Detection of blood sugar level in diabetes diagnosis

WQD7001 Principles of Data Science

13 January 2022

Di Bei s2013283
Can Sun s2104926
Sheng Dong s2118080
Thoo Pooi Luen 17218141
Bingyan Li s2100331

App url: https://crispopopo.shinyapps.io/Diabetes/
code: https://github.com/DiBei/WQD7001-Group-Project

About The App

Features

Pregnancies
Glucose
Blood Pressure

Skin Thickness
Insulin
BMI
Diabetes Pedigree Function
Age

Detection of blood sugar level in diabetes diagnosis

Do you want to check your blood sugar levels?

Purposes

Figure out what factors could affect the blood sugar of diabetics.
Compare out what algorithm works the best in prediction blood sugar problem of diabetic.
Find out what method we could use to collect patient blood sugar.

Who can use?

The patient who has diabetes or anyone who wants test their own blood sugar.

Dataset and Data Science Process

Data Science Process:

Design a shiny app to collect the blood sugar, height, weight, blood pressure …
From the date we collect we could combine the blood situation and personal detail to analyze the patient status and provided health status and predict the high risk.

We can see that diabetes is more closely related to Glucose, Blood Pressure and BMI.Note: 0 = Not Diabetic and 1 = Diabetic.

Summary of Experience

The dataset consists about 768 recipes and consists of 8 attributes in the original datasets Data source：Kaggle https://www.kaggle.com/mathchi/diabetes-data-set

How to check blood glucose levels and make health judgments
Process the data ready for modelling by using different libraries in RStudio.
Understand and build up the shiny app architecture.