Assisting clinicians in predicting affected livers from patient data using DLAPDL

Main Article Content

Dr. R. MALATHI

Abstract

Liver, biggest organ in the human body, controls most metabolic activities in himans including converting nutrients into food, bile synthesis, protein creation, glucose storage/, processing cleaning the blood, immunological component production, bilirubin clearance etc. Thus, it is an important and crucial body organ, and its maintenance is primary to human health. Liver is overlooked by humans due to their unhealthy lifestyle routines, thus resulting in acute to severe liver problems like LCs (Liver Cancers). Healthcare systems have been using automations in health related decisions where the systems extract relevant information from massive medical datasets using MLTs (Machine Learning Techniques) which assist clinicians in taking accurate and quick choices in terms of illness predictions or diagnosis. This paper proposes an automated diagnostic framework called DLAPDL- (Deep Learning Approach for Prediction of Diseased Liver) based on CNNs (Convolution Neural Networks) to estimate DLs (Diseased Livers) based on medical reports data of patients. In this respect, this paper presents an in-depth examination of predictions of DLs. The proposed approach’s results show higher levels of accuracy in experimentations and evaluations on medical datasets.

Article Details

Section
Articles