Digitization of Prior Authorization in Healthcare Management using Machine Learning

Abstract

Prior Authorization is the widely used process by Health Insurance companies in United States before they agree to cover prescribed medication under Medical Insurance. However traditional approach includes long length paper works, leading patients getting delayed in getting their claim processed. This delay may deteriorate patient’s medical condition. Also due to man made errors there is a chance of incorrect decision making process on the claims. On the other hand, physicians are losing their time in getting their prescribed medication approved. It is essential to reduce the wait time of patients and tedious work of physicians for healthcare to be effective. This demands advanced technology which can aid in boosting the decision making process of prior authorization methodology. The aim of this work is to digitize the prior authorization process by implementing classification algorithms which can classify the prior authorization applications into Accepted/Rejected/Partially Accepted classes. Proposed a web application which inputs prior authorization claim details and outputs the predicted class of the claim. Analyzed and collected significant features by implementing Feature selection. Developed classification models using Artificial Neural Networks, Random Forest. Implemented model validation techniques to evaluate classifiers performance. From the research findings Generic medication cost, type of Health insurance plan, Addictive nature and side effects of the prescribed drug, patient physical qualities like Age/Gender/Current Medical condition are the significant attributes that impact the decision making process in prior authorization process. Then implemented classifiers exhibited accurate performance on the Train and Test data. Amongst Artificial Neural Networks portrayed the more accuracy. Further analyzed confusion matrix for developed models. In addition to that performed k-fold cross validation and availed performance evaluation metrics to validate the model performance. Ameliorated Healthcare by removing time, location barriers in Prior Authorization process while ensuring patients get quality and economical medication. The proposed web application with machine learning predictive model as backend, automates the prior authorization process by classifying the applications in few seconds.