A comparative analysis of predictive models of morbidity in intensive care unit after cardiac surgery - Part I: Model planning

BMC Medical Informatics and Decision Making

Volumn 7, Issue , 2007, Pages

  Barbini, Emanuela ^a   Cevenini, Gabriele ^a   Scolletta, Sabino ^a   Biagioli, Bonizella ^a   Giomarelli, Pierpaolo ^a   Barbini, Paolo ^a  

^a UNIVERSITY OF SIENA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

ACCURACY; ALGORITHM; BAYES THEOREM; CALIBRATION; COMPARATIVE STUDY; HEART SURGERY; INTENSIVE CARE UNIT; LOGISTIC REGRESSION ANALYSIS; MORBIDITY; PRACTICE GUIDELINE; REVIEW; RISK ASSESSMENT; SCORING SYSTEM; STATISTICAL MODEL; ARTICLE; ARTIFICIAL NEURAL NETWORK; FEMALE; HOSPITAL READMISSION; HUMAN; LENGTH OF STAY; MALE; POSTOPERATIVE COMPLICATION; PREDICTION AND FORECASTING; STANDARD; STATISTICS;

ALGORITHMS; BAYES THEOREM; CARDIAC SURGICAL PROCEDURES; FEMALE; HUMANS; INTENSIVE CARE UNITS; LENGTH OF STAY; LOGISTIC MODELS; MALE; MODELS, STATISTICAL; MORBIDITY; NEURAL NETWORKS (COMPUTER); PATIENT READMISSION; POSTOPERATIVE COMPLICATIONS; PREDICTIVE VALUE OF TESTS; RISK ASSESSMENT;

EID: 39349102353     PISSN: None     EISSN: 14726947     Source Type: Journal    
DOI: 10.1186/1472-6947-7-35     Document Type: Review

References (71)

