The Diabetes Project aims to revolutionize diabetes management through innovative technologies and data-driven approaches. This documentation serves as a guide for understanding the project's scope, goals, and implementation strategies.
This project focuses on predictive analysis for diabetes diagnosis using a dataset originally sourced from the National Institute of Diabetes and Digestive and Kidney Diseases.
The dataset contains various medical and demographic variables for a group of Pima Indian heritage females who are at least 21 years old.
The primary objective of this project is to develop a predictive model that can diagnostically predict whether a patient has diabetes based on the provided diagnostic measurements and demographic information.
Pregnancies:- Number of times pregnant Glucose:- Plasma glucose concentration a 2 hours in an oral glucose tolerance test BloodPressure:- Diastolic blood pressure (mm Hg) SkinThickness:- Triceps skin fold thickness (mm) Insulin-: 2-Hour serum insulin (mu U/ml) BMI:- Body mass index (weight in kg/(height in m)^2) DiabetesPedigreeFunction:- Diabetes pedigree function Age:- Age (years) Outcome:- Class variable (0 or 1)
65.1% patients in the dataset do NOT have diabetes.
34.9% patients in the dataset has diabetes.
It has a descent level of precision, indicating that when it predicts positive cases (diabetic). It's correct about 65% of the time.
Out of the 768 patients, 268 have been diagnosed with diabetes.
Patients with high blood pressure has greater chances of diabetes.
An increase in Blood pressure BMI and skin thickness also increases.
Increasing level of glucose and insulin increases chances of diabetes.