Predicting the pharmaceutical needs of hospitals using machine learning algorithms

People’s lives are always threatened by various diseases. The role of health and medical services, in particular medicine, is undeniable in protecting their lives. Timely preparation and providing medicine for patients is vital since medicine shortage can endanger their lives while excessive accumulation of medicine can put them at expiration risk and waste health budgets. To this end, in this paper, we aim at introducing a model for the prediction of commonly used medicine (type and amount) in hospitals. For that, in our applied research, we initially used patients’ data from the Afzalipur Hospital in Kerman collected for 3 years consisting of 283 features, which included over 9351 different medicine and 121,690 patients. Then, nine features were selected using experts’ feedback and were fed into the random forest and neural network algorithms. For the prediction task, medicine types and their amounts were predicted for each individual using different training sets. In addition, the right prediction time was also found which is when predictions have a promising accuracy while the executive team of a hospital has enough time to provide the right amounts of the most used medicine. The performance of algorithms was evaluated using a confusion matrix (precision, recall, F1, and accuracy metrics). Our results showed that the random forest had a promising performance in predicting the amounts of the most used medicine for a month using 2 years of data (accuracy 83.3%) while its accuracy in predicting medicine was 35.9%. Therefore, we conclude that the random forest algorithm has the potential to effectively and accurately predict medicine amounts by analyzing large amounts of data and detecting patterns that may not be easily discernible to humans.