1. Performance of prognostic models in critically ill cancer patients - a review. S den Boer NF de Keizer E de Jonge, Critical Care 2005 9 R458 R463 16137361 10.1186/cc3765
2. Logistic regression and artificial neural network classification models: a methodology review. S Dreiseitl L Ohno-Machado, J Biomed Inform 2002 35 352 359 10.1016/S1532-0464(03)00034-0 12968784
3. Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency room. F Jaimes J Fabiarz D Alvarez C Martinez, Crit Care 2005 9 R150 156 15774048 10.1186/cc3054
4. Cardiac surgery risk models: a position article. DM Shahian EH Blackstone FH Edwards FL Grover GL Grunkemeier DC Naftel SA Nashef WC Nugent ED Peterson, Ann Thorac Surg 2004 78 1868 1877 10.1016/j.athoracsur.2004.05.054 15511504
5. A multivariate Bayesian model for assessing morbidity after coronary artery surgery. B Biagioli S Scolletta G Cevenini E Barbini P Giomarelli P Barbini, Crit Care 2006 10 R94 16813658 10.1186/cc4441
6. Should morbidity replace mortality as an end-point for clinical trials in intensive care? AJ Petros JC Marshall HKF Van Saene, Lancet 1995 345 369 371 10.1016/S0140-6736(95)90347-X 7772121
7. ICU admission score for predicting morbidity and mortality risk after coronary artery bypass grafting. TL Higgins FG Estafanous FD Loop GJ Beck JC Lee NJ Starr WA Knaus DM Cosgrove III, Ann Thorac Surg 1997 64 1050 1058 10.1016/S0003-4975(97)00553-5 9354526
8. Stratification of morbidity and mortality outcome by preoperative risk factors in coronary artery bypass patients. TL Higgins FG Estafanous FD Loop GJ Beck JM Blum L Paranandi, Jama 1992 267 2344 2348 10.1001/jama.267.17.2344 1564774
9. Intraoperative physiologic variables and outcome in cardiac surgery: Part I. In-Hospital Mortality. GK van Wermeskerken JW Lardenoye SE Hill HP Grocott B Phillips-Bute PK Smith JG Reves MF Newman, Ann Thorac Surg 2000 69 1070 1076 10.1016/S0003-4975(99)01443-5 10800796
10. Intraoperative hemodynamic predictors of mortality, stroke, and myocardial infarction after coronary artery bypass surgery. DL Reich CA Bodian M Krol M Kuroda T Osinski DM Thys, Anesth Analg 1999 89 814 822 10.1097/00000539-199910000-00002 10512249
11. Quantifying risk and assessing outcome in cardiac surgery. TL Higgins, J Cardiothor Vasc Anesth 1998 12 330 340 10.1016/S1053-0770(98)90018-0
12. Effect of changing patient mix on the performance of an intensive care unit severity-of-illness model: How to distinguish a general from a specialty intensive care unit. R Murphy-Filkins D Teres S Lemeshow DW Hosmer, Crit Care Med 1996 24 1968 1973 10.1097/00003246-199612000-00007 8968263
13. Outcome prediction models on admission in a medical intensive care unit: Do they predict individual outcome? JH Schafer A Maurer F Jochimsen C Emde K Wegscheider HR Arntz J Heitz B Krell-Schroeder A Distler, Crit Care Med 1990 18 1111 1117 2209038
14. Predictors of outcome in cardiac surgical patients with prolonged intensive care stay. TA Ryan MY Rady CA Bashour M Leventhal M Lytle NJ Starr, Chest 1997 112 1035 1042 9377914
15. DW Hosmer S Lemeshow, Applied Logistic Regression New York: Wiley 2000
16. Multivariate prediction of in-hospital mortality associated with coronary artery bypass graft surgery. GT O'Connor SK Plume EM Olmstead LH Coffin JR Morton CT Maloney ER Nowicki DG Levy JF Tryzelaar F Hernandez L Adrian KJ Casey D Bundy DN Soule CAS Marrin WC Nugent DC Charlesworth R Clough S Katz BJ Leavitt JE Wennberg, Circulation 1992 85 2110 2118 1591830
17. APACHE II: a severity of disease classification system. WA Knaus EA Draper DP Wagner JE Zimmerman, Crit Care Med 1985 13 818 829 10.1097/00003246-198510000-00009 3928249
18. The APACHE III prognostic system. Risk prediction of hospital mortality for critically ill hospitalised adults. WA Knaus DP Wagner EA Draper JE Zimmerman M Bergner PG Bastos CA Sirio DJ Murphy T Lotring A Damiano, Chest 1991 100 1619 1636 10.1378/chest.100.6.1619 1959406
19. A new Simplified Acute Physiology score (SAPS II) based on a European/North American multicenter study. JR Le Gall S Lemeshow F Saulnier, JAMA 1993 270 2957 2963 10.1001/jama.270.24.2957 8254858
20. Mortality Probability Models (MPMII) based on an international cohort of intensive care unit patients. S Lemeshow D Teres J Klar JS Avrunin SH Gehlbach J Rapoport, JAMA 1993 270 2478 2486 10.1001/jama.270.20.2478 8230626
