This paper is published in Volume-7, Issue-6, 2022
Area
Machine Learning
Author
Sussma S., Srivignesh S., Kishore V. S., Dr. M. Marimuthu
Org/Univ
Coimbatore Institute of Technology, Coimbatore, Tamil Nadu, India
Pub. Date
06 January, 2022
Paper ID
V7I6-1394
Publisher
Keywords
Bilirubin, Jaundice, Prediction, Supervised Learning, Predictive Analytics

Citationsacebook

IEEE
Sussma S., Srivignesh S., Kishore V. S., Dr. M. Marimuthu. Jaundice prediction using Machine Learning approach, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Sussma S., Srivignesh S., Kishore V. S., Dr. M. Marimuthu (2022). Jaundice prediction using Machine Learning approach. International Journal of Advance Research, Ideas and Innovations in Technology, 7(6) www.IJARIIT.com.

MLA
Sussma S., Srivignesh S., Kishore V. S., Dr. M. Marimuthu. "Jaundice prediction using Machine Learning approach." International Journal of Advance Research, Ideas and Innovations in Technology 7.6 (2022). www.IJARIIT.com.

Abstract

Jaundice occurs when the rise in the level of bilirubin causes the skin, mucus membrane, and white part of the eyes to appear yellowish. bilirubin is a reddish-yellow substance produced when red blood cells break down.it is excreted through the liver. the bilirubin level will rise up when an abnormally high level of red blood cells breaks down. Any person with liver disease develops jaundice (i.e) when the liver does metabolize bilirubin the way it’s supposed to do, jaundice is developed. Depending on the underlying cause of jaundice, treatment will be provided. If it is caused by viral hepatitis, it will recover on its own. If the cause is because of other infections, diagnosing will be the appropriate treatment. The objective of this work is to develop the most efficient model for any medical lab to predict jaundice. Any data containing relevant factors to jaundice can be used in this model. The standard dataset is collected containing the components age, gender, total bilirubin, direct bilirubin, total protein level, albumin, sgpt, sgot and etc. Principal component analysis and factor analysis are performed to identify the useful and important factors which help to determine jaundice. Supervised learning models such as random forest, decision tree, support vector machines, naive Bayes classifier, and other models are used to train the dataset to predict jaundice with better accuracy.