A Study of Support Vector Machine Algorithm for Liver Disease Diagnosis

摘要

Patients with liver disease have been continuously increasing because of excessive consumption of alcohol, inhale of harmful gases, intake of contaminated food, pickles and drugs. The liver has many essential functions, and liver disease presents a number of concerns for the delivery of medical care. Chronic liver disease (CLD) is common long-term conditions in the developed and developing world. Classification techniques are very popular in various automatic medical diagnosis tools. Early identification of the cancer has been often vital for the survival of the patients. Support vector machine (SVM) is supervised learning model with associated learning algorithms that analyze data and recognize patterns. In this work, Support vector machine is used for classifying liver disease using two liver patients datasets with different features combinations such as SGOT, SGPT and Alkaline Phosphates, evaluating a support vector machine classifier by measuring its performance based on: accuracy, error rate, sensitivity, prevalence and specificity. Results show that the accuracy, error rate, sensitivity and prevalence at first 6ordered features are the best for ILPD dataset compared to BUPA dataset. This can be attributed to a number of useful attributes like Total bilirubin, direct bilirubin, Albumin, Gender, Age and Total proteins are available in the ILPD liver dataset compared to the BUPA dataset which can help in diagnosis of liver disease.