P, Connors Jr A, Wagner D, et al. Veterans affairs intensive care unit risk adjustment model: validation, updating, recalibration. Crit Care Med 2008;36(4):1031-42.
9. Vapnik V. Statistical learning theory (1998), John Wiley, New York
10. Luaces O, Quevedo JR, Taboada F, Albaiceta GM, Bahamonde A. Prediction of probability of survival in critically ill patients optimizing the area under the ROC curve. In: Veloso MM, editor. Proceedings of the international joint conference on artificial intelligence (IJCAI'07). AAAI Press, Menlo Park, California, USA; 2007. p. 956-61.
11. Matheny M., Resnic F., Arora N., and Ohno-Machado L. Effects of SVM parameter optimization on discrimination and calibration for post-procedural PCI mortality. J Biomed Inform 40 6 (2007) 688-697
12. Hanley J., and McNeil B. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143 1 (1982) 29-36
13. Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Smola A, Bartlett P, Schölkopf B, Schuurmans, editors. Advances in large margin classifiers. Cambridge, Massachusetts, USA: MIT Press; 2000. p. 61-74.
14. Joachims T. A support vector method for multivariate performance measures. In: Luc de Raedt, Stefan Wrobel, editors. Proceedings of the international conference on machine learning (ICML'05); 2005. p. 377-84.
15. Joachims T. Training linear SVMs in linear time. In: Ungar L, Craven M, Gunopulos D, Eliassi-Rad T, editors. Proceedings of the ACM SIGKDD conference on knowledge discovery and data mining (KDD). ACM Press, New York, USA; 2006. p. 217-26.
16. Brier G. Verification of forecasts expressed in terms of probability. Monthly Weather Rev 78 (1950) 1-3
17. Cortes C, Mohri M. AUC optimization vs. error rate minimization. In: Thrun S, Saul L, Schölkopf B, editors. Advances in neural information processing systems 16. Cambridge, Massachusetts, USA: MIT Press; 2004.
18. Herbrich R, Graepel T, Obermayer K. Large margin rank boundaries for ordinal regression. In: Smola A, Bartlett P, Schölkopf B, Schuurmans D, editors. Advances in large margin classifiers. Cambridge, Massachusetts, USA: MIT Press; 2000. p. 115-32.
19. Joachims T. Optimizing search engines using clickthrough data. In: Zaïane OR, Goebel R, Hand D, Keim D, Ng R, editors. Proceedings of the ACM SIGKDD conference on knowledge discovery and data mining (KDD). ACM Press, New York, USA; 2002. p. 133-42.
20. Bahamonde A, Bayón GF, Díez J, Quevedo JR, Luaces O, del Coz JJ, et al. Feature subset selection for learning preferences: a case study. In: Greiner R, Schuurmans D, editors. Proceedings of the international conference on machine learning (ICML'04); 2004. p. 49-56.
21. Silva A., Cortez P., Santos M., Gomes L., and Neves J. Mortality assessment in intensive care units via adverse events using artificial neural networks. Artif Intell Med 36 3 (2006) 223-234
22. de Rooij S., Abu-Hanna A., Levi M., and de Jonge E. Identification of high-risk subgroups in very elderly intensive care unit patients. Crit Care 11 2 (2007) 33
23. Nannings B., Abu-Hanna A., and de Jonge E. Applying PRIM (patient rule induction method) and logistic regression for selecting high-risk subgroups in very elderly ICU patients. Int J Med Inform 77 4 (2008) 272-279
24. Rivera-Fernández R., Vázquez-Mata G., Bravo M., Aguayo-Hoyos E., Zimmerman J., Wagner D., et al. The APACHE III prognostic system: customized mortality predictions for Spanish ICU patients. Intensive Care Med 24 6 (1998) 574-581
25. Lin CJ, Weng RC, Keerthi SS. Trust region Newton method for logistic regression. J Mach Learn Res 2008;9(April):627-50.
26. Demšar J. Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7 (2006) 1-30