DEV Community

spiritupbro
spiritupbro

Posted on • Edited on

IBM Auto AI Predict Early Stage Diabetes - Part 1

Introduction

What is diabetes ? diabetes is a serious condition where your blood glucose level is too high. There are two main types, Type 1 and Type 2. They're different conditions, but they’re both serious[1]. About 422 million people worldwide have diabetes, the majority living in low-and middle-income countries, and 1.6 million deaths are directly attributed to diabetes each year. Both the number of cases and the prevalence of diabetes have been steadily increasing over the past few decades[2].


diabetes infographic from WHO

The American Diabetes Association (ADA) released new research on March 22, 2018 estimating the total costs of diagnosed diabetes have risen to $327 billion in 2017 from $245 billion in 2012, when the cost was last examined.

This figure represents a 26% increase over a five-year period.

The study, Economic Costs of Diabetes in the U.S. in 2017, was commissioned by the ADA and addresses the increased financial burden, health resources used, and lost productivity associated with diabetes in 2017. The study includes a detailed breakdown of costs along gender, racial, and ethnic lines, and also includes a breakdown of costs on a state-by-state basis[3].


Diabetes Cost Infographic from diabetes.org

As you can see in the infographic above, the price to treat diabetes is very expensive,and because of that it's easier for us to prevent this diabetes, than to get one of it, if we can detect if we got diabetes, we can go to the nearest doctor to get an advice on how to stop the diabetes, so that the diabetes doesn't get to the critical stage, one of the solution to that is using machine learning, we need to get the data of the patient that has an early stage diabetes then put it into machine learning model to check if we got one or no, that way we can prevent the diabetes to be spread even more. We can use tools like IBM Auto AI to achieve that, IBM Auto AI is a really simple tool to create machine learning model to be deployed into a web service and then we can get the prediction out of it to create that let's go to part 2.

Top comments (0)