Hepatic Disease Detector
My fascination for machine learning apparently never seems to fade away and here I am with another app related to disease detection in machine learning. I created this and the last web app together after discovering both those datasets and successfully deployed both of them. This app is a hepatic disease detector and detects if you have a liver disease using machine learning.
This web app predicts if you have Hepatitis, Fibrosis, Cirrhosis or no hepatic disease based upon a number of parameters such as age, Albumin, Alkaline Phosphate, Alanine Aminotransferase, Aspartate Aminotransferase, Bilirubin, Serum Cholinesterase, Cholestrol, Creatinine, Gamma-Glutamyl Transferase and Prothrombin. I will explain the meaning of these terms as you read through the article. This web app works on the random forest classifier algorithm and is coded majorly in python.
We have deployed the app using Streamlit. It is an open source framework that allows data science teams to deploy web apps fairly easily. It's one of the best hosting services I've used and it's great for quick and easy deployment of web apps. The app is coded in python.
The web app uses interactive visual and graphical interpretations to display the outcome and compare the input parameters given by the user. The sidebar sliders help in changing the values of the parameters for determination of the result. The graphs compare the values of the patient with others ( both with hepatic disease and non-hepatic disease patients). It also provides the accuracy of the result which is greater than 90%.
A value of 0 on the graph indicates that the patient has no hepatic diseases, a value of 1 indicates that he/she has hepatitis, a value of 2 indicates that he/she has fibrosis and a value of 3 indicates that he/she has cirrhosis. This web app was a learning curve for us and has improved our knowledge about Machine learning significantly. We hope to deploy more apps in the future and share them with you. Feel free to add onto this project and don't hesitate to drop by any suggestions. The link for the diabetes detector web app is as follows : https://share.streamlit.io/braxtonova/hepatitis/main/app.py
About this dataset: This dataset was donated by G.Gong of Carnegie Mellon University via Bojan Cestnik of Jozef Stefan Institute, Slovenia. The parameters include Albumin (a protein made by the liver which keeps keep fluid in the bloodstream so it doesn't leak into other tissues), Alkaline Phosphate (an enzyme in a person's blood that helps break down proteins), Alanine Aminotransferase (an enzyme found mostly in the cells of the liver and kidney. High levels of this enzyme may cause liver damage), Aspartate Aminotransferase (an enzyme mostly found in the heart and liver. High levels of this enzyme indicate that the liver / muscle cells might be injured), Bilirubin (yellowish pigment that is made during the normal breakdown of red blood cells. Bilirubin passes through the liver and is eventually excreted out of the body. Higher than normal levels of bilirubin may indicate different types of liver or bile duct problems.), Serum Cholinesterase (a blood test that looks at levels of 2 substances that help the nervous system work properly. They are called acetylcholinesterase and pseudocholinesterase. Your nerves need these substances to send signals.), Cholestrol (High cholesterol can limit blood flow, increasing the risk of a heart attack or stroke), Creatinine ( the waste product of creatine, which the muscles use to make energy.High levels in the blood might indicate that the kidneys are not working correctly.), Gamma-Glutamyl Transferase ( a transferase that catalyzes the transfer of gamma-glutamyl functional groups from molecules such as glutathione to an acceptor that may be an amino acid, a peptide or water) and Prothrombin (a protein made by the liver. It is one of several substances known as clotting (coagulation) factors).
Disclaimer: This is just a learning project based on one particular dataset so please do not depend on it to actually know if you have breast cancer or not. It might still be a false positive or false negative. A doctor is still the best fit for the determination of such diseases.
World Hepatitis Day is commemorated each year on 28 July to enhance awareness of viral hepatitis, an inflammation of the liver that causes a range of health problems, including liver cancer.There are five main strains of the hepatitis virus – A, B, C, D and E. Together, hepatitis B and C are the most common cause of deaths, with 1.3 million lives lost each year. Amid the COVID-19 pandemic, viral hepatitis continues to claim thousands of lives every day.This year’s theme is “Hepatitis-free future,” with a strong focus on preventing hepatitis B among mothers and newborns.
Comments
Post a Comment
Comment your thoughts/doubts and we'd reply. Please be respectful