Diabetes Prediction Analysis

Diabetes is a disease that occurs when your blood glucose, also called blood sugar, is too high. Over time, having too much glucose in your blood can cause health problems, such as heart disease, nerve damage, eye problems, and kidney disease. An estimated 30.3 million people in the United States have diabetes. About one in four people with diabetes don’t know they have the disease. An estimated 84.1 million Americans aged 18 years or older have prediabetes. The earlier diagnosis is obtained, the much easier we can control it. Machine learning can help people make a preliminary judgment about diabetes mellitus according to their daily physical examination data, and it can serve as a reference for doctors. [DataSet] , [1]

Simply enter data and click predict to see the results

Example of postive case:

  • Pregnancies: 6
  • Glucose: 148
  • BloodPressure: 72
  • SkinThickness: 35
  • Insulin: 0
  • BMI: 33.6
  • Pedigree: 0.627
  • Age: 50
  • Example of negative case:

  • Pregnancies: 1
  • Glucose: 85
  • BloodPressure: 66
  • SkinThickness: 29
  • Insulin: 0
  • BMI: 26.6
  • Pedigree: 0.351
  • Age: 31
  • Predict Diabetes with Machine Learning

    Total Previous Pregnancies

    Glucose

    Blood Pressure

    Skin Fold Thickness

    Blood Serum Insulin

    BMI

    Diabetes Pedigree Function

    Age

    Virtualizations


    BMI vs Family History

    The correlation between BMI and Family Pedigree(Diabetes Pedigree Function). Orange respresents positive for diabetes. Green respresents those without diabetes.

    Frequency with Age

    Here we see the Frequency of diabetes in people between the ages of 20 and 80.

    Confusion Matrix

    Confusion matrices are used to visualize important predictive analytics like recall, specificity, accuracy, and precision. Confusion matrices are useful because they give direct comparisons of values like True Positives, False Positives, True Negatives and False Negatives.

    Misc Data



    © Made by a Human.