An Ensemble based technique (EARLNP) for recommendations of Lupus activity in Humans from kidney datasets

Main Article Content



Global healthcare systems are perfect examples of digital technology evolutions. These systems analyze large amounts of patient data for deriving insights and assisting clinicians in prediction of diseases. Automated health recommenders are becoming popular in healthcare where intelligent systems have significant importance in their capability to aid decision making processes about illnesses. The recommender system using patient's lifestyles or physical health records forecast health issues including the presence of LNs (Lupus Nephritis ), a severe form of SLE (Systemic Lupus Erythematosus) which caused by immune complex deposits in human kidneys. In their acute phases, they cause substantial injuries and nephron losses and when not treated adequately, kidneys turn into chronic or irreversibly damaged.Though therapies for handling LNs have improved, it is imperative for systems which predict consensual outcomes. Hence, the main objective of this paper is to propose a non-invasive health recommender technique called EARLNAP, an ensemble technique for implementations in kidneys malfunctioning recommender systems. The results of this system are favorable in terms of its performances and performance metrics.

Article Details