Abstract
Patient-controlled epidural analgesia (PCEA) has been applied to reduce postoperative pain in orthopedic surgical patients. Unfortunately, PCEA is occasionally accompanied by nausea and vomiting. The logistic regression (LR) model is widely used to predict vomiting, and recently support vector machines (SVM), a supervised machine learning method, has been used for classification and prediction. Unlike our previous work which compared Artificial Neural Networks (ANNs) with LR, this study uses a SVM-based predictive model to identify patients with high risk of vomiting during PCEA and comparing results with those derived from the LR-based model. From January to March 2007, data from 195 patients undergoing PCEA following orthopedic surgery were applied to develop two predictive models. 75% of the data were randomly selected for training, while the remainder was used for testing to validate predictive performance. The area under curve (AUC) was measured using the Receiver Operating Characteristic curve (ROC). The area under ROC curves of LR and SVM models were 0.734 and 0.929, respectively. A computer-based predictive model can be used to identify those who are at high risk for vomiting after PCEA, allowing for patient-specific therapeutic intervention or the use of alternative analgesic methods.
Highlights
Diagnosis, outcome prediction, and signal processing[8,9,10]
The analyses are based on retrospectively collected data of 195 patients (91 men and 104 women) who were classified into vomiting and non-vomiting groups according to their response to patient-controlled epidural analgesia (PCEA)
The results indicate that the Support Vector Machine (SVM) models have better discriminating power than the Logistic Regression (LR) model to identify patients with a high risk for vomiting during PCEA after orthopedic surgery
Summary
No previous studies have applied SVM to investigate PONV, for PCEA cases. We suspect that SVM could prove to be a more powerful method for predicting PONV for orthopedic patients using PCEA. We designed a retrospective study to construct an effective predictive model for PONV with high sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The proposed prediction model for PCEA could potentially be used to adjust the background agent and infusion rate of PCEA in response to individual patient conditions to prevent PONV. The predictive model could be used to identify patients who are at high risk of vomiting after PCEA, allowing for early intervention to reducing potential discomfort and anxiety while increasing patient satisfaction. We compared the predictive performance of the SVM model with that of a model constructed using logistic regression
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have