Overview / Usage

Liver Diseases account for over 2.4% of Indian deaths per annum. Liver disease is also difficult to diagnose in the early stages owing to subtle symptoms. Often the symptoms become apparent when it is too late. Early diagnosis can potentially be life-saving. Although not discoverable to even the experienced medical practitioner, the early symptoms of these diseases can be detected. Early diagnoses of patients can increase his/her life span substantially. This POC aims to diagnosis patient’s liver status with the help of several patient parameters such as age, Bilirubin, Alkaline Phosphotase, Alamine Aminotransferase, and Aspartate Aminotransferase among others. The Neural Network predicts whether the patient is suffering from a Liver Disease or not.

Methodology / Approach

1.  Data Analysis: This is in general looking at the data to figure out what’s going on, inspect the data - Check whether there is any missing data, irrelevant data and do a clean-up.
   

2.  Data Visualization: Visualizing the data in the form of graphs
   

3.  Feature selection: Identifying the feature that can be a factor for liver disease for both male and female genders. Search for any trends, relations & correlations.
   

4.  Draw an inference and predict whether the patient can be identified to be having liver disease or not using various machine learning algorithms: Logistic Regression, Gaussian Naive Bayes, Random Forest
   

Technologies Used

Programming Language: Python3
Libraries: pandas, numpy, matplotlib, seaborn, sklearn
Platform: Intel® AI DevCloud