By Aziz Alreshidi Email : swe2010-m-s@hotmail.com
Abstract Explore and compare machine learning techniques and tools used to predict liver disease for patients in India utilizing a set of health data measurements. Description of data source and web links The Indian Liver Patient Dataset (ILPD) contains 10 health variables for Indian patients along with a binary outcome variable indicating whether or not the patient has a liver disease. The data set was published on 2012-05-21 by two professors and an associate computer science research professor.
University of California, Irvine: Center for Machine Learning and Intelligent Systems ILPD (Indian Liver Patient Dataset) Data Set https://archive.ics.uci.edu/ml/datasets/ILPD+(Indian+Liver+Patient+Dataset)#
Kaggle: UCI Machine Learning Indian Liver Patient Records https://www.kaggle.com/uciml/indian-liver-patient-records/version/1
Number of records and size of the dataset This dataset contains a total of 583 records. 416 records are for patients that have a liver disease apart from 167 patients who do not have a liver disease. The dataset is presented in CSV format with a file size of 24kb.
Number and description of attributes in the dataset 10 features are recorded for these patients as well as classification labels of disease/no disease.
Using Convolutional Neural Networks (CNN)
Here is the CNN i put the input_diminetion as 11 becouse we have 11 features.
See Corrolation between Features
ploting Model Performance
Classification Report
