A multivariate Bayesian model for assessing morbidity after coronary artery surgery

Abstract

IntroductionAlthough most risk-stratification scores are derived from preoperative patient variables, there are several intraoperative and postoperative variables that can influence prognosis. Higgins and colleagues previously evaluated the contribution of preoperative, intraoperative and postoperative predictors to the outcome. We developed a Bayes linear model to discriminate morbidity risk after coronary artery bypass grafting and compared it with three different score models: the Higgins' original scoring system, derived from the patient's status on admission to the intensive care unit (ICU), and two models designed and customized to our patient population.MethodsWe analyzed 88 operative risk factors; 1,090 consecutive adult patients who underwent coronary artery bypass grafting were studied. Training and testing data sets of 740 patients and 350 patients, respectively, were used. A stepwise approach enabled selection of an optimal subset of predictor variables. Model discrimination was assessed by receiver operating characteristic (ROC) curves, whereas calibration was measured using the Hosmer-Lemeshow goodness-of-fit test.ResultsA set of 12 preoperative, intraoperative and postoperative predictor variables was identified for the Bayes linear model. Bayes and locally customized score models fitted according to the Hosmer-Lemeshow test. However, the comparison between the areas under the ROC curve proved that the Bayes linear classifier had a significantly higher discrimination capacity than the score models. Calibration and discrimination were both much worse with Higgins' original scoring system.ConclusionMost prediction rules use sequential numerical risk scoring to quantify prognosis and are an advanced form of audit. Score models are very attractive tools because their application in routine clinical practice is simple. If locally customized, they also predict patient morbidity in an acceptable manner. The Bayesian model seems to be a feasible alternative. It has better discrimination and can be tailored more easily to individual institutions.

Algorithms to Estimate PaCO2and pH Using Noninvasive Parameters for Children with Hypoxemic Respiratory Failure

“…However, machine-learning techniques have been used extensively in medicine, 21 in gene expression studies, [22][23][24] for classification of cardiac arrhythmias, 25 for predicting morbidity after coronary artery bypass surgery, 26 and for predicting when weaning from ventilator support should begin. 27 Gaussian processes have been applied in adults with ALI to model the pressure-volume curve to titrate PEEP.…”

Risk Models That Use Postoperative Patient Monitoring Data to Predict Outcomes in Adult Cardiac Surgery: A Systematic Review

“…In 2006 Biagioli et al produced a risk model for cardiac surgery using a Bayes linear approach. [42] The authors trained their model to predict morbidity using data for a range of predictor variables taken from a group of 740 patients undergoing CABG surgery. The final model included pre-and intraoperative data combined with white cell count and oxygen delivery index measured within 3 hours of ICU admission.…”

Surgical process modelling: a review

“…The correlation of SPMs with other information, such as patient-specific models, is an important prospect in the field. Patient-specific models are constructed from pre and post-operative patient data such as clinical data or images (Edwards et al, 1995;Biagioli et al, 2006;Verduijn et al, 2007;Kuhan et al, 2002). Being able to correlate patient outcomes and pre-operative data with SPM would allow predictions to be made of the best possible surgical processes.…”