21. Use of a Bayesian statistical model for risk assessment in coronary artery surgery. FH Edwards RF Peterson C Bridges EL Ceithaml, Ann Thorac Surg 1995 59 1611 1612 10.1016/0003-4975(95)00189-R 7771861
22. Bayesian-logit model for risk assessment in coronary artery bypass grafting. G Marshall ALW Shroyer FL Grover KE Hammermeister, Ann Thorac Surg 1994 57 1492 1500 8010792
23. An evaluation of existing risk stratification models as a tool for comparison of surgical performances for coronary artery bypass grafting between institutions. G Asimakopoulos S Al-Ruzzeh G Ambler RZ Omar P Punjabi M Amrani KM Taylor, Eur J Cardiothorac Surg 2003 23 935 941 10.1016/S1010-7940(03)00165-9 12829069
24. Predicting operative risk for coronary artery surgery in the United Kingdom: a comparison of various risk prediction algorithms. B Bridgewater H Neve N Moat T Hooper M Jones, Heart 1998 79 350 355 9616341
25. Predicting mortality after coronary artery bypass surgery: what do artificial neural networks learn? The Steering Committee of the Cardiac Care Network of Ontario. JV Tu MC Weinstein BJ McNeil CD Naylor, Med Decis Making 1998 18 229 235 9566456
26. Coronary artery bypass risk prediction using neural networks. RP Lippmann DM Shahian, Ann Thorac Surg 1997 63 1635 1643 10.1016/S0003-4975(97)00225-7 9205161
27. An empirical comparison of multivariable methods for estimating risk of death from coronary heart disease. MW Knuiman HT Vu MR Segal, J Cardiovasc Risk 1997 4 127 134 10.1097/00043798-199704000-00009 9304494
28. Assessment of predictive models for binary outcomes: an empirical approach using operative death from cardiac surgery. G Marshall FL Grover WG Henderson KE Hammermeister, Stat Med 1994 13 1501 1511 10.1002/sim.4780131502 7973229
29. Mathematical models and the assessment of performance in cardiology. HM Krumholz, Circulation 1999 99 2067 2069 10217642
30. Cardiac surgery risk modeling for mortality: a review of current practice and suggestions for improvement. RZ Omar G Ambler P Royston J Eliahoo KM Taylor, Ann Thorac Surg 2004 77 2232 2237 10.1016/j.athoracsur.2003.10.032 15172320
31. Risk stratification in heart surgery: comparison of six score systems. HJ Geisser P Holzl S Marohl F Kuhn-Regnier U Mehlhorn M Sudkamp ER De Vivie, Eur J Cardiothorac Surg 2000 17 400 406 10.1016/S1010-7940(00)00385-7 10773562
32. Intra-institutional prediction of outcome after cardiac surgery: comparison between a locally derived model and the EuroSCORE. O Pitkanen M Niskanen S Rehnberg M Hippelainen M Hynynen, Eur J Cardiothorac Surg 2000 18 703 710 10.1016/S1010-7940(00)00579-0 11113679
33. K Fukunaga, Introduction to Statistical Pattern Recognition Boston: Academic Press 1990
34. CM Bishop, Neural Networks for Pattern Recognition New York: Oxford University Press Inc 1995
35. DS Sivia J Skilling, Data Analysis: A Bayesian Tutorial Oxford: Oxford University Press 2006
36. PM Lee, Bayesian Statistics - An Introduction London: Arnold 2004
37. kappa Nearest neighbors QSAR modeling as a variational problem: theory and applications. P Itskowitz A Tropsha, J Chem Inf Model 2005 45 777 785 10.1021/ci049628+ 15921467
38. A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. A Statnikov CF Aliferis I Tsamardinos D Hardin S Levy, Bioinformatics 2005 21 631 643 10.1093/ bioinformatics/bti033 15374862
39. WJ Krzanowski, Principles of Multivariate Analysis: A User's Perspective Oxford: Clarendon Press 1988
40. What price perfection? Calibration and discrimination of clinical prediction models. GA Diamond, J Clin Epidemiol 1992 45 85 89 10.1016/0895-4356(92)90192-P 1738016
41. VN Vapnik, The Nature of Statistical Learning Theory New York: Springer-Verlag 1999
42. Ready-made, recalibrated, or remodeled? Issues in the use of risk indexes for assessing mortality after coronary artery bypass graft surgery. J Ivanov JV Tu CD Naylor, Circulation 1999 99 2098 2104 10217648
43. Comparing risk-adjustment methods for provider profiling. ER DeLong ED Peterson DM DeLong LH Muhlbaier S Hackett DB Mark, Stat Med 1997 16 2645 2664 10.1002/(SICI)1097-0258(19971215)16:23<2645::AID-SIM696>3.0.CO;2-D 9421867
44. Validation and updating of predictive logistic regression models: a study on sample size and shrinkage. EW Steyerberg GJ Borsboom HC van Houwelingen MJ Eijkemans JD Habbema, Stat Med 2004 23 2567 2586 10.1002/sim.1844 15287085
