How Well Does a Sequential Minimal Optimization Model Perform in Predicting Medicine Prices for Procurement System?

Abstract

The lack of an efficient approach in managing pharmaceutical prices in the procurement system led to a substantial burden on government budgets. In Thailand, although the reference price policy was implemented to contain the drug expenditure, there have been some challenges with the price dispersion of medicines and pricing information transparency. This phenomenon calls for the development of a potential algorithm to estimate appropriate prices for medical products. To serve this purpose, in this paper, we first developed the model by the sequential minimal optimization (SMO) algorithm for predicting the range of the prices for each medicine, using the Waikato environment for knowledge analysis software, and applying feature selection techniques also to examine improving predictive accuracy. We used the dataset comprised of 2424 records listed on the procurement system in Thailand from January to March 2019 in the application and used a 10-fold cross-validation test to validate the model. The results demonstrated that the model derived by the SMO algorithm with the gain ratio selection method provided good performance at an accuracy of approximately 92.62%, with high sensitivity and precision. Additionally, we found that the model can distinguish the differences in the prices of medicines in the pharmaceutical market by using eight major features—the segmented buyers, the generic product groups, trade product names, procurement methods, dosage forms, pack sizes, manufacturers, and total purchase budgets—that provided the highest predictive accuracy. Our findings are useful to health policymakers who could employ our proposed model in monitoring the situation of medicine prices and providing feedback directly to suggest the best possible price for hospital purchasing managers based on the feature inputs in their procurement system.