A Hybrid Approach for Prediction and Stage Wise Classification of Liver Failure K.Prakash Dr. S.Saradha, Research Scholar Assistant Professor Department of Computer Science Department of Computer Science Vel’s Institute of Science, Technology Vel’s Institute of Science, Technology & Advanced Studies(VISTAS) & Advanced Studies(VISTAS) Pallavaram, Chennai, Tamil Nadu.Indi a Pallavaram, Chennai, Tamil Nadu,Indi a prakash.researchscholar23@gmail.com saradha.research@gmail.com Abstract— Early stage disease prediction is an important research area in health sector and it used to helpful to give the required treatment on time. The different stages of liver failure classification are an import research to the society due to huge amount liver failure causes. The early stage of cirrhosis failure prediction reduces the risk of human life. In this research article we propose deep learning based techniques for prediction and classification using fatty liver. The new propose work is the combination of ensemble learning (EL), conventional neural network (CN) and belief neural network. So, the proposed method is called EL-CN. The EL used to predict the features and add the different features using combing all the features. The CNN is used to manage and classify the stage wise prediction and classification. The BNN is increase the accuracy and prediction rates with supporting features. The propose work EL-CN implemented using liver datasets. The liver dataset consists of MRI images and corresponding features. The propose work implemented using python programming language and used different metrics such as accuracy, specificity and sensitivity. Predicted outcomes evaluated with dominant existing works and produced better results in terms of metrics rates such as 98.8% , 98.6% , and 98.4% respectively. Keywords: Liver Failure – Classification and Prediction- Ensemble learning - CNN – BNN 1.I NTRO DUC TIO N Early disease diagnosis and prediction are essential to safeguarding and danger to human life. The injured and damaged liver lead to human healthy life and it affect the lifespan of human. The classifications of liver disorder classification are, such as cirrhosis, hepatitis, fatty liver, liver cancer, and liver tumors. The usage of harmful chemicals and alcohol both contributed to the hepatitis' growth. Hepatic cirrhosis, often known as liver cirrhosis, is the final stage of liver disease. The functionality of the liver is hampered by the development of fibrosis. The causes of cirrhosis are hepatitis and chronic alcoholism. Another reason for cirrhosis is problems of alcohol and other drug consumption. Alcohol-free behavior makes the liver obese. Cirrhosis symptoms include fatigue, easy bleeding, weight loss, itchy skin, and others. [1]. Various stages of liver function and liver failure made up of inflammation, cirrhosis, fibrosis, end-stage liver disease (ESLD), and finally affect liver cancer. The common factor that binds all human existence is cirrhosis. Early detection and classification of cirrhosis are critical for preventing the thread of life. The starting stages of non-alcoholic fatty liver disease were identified and predicted in this study (NAFLD). MRI and CT scans were used to assess and identify the final liver failure. In comparison of CT images and MRI dataset produced effective classification and prediction results since CT scans displayed less visibility. This study, used MRI scans images for classification and prediction and classification using variety of techniques, including data analysis, data mining, and artificial intelligence techniques, are used to early stage classification and prediction of cirrhosis [2–3]. Machine and deep learning are two subcategories of artificial intelligence. Many researchers have already presented numerous machine learning and deep learning-based methodologies. We proposed a deep learning-based mechanism in this work [3-5]. When it comes to categorization and prediction, deep and machine learning are effective compared to the previous data mining techniques. The different machine learning algorithms are nearest neighborhood, SVM, neural network, and ensemble learning algorithms are help to classify and predict unhealthy cirrhosis. Machine learning techniques support to classification and prediction is one of its main advantages, albeit prediction and classification accuracy could be increased. Deep learning, however, generates better categorization and accuracy because it employs several layers. The contribution of the proposed work as follows: Proceedings of the Seventh International Conference on Communication and Electronics Systems (ICCES 2022) IEEE Xplore Part Number: CFP22AWO-ART; ISBN: 978-1-6654-9634-6 978-1-6654-9634-6/22/$31.00 ©2022 IEEE 1679 2022 7th International Conference on Communication and Electronics Systems (ICCES) | 978-1-6654-9634-6/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICCES54183.2022.9835913 Authorized licensed use limited to: SRM University. Downloaded on November 10,2022 at 09:12:54 UTC from IEEE Xplore. Restrictions apply.