Data Study on Cardiovascular Diseases and Risk Factors
The skills the author demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.
I wanted to study various Cardiovascular Diseases and Risk Factors to highlight the correlation between them, and trends across the country. For this I used the dataset provided by the National Cardiovascular Disease Surveillance System. The system is designed to integrate multiple indicators from many data sources to provide a comprehensive picture of the public health burden of Cardiovascular diseases and associated risk factors in the United States. BRFSS is a continuous, state-based surveillance system that collects information about modifiable risk factors for chronic diseases and other leading causes of death.
The data reveals the risk factors associated with cardiovascular diseases for U.S.A states. It also gives information about the percentage of people in a specific state having risk factors associated with cardiovascular diseases. The data is organized by states and indicator, and they include CVDs (e.g., heart failure) and risk factors (e.g., hypertension). The data can be plotted as trends and stratified by age group, gender, and race/ethnicity.
I created an app that provides users to visualize the data on map of the country according to age, gender, ethnicity and year selected. The user could also select the Cardiovascular Disease and the Risk Factor and see if they are correlated to each other. I found out that Smoking and Hypertension is correlated to Stroke and Diabetes is correlated to Coronary Heart Diseases.
Physical inactivity, cholesterol abnormalities are not directly correlated to major cardiovascular diseases. They may or may not be responsible for increase in cardiovascular diseases.
Also, user could see in which particular year the risk factors for the cardiovascular disease for specific state was at its peak. This would then be able to imply if any health initiatives are working over years.
The user could also compare two states and see which state had the higher indication of prevalence of a certain disease.
Further Investigation of Data
We can enrich the data further by bringing in the population, income data and Medicaid spend on cardiovascular diseases. Income would allow us to correlate if the malnutrition is caused by poverty. This then could be used to assess if the cost of improving the nutrition in a certain population segment is less than Medicaid spend to treat disease. This data will allow governmental with better spending decisions
Also mapping population to diseases helps understand the potential market size of heart medication. This helps in supply-chain planning. If a pharmaceutical company wants to launch a new drug or treatment, they can decide to launch the treatment where the patient density is highest.
Population data over years will also tell us if the increase in rate of disease is due to healthy people moving out of state. We can then decide to pull in more relevant data for further analysis.
GitHub Source Code: https://github.com/k-malviya/Shiny_CDRF