Fatty liver disease prediction: Using machine learning algorithms
Publication Name
Predictive Data Modelling for Biomedical Data and Imaging
Abstract
It has been seen that a lot of individuals nowadays are struggling with a variety of health problems. Even an infant, upon entering this world, might be subjected to the ravages of several illnesses. The prevalence of liver disease is rising faster than that of any other illness. The liver is the biggest organ located inside the human body. It assists in the digestion of meals, the storage of energy, and the elimination of toxins from the body. A condition known as fatty liver disease (FLD) occurs when there is an accumulation of fat in the liver. Every technological advancement that gives more accurate, timely, and useful analysis to provide an appropriate treatment plan in a timely manner is of immense value. At this very moment, ML is rapidly becoming the dominant force in the globe. The usage of the enormous potential offered by ML has the potential to be of help to the medical industry in several different ways. Technology based on ML enables medical practitioners to more accurately produce medication solutions that are suited to the features of specific patients. With this aim, this chapter presents several different ML algorithms, namely logistic regression, decision tree classifier, random forest classifier, KNN classifier, CatBoost classifier, and gradient boosting classifier, to perform the prediction of fatty liver diseases. This study analyzed these ML models for their degree of accuracy by using the dataset of Indian patients. ML classifiers might assist medical organizations identify and classify FLD proactively, which is important in impoverished economies.
Open Access Status
This publication is not available as open access
First Page
279
Last Page
294