BI Blog,  Data Visualization,  News

Predict Heart Disease with Oracle Data Visualization

An interesting post was published yesterday on the Oracle Analytics Blog by Joseph Kuttikat, explains how Machine Learning tools can be used to analyze medical data and how these tools can be used to extract important information for health and prevention.

The analyzed data concern cases of Heart Disease (including Coronary Heart Disease, Hypertension, and Stroke).

Heart Disease accounts for about 1 of every 3 deaths in the US, or nearly 801,000 deaths in one year, according to the American Heart Association, Cardiovascular disease is the leading global cause of death, accounting for more than 17.3 million deaths per year in 2013, a number that is expected to grow to more than 23.6 million by 2030.

In fact, they used a method consisting of training a model using actual known values of a column, to predict the column value for unknown cases. This method comes under the domain of Supervised Machine Learning. Oracle Data Visualization comes equipped with inbuilt algorithms to perform such supervised multi-classification and others. Users can choose any one of these algorithms based on the need. Here is a snapshot showing list of inbuilt algorithms in Oracle Data Visualization that can perform this multi-classification, as seen in the graphic below:

heart1.jpg

By using these methods, even a simple-to-use data visualization tool can help answer complex questions and get to the heart of the matter.

heart2

In the demonstration video below Oracle shows how Oracle Data Visualization and machine learning algorithms are applied on patient health data to predict the prospect of heart disease.

The process shown in the video below can be summarized as follows:

  • Get data of patients known to have heart disease. This dataset contains information related to heart diseases like blood sugar, cholesterol and other medical information about the individual
  • Create a multi-classification neural net model using that data
  • Use that model to predict the heart disease likelihood in other individuals for whom we know their medical history or medical information

The machine learning plugin example seen in the video can be downloaded from the Oracle Analytics Store. The name of the project is Example DV project: Heart Disease Prediction

Source: Oracle Analytics Blog

 

Leave a Reply