45. Methods for selection of adequate neural network structures with application to early assessment of chest pain patients by biochemical monitoring. J Ellenius T Groth, Int J Med Inform 2000 57 181 202 10.1016/S1386-5056(00)00065-4 10961573
46. Dimensionality and Sample Size Considerations in Pattern Recognition Practice. AK Jain B Chandrasekaran, Handbook of Statistics. Amsterdam, Krishnaiah PR, Kanal LN, 1982
47. Stepwise discriminant analysis. RI Jennrich, Statistical methods for digital computers. New York, Enslein K, Ralston A, Wilf HS, 1977 76 95
48. P Armitage G Berry, Statistical methods in medical research Oxford: Blackwell Scientific Publications 1987
49. The meaning and use of the area under a receiver operating characteristics (ROC) curve. JA Hanley BJ McNeil, Radiology 1982 143 29 36 7063747
50. Areas beneath the relative operating characteristics (ROC) and relative operating levels (ROL) curves: Statistical significance and interpretation. SJ Mason NE Graham, Quarterly Journal of the Royal Meteorological Society 2002 128 2145 2166 10.1256/003590002320603584
51. The use of receiver operating characteristic curves in biomedical informatics. TA Lasko JG Bhagwat KH Zou L Ohno-Machado, J Biomed Inform 2005 38 404 415 10.1016/j.jbi.2005.02.008 16198999
52. The area above the ordinal dominance graph and the area below the receiver operating characteristic graph. DC Bamber, Journal of Mathematical Psychology 1975 12 387 415 10.1016/0022-2496(75)90001-2
53. ROC curves in clinical chemistry: uses, misuses, and possible solutions. NA Obuchowski ML Lieber FH Wians Jr, Clin Chem 2004 50 1118 25 10.1373/clinchem.2004.031823 15142978
54. A new vector partition of the probability score. AH Murphy, J Appl Meteor 1973 12 595 600 10.1175/1520-0450(1973)012<0595:ANVPOT>2.0.CO;2
55. Recalibration of risk prediction models in a large multicenter cohort of admissions to adult, general critical care units in the United Kingdom. DA Harrison AR Brady GJ Parry JR Carpenter K Rowan, Crit Care Med 2006 34 1378 1388 10.1097/01.CCM.0000216702.94014.75 16557153
56. Mortality and other event rates: what do they tell us about performance? JL Moran PJ Solomon, Crit Care Resusc 2003 5 292 304 16563120
57. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. FE Harrell Jr KL Lee DB Mark, Stat Med 1996 15 361 387 10.1002/(SICI)1097-0258(19960229)15: 4<361::AID-SIM168>3.0.CO;2-4 8668867
58. Bayes' theorem - a review. P Schulman, Cardiol Clin 1984 2 319 327 6399868
59. Classification of postoperative cardiac patients: comparative evaluation of four algorithms. E Artioli G Avanzolini P Barbini G Cevenini G Gnudi, Int J Biomed Comput 1991 29 257 270 10.1016/0020-7101(91)90043-E 1778641
60. RO Duda PE Hart DG Stork, Pattern Classification New York: John Wiley and Sons 2001
61. Classification efficiency of multinomial logistic regression relative to ordinal logistic regression. MK Campbell A Donner, J Am Stat Assoc 1989 84 587 591 10.2307/2289946
62. BG Tabachnick LS Fidell, Using Multivariate Statistics New York: Harper Collins 1996
63. GD Friedman, Primer of Epidemiology New York: McGraw Hill 2004
64. On logit confidence intervals for the odds ratio with small samples. A Agresti, Biometrics 1999 55 597 602 10.1111/j.0006-341X.1999.00597.x 11318220
65. BW Silverman, Density Estimation for Statistics and Data Analysis London: Chapman and Hall 1986
66. Statistical downscaling using K-nearest neighbors. S Gangopadhyay M Clark B Rajagopalan, Water Resources Research 2005 41 W02024, 1 23 10.1029/2004WR003444
67. An optimal algorithm for approximate nearest neighbor searching in fixed dimensions. S Arya DM Mount NS Netanyahu R Silverman AY Wu, Journal of the ACM 1998 45 891 923 10.1145/293347.293348
68. Logistic regression for autocorrelated data with application to repeated measures. A Azzalini, Biometrika 1994 81 767 775 10.1093/biomet/81.4.767
69. Logistic regression for correlated binary data. S Le Cessie JC Van Houwelingen, Appl Statist 1994 43 95 108 10.2307/2986114
70. Regression analysis for correlated data. K-Y Liang SL Zeger, Annu Rev Pub Health 1993 14 43 68 10.1146/annurev.pu.14.050193.000355
71. A comparative analysis of predictive models of morbidity in intensive care unit after cardiac surgery - Part II: an illustrative example. G Cevenini E Barbini S Scoletta B Biagioli P Giomarelli P Barbini, BMC Med Inf Dec Mak 2007 7 36 10.1186/1472-6947-7-36