Artificial neural networks versus proportional hazards Cox models to predict 45-year all-cause mortality in the Italian Rural Areas of the Seven Countries Study

BMC Medical Research Methodology

Alessandro Menotti¹  Paolo Emilio Puddu² 

[1] Associazione per la Ricerca Cardiologica, Rome, Italy;Laboratory of Biotechnologies Applied to Cardiovascular Medicine, Department of Cardiovascular, Respiratory, Nephrological, Anesthesiological and Geriatrical Sciences, Sapienza, University of Rome, Viale del Policlinico, 155, Rome 00161, Italy

关键词: Seven countries study;    Epidemiology;    45-year follow-up;    All-cause mortality;    Prediction;    Cox models;    Neural networks;   

Others  :  1136526
DOI  :  10.1186/1471-2288-12-100

 received in 2011-10-19, accepted in 2012-06-23,  发布年份 2012

【 授权许可】

   
2012 Puddu and Menotti; licensee BioMed Central Ltd.

【 参考文献 】

• [1]Afifi AA, Clark V: Computer aided multivariate analysis. Van Nostrand Reinhold Co, New York; 1990.
• [2]Miller Ch C III, Reardon MJ, Safi HJ: Risk stratification. University Press, A practical guide for clinicians. Cambridge; 2001.
• [3]Menotti A, Puddu PE, Lanti M: Il rischio in Cardiologia: dalla teoria alla pratica. Edizioni Internazionali srl, Pavia; 2004.
• [4]Friedman JH, Stuetzle RJ: Projection pursuit regression. J Am Stat Assoc 1981, 76:817-823.
• [5]Hornik K, Stinchcomb X, White X: Miltilayer feedforward networks are universal approximators. Neural Net 1989, 2:359-366.
• [6]Friedman JH: Multivariate adaptive regression splines. Ann Stat 1991, 19:1-141.
• [7]Ciampi A, Hogg SA, McKinney S, Thiffault J: RECPAM, a computer program for recursive partition and amalgamation for censored survival data and other situations frequently occurring in biostatistics. I. methods and program features. Comp Meth Progr Biomed 1988, 26:239-256.
• [8]Zhang H: Recursive partitioning and tree-based methods. In Handbook of computational statistics. Edited by Gentle JE, Hardle W, Mori Y. Springer, Berlin; 2004.
• [9]Lee JW, Um SH, Lee JB, Mun J, Cho H: Scoring and staging systems using Cox linear regression modeling and recursive partitioning. Meth Inform Med 2006, 45:37-43.
• [10]Delen D, Oztekin A, Kong ZJ: A machine learning-based approach to prognostic analysis of thoracic transplantations. Artif Intel Med 2010, 49:33-42.
• [11]Tu JV: Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 1996, 49:1225-1231.
• [12]Dayhoff JE, DeLeo JM: Artificial neural networks. Opening the black box. Cancer 2001, 91:1615-1635.
• [13]Hosmer DW, Lemeshow S: Applied logistic regression. 2nd edition. John Wiley and Sons, New York; 2000.
• [14]Hanley JA, McNeil BJ: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982, 143:29-36.
• [15]Zweig MH, Campbell G: Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin Chem 1993, 39:561-577.
• [16]Obuchowski NA: Receiver operating characteristic curves and their use in radiology. Radiology 2003, 229:3-8.
• [17]Pepe MS: The statistical evaluation of medical tests for classification and prediction. Oxford University Press, New York; 2003.
• [18]Hanley JA, McNeil BJ: A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology 1983, 148:839-843.
• [19]DeLong ER, DeLong DM, Clarke-Pearson DL: Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988, 44:837-845.
• [20]Bandos AI, Rockette HE, Gur D: A conditional nonparametric test for comparing two areas under the ROC curves from paired design. Acad Radiol 2005, 12:291-297.
• [21]Hense HW: Observations, predictions and decisions assessing cardiovascular risk assessment. Int J Epidemiol 2004, 33:235-239.
• [22]Shahian DM, Blackstone EH, Edwards FH, Grover FL, Grunkemeier GL, Naftel DC, Nashef SAM, Nugent WC, Peterson ED: Cardiac surgery risk models: a position article. Ann Thorac Surg 2004, 78:1868-1877.
• [23]Warner BA: Thoughts and considerations on modelling coronary bypass surgery risk. Ann Thorac Surg 1997, 63:1529-1530.
• [24]Orr RK: Use of a probabilistic neural network to estimate the risk of mortality after surgery. Med Decis Making 1997, 17:178-185.
• [25]Altman DG: Categorizing continuous variables. Br J Cancer 1991, 64:975.
• [26]Lippmann RP, Shahian DM: Coronary artery bypass risk prediction using neural networks. Ann Thorac Surg 1997, 63:1635-1643.
• [27]Nilsson J, Ohlsson M, Thulin L, Höglund P, Nashef SAM, Brandt J: Risk factor identification and mortality prediction in cardiac surgery using artificial neural networks. J Thorac Cardiovasc Surg 2006, 132:12-19.
