AI-based recommendation model for effective decision to maximise ROI

Abstract

Healthcare researchers have recently concentrated their efforts on new medication development methodologies that draw on existing pharmacological data. Even while drug–gene interactions are uncommon, a major danger is that medications will have an unexpected/unintended interaction with off-target proteins, resulting in side effects. There are a number of strategies for predicting drug interactions, but many of them require inputs like drug targets, which are hard to come by. In order to better understand drug interactions and to perform drug recommendations based on the analysis, particularly DDIs, several computational tools have been created. In addition to the possibility of DDI occurrence, these methods do not provide enough specifics, and they typically necessitate comprehensive pharmacological information that is not readily available for DDI prediction. Several academic areas have exceptional progress with deep learning during the last decade. Deep learning has emerged as a viable and successful technique for working with biological and chemical data due to its ability to learn at higher levels of abstraction. Deep learning techniques have been used to increase the accuracy of predicting DDI, and the results are encouraging. In the proposed model, an Interactive Drug Recommendation Model using Deep Learning Approach with Drug Data Analysis (IDR-DLA-DDA), several drugs are analysed and then drug recom mendation is performed to the end users based on the analysis. The proposed model suggests suitable drugs to the end users. The proposed model is contrasted with the existing models, and the results represent that the proposed model is efficient in recommending a suitable drug.