Prediction of Pre-Diabetes and Diabetes in Mothers above 21 years of age with Machine Learning Models
The purpose of this project titled, ‘Prediction of Pre-Diabetes and Diabetes in Mothers above 21 years of age with Machine Learning Models’, was to build a website which collects relevant user details and predicts their diabetic condition using a Machine Learning model.
The project titled 'Prediction of Pre-Diabetes and Diabetes in Mothers above 21 years of Age' features several data visualisation and pre-processing techniques before feeding the data to various Machine Learning Models to obtain the best trained model which is then used to predict diabetic condition of a patient via the website.
The target users for our project are mothers over the age of 21 who are relatively more prone to diabetes. They can use the website for self-diagnosis, helping them make better health decisions and get medical consultation to avoid future complications.
The project made use of libraries like Matplotlib to visualise the data and observe patterns and outliers and facilitated the data cleansing process. Scikit-Learn was used to implement the Machine Learning Models.
Flask was used to deploy the model and make predictions after inputting the various health attributes.
The below image shows the website interface that makes predictions using the trained Machine Learning Model.
From the analysis, the best performing model was the Random Forest Classifier with an increased accuracy of 81%.
Made with ❤