Healthcare systems Exploration and Data Analysis

Posted on Aug 12, 2015
The skills we demoed here can be learned through taking Data Science with Machine Learning bootcamp with