Performance Evaluation of Machine Learning Algorithms to Predict the Medication Prescription Errors in Intensive Care Units

Medication error can be considered as one of the major issues in healthcare. Critical care unit is considered as the most crucial unit where medication errors if occurred can be dangerous at the cost of life of a patient. Artificial intelligence has the capacity to significantly reduce prescription errors by helping to identify potential mistakes before they take place. This study is an attempt to compare and choose a machine learning algorithm for the machine learning model that will help the doctors and clinicians working in the intensive care unit to reduce the prescription errors in intensive care unit. In this study machine learning classification techniques have been applied to choose the best machine learning algorithm for the problem of predicting the prescription errors in intensive care unit. The result shows that K Nearest Neighbors (KNN) shows the best accuracy (99.13 %).