Neural Network Assessment of Perioperative Cardiac Risk in Vascular Surgery Patients

Neural networks were developed to predict perioperative cardiac complications with data from 567 vascular surgery patients. Neural network scores were based on cardiac risk factors and dipyridamole thallium results. These scores were converted into like lihood ratios that predicted cardiac risk. The prognostic accuracy of the neural networks was similar to that of logistic regression models (ROC areas 76.0% vs 75.8%), but their calibration was better. Logistic regression overestimated event rates in a group of high-risk patients (predicted event rate, 64%; observed rate 30%; n = 50, p < 0.001). On a validation set of 514 patients, the neural networks still had ROC similar areas to those of logistic regression (68.3% vs 67.5%), but logistic regression again overesti mated event rates for a group of high-risk patients. The calibration difference was reflected in the Hosmer-Lemeshow chi-square statistic (18.6 for the neural networks, 45.0 for logistic regression). The neural networks successfully estimated perioperative cardiac risk with better calibration than comparable logistic regression models. Key words. neural networks; logistic regression; likelihood ratio; Bayes' theorem; cardiac risk. (Med Decis Making 1998;18:70-75)

[1]  S. Fiske,et al.  The Handbook of Social Psychology , 1935 .

[2]  M. R. Mickey,et al.  Estimation of Error Rates in Discriminant Analysis , 1968 .

[3]  D. Hosmer,et al.  Goodness of fit tests for the multiple logistic regression model , 1980 .

[4]  A. Albert,et al.  On the use and computation of likelihood ratios in clinical chemistry. , 1982, Clinical chemistry.

[5]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[6]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  D. Singer,et al.  Dipyridamole-thallium scanning in patients undergoing vascular surgery. Optimizing preoperative evaluation of cardiac risk. , 1987, JAMA.

[9]  B. S. Cutler.  Dipyridamole-thallium scanning in patients undergoing vascular surgery: optimizing preoperative evaluation of cardiac risk: Eagle KA, Singer DE, Brewster DC, et al. JAMA 1987; 257: 2185-9 , 1987 .

[10]  T. Riles,et al.  The value of silent myocardial ischemia monitoring in the prediction of perioperative myocardial infarction in patients undergoing peripheral vascular surgery. , 1989, Journal of vascular surgery.

[11]  C. Coley,et al.  Combining clinical and thallium data optimizes preoperative assessment of cardiac risk before major vascular surgery , 1989 .

[12]  J. Calvin,et al.  A comparison of dipyridamole-thallium imaging and exercise testing in the prediction of postoperative cardiac complications in patients requiring arterial reconstruction. , 1989, Journal of vascular surgery.

[13]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[14]  W. Baxt.  Use of an artificial neural network for the diagnosis of myocardial infarction. , 1991, Annals of internal medicine.

[15]  J. Tu,et al.  Use of a neural network as a predictive instrument for length of stay in the intensive care unit following cardiac surgery. , 1993, Computers and biomedical research, an international journal.

[16]  M. Rubenfire,et al.  Neural network in the clinical diagnosis of acute pulmonary embolism. , 1993, Chest.

[17]  M. Ebell.  Artificial neural networks for predicting failure to survive following in-hospital cardiopulmonary resuscitation. , 1993, The Journal of family practice.

[18]  Timothy Masters,et al.  Probabilistic Neural Networks , 1993 .

[19]  Bruce W. Colletti,et al.  Artificial intelligence versus logistic regression statistical modelling to predict cardiac complications after noncardiac surgery , 1994, Clinical Cardiology.

[20]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[21]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[22]  R. Dybowski,et al.  Artificial neural networks in pathology and medical laboratories , 1995, The Lancet.

[23]  G. L’italien,et al.  Sex differences in perioperative and long-term cardiac event-free survival in vascular surgery patients. An analysis of clinical and scintigraphic variables. , 1995, Circulation.

[24]  R. Rutledge,et al.  Injury severity and probability of survival assessment in trauma patients using a predictive hierarchical network model derived from ICD-9 codes. , 1995, The Journal of trauma.

[25]  K A Eagle,et al.  Development and validation of a Bayesian model for perioperative cardiac risk assessment in a cohort of 1,081 vascular surgical candidates. , 1996, Journal of the American College of Cardiology.