Postoperative vomiting in pediatric oncologic patients: prediction by a fuzzy logic model

Objective To report a fuzzy logic mathematical model to predict postoperative vomiting (POV) in pediatric oncologic patients and compare with preexisting scores. Background Although POV has a high incidence in children and may decrease parental satisfaction after surgeries, there is only one specific score that predicts POV in children: the Eberhart's score. In this study, we report a fuzzy model that intends to predict the probability of POV in pediatric oncologic patients. Fuzzy logic is a mathematical theory that recognizes more than simple true and false values and takes into account levels of continuous variables such as age or duration of the surgery. The fuzzy model tries to account for subjectiveness in the variables. Methods Preoperative potential risk factors for POV in 198 children (019year old) with malignancies were collected and analyzed. Data analysis was performed with the chi-square test and logistic regression to evaluate probable risk factors for POV. A system based on fuzzy logic was developed with the risk factors found in the logistic regression, and a computational interface was created to calculate the probability of POV. Results The model showed a good performance in predicting POV. After the analysis, the model was compared with Eberhart's score in the same population and showed a better performance. Conclusions The fuzzy score can predict the chance of POV in children with cancer with good accuracy, allowing better planning for postoperative prophylaxis of vomiting. The computational interface is available for free download at the internet and is very easy to use.