• [28]Voss R, Cullen P, Schulte H, Assmann G: Prediction of risk of coronary events in middle-aged men in the prospective cardiovascular Münster study (PROCAM) using neural networks. Int J Epidemiol 2002, 31:1253-1262.
• [29]Puddu PE, Menotti A: Artificial neural network versus multiple logistic function to predict 25-year coronary heart disease mortality in the Seven Countries Study. Eur J Cardiovasc Prev Rehabil 2009, 16:583-591.
• [30]May M: Commentary: improved coronary risk prediction using neural networks. Int J Epidemiol 2002, 31:1262-1263.
• [31]Menotti A, Lanti M, Maiani G, Kromhout D: Determinants of longevity and all-cause mortality among middle-aged men. Role of 48 personal characteristics in a 40-year follow-up of Italian Rural Areas in the Seven Countries Study. Aging Clin Exp Res 2006, 18:394-406.
• [32]Keys A, Blackburn H, Menotti A, Buzina R, Mohacek I, Karvonen MJ, Punsar S, Aravanis C, Corcondilas A, Dontas AS, Lekos D, Fidanza F, Puddu V, Taylor HL, Monti M, Kimura N, Van Buchem FSP, Djordjevic BS, Strasser T, Anderson JT, Den Hartog C, Pekkarinen M, Roine P, Sdrin H: Coronary heart disease in seven countries. Circulation 1970, 41(suppl 1):1-211.
• [33]Anderson JT, Keys A: Cholesterol in serum and lipoprotein fractions: its measurement and stability. Clin Chem 1956, 2:145-159.
• [34]Rose G, Blackburn H: Cardiovascular survey methods. World Health Organization, Geneva; 1968.
• [35]Gini C: Measurement of inequality of incomes. Econ J 1921, 31:124-126.
• [36]Cox DR: Regression models and life tables. J Roy Stat Soc 1972, B43:185-220.
• [37]White H: Learning in artificial neural networks: a statistical perspective. Neural Comput 1989, 1:425-464.
• [38]Liestol K, Andersen PK, Andersen U: Survival analysis and neural nets. Stat Med 1994, 13:1189-1200.
• [39]Keys A, Aravanis C, Blackburn H, Buzina R, Djordjevic BS, Dontas AS, Fidanza F, Karvonen MJ, Kimura N, Menotti A, Mohacek I, Nedeljkovic S, Puddu V, Punsar S, Taylor HL, Van Buchem F: Seven Countries Study. In A multivariate analysis of death and coronary heart disease. Edited by Keys A. Harvard Univ Press, Cambridge, Mass; 1980.
• [40]Puddu PE, Brancaccio G, Leacche M, Monti F, Lanti M, Menotti A, Gaudio C, Papalia U, Marino B, OP-RISK Study Group: Prediction of early and delayed postoperative deaths after coronary artery bypass surgery in Italy. Multivariate prediction based on Cox and logistic models and a chart based on the accelerated failure time model. Ital Heart J 2002, 3:166-181.
• [41]Sciangula A, Puddu PE, Schiariti M, Acconcia MC, Missiroli B, Papalia U, Gaudio C, Martinelli G, Cassese M: Comparative application of multivariate models developed in Italy and Europe to predict early (28 days) and late (1 year) postoperative death after on- or off-pump coronary artery bypass grafting. Heart Surg Forum 2007, 10:E258-E266.
• [42]Puddu PE, Menotti A, Tolonen H, Nedeljkovic S, Kafatos A: Determinants of 40-year all-cause mortality in the European cohorts of the Seven Countries Study. Eur J Epidemiol 2011, 26:595-608. 8
• [43]Lim T-S, Loh W-Y, Shih Y-S: A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms. Machine Learn 2000, 40:203-228.
• [44]Wolfe R, McKenzie DP, Black J, Simpson P, Gabbe BJ, Cameron PA: Models developed by three techniques did not achieve acceptable prediction of binary trauma outcomes. J Clin Epidemiol 2006, 59:26-35.
• [45]Austin PC: A comparison of regression trees, logistic regression, generalized additive models, and multivariate adaptive regression splines for predicting AMI mortality. Stat Med 2007, 26:2937-2957.
• [46]Austin PC, Tu JV, Lee DS: Logistic regression had superior performance compared with regression trees for predicting in-hospital mortality in patients hospitalized with heart failure. J Clin Epidemiol 2010, 63:1145-1155.
• [47]Anderson KM, Castelli WP, Levy D: Cholesterol and mortality. 30 years of follow-up from the Framingham study. JAMA 1987, 257:2176-2180.
• [48]Ferrie JE, Singh-Manoux A, Kivimäki M, Mindell J, Breeze E, Smith GD, Shipley MJ: Cardiorespiratory risk factors as predictors of 40-year mortality in women and men. Heart 2009, 95:1250-1257.
• [49]Goto A, Yasumura S, Nishise Y, Sakihara S: Association of health behavior and social role with total mortality among Japanese elders in Okinawa, Japan. Aging Clin Exp Res 2003, 15:443-450.