Diabetes Detection Web Application 🔎

This is a diabetes detection web application that uses machine learning to detect whether someone has diabetes that uses the Pima Indians Diabetes Database. It utilzes the Streamlit libary.

Dataset Used 📝

This dataset was derived from Kaggle. It is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. This will be used to diagnostically predict whether or not a patient has diabetes, based on certain diagnostic measurements included in the dataset.

Several constraints were placed on the selection of these instances from a larger database. In particular, all patients here are females at least 21 years old of Pima Indian heritage.

Predictor Values Include:

• Number of Pregnancies
• Body Mass Index(BMI)
• Insulin Level
• Age
• Blood Pressure
• Skin Thickness
• Diabetes Pedigree Function

Machine Learning Models used ✨

• Logistic Regression
• Random Forest Classifier
• K Nearest Neighbors

Snapshots of the web application 📷

• To run, install requirements.txt then run this command:

streamlit run app.py

The notebook is also included in this repo, feel free to fork and improve this project 😃