Local analgesia adverse effects prediction using multi-label classification

It is desirable to determine minimal effective initial local anesthetic bolus required to provide satisfactory analgesia following surgery. A way to predict potential adverse effects based on the type of anesthetic and initial bolus amount administered would be a significant contribution to presonalized medicine. In this work, we propose new methods for multi-label classification to predict adverse effects in order to help doctors make appropriate treatment decisions. In this endeavor, the Pair-Dependency Multi-Label Bayesian Classifier (PDMLBC) and Complete-Dependency Multi-Label Bayesian Classifier (CDMLBC) models are proposed as classifiers that take into account the impact of features on the dependency between labels. We evaluated the proposed models on 36 patients who had recently received arthroscopic shoulder surgery. The experimental results show that the CDMLBC model outperforms other existing methods in multi-label classification. (c) 2012 Elsevier B.V. All rights reserved.