This project focuses on predicting whether a patient has diabetes using a neural network model built from scratch. The model is based on the PIMA Indians Diabetes Dataset, which contains various health-related features such as blood glucose levels, insulin, age, and BMI. This project also serves for me to explore the mathematical foundations of neural networks and how they can uncover complex relationships within medical data.
The dataset used in this project is the Pima Indians Diabetes Database, which is publicly available on Kaggle. It contains 768 samples and 9 features related to medical attributes of patients.
- Pregnancies: Number of times the patient was pregnant.
- Glucose: Plasma glucose concentration over 2 hours.
- BloodPressure: Diastolic blood pressure (mm Hg).
- SkinThickness: Triceps skinfold thickness (mm).
- Insulin: 2-hour serum insulin (mu U/ml).
- BMI: Body mass index (weight in kg/(height in m)^2).
- DiabetesPedigreeFunction: A function that rates the likelihood of diabetes based on family history.
- Age: Age of the patient.
- Outcome: 0 for non-diabetic, 1 for diabetic.
Kaggle: Pima Indians Diabetes Database
I'm always eager to learn new techniques and improve my skills. If you have any questions, feedback, or would simply like to discuss ideas, feel free to reach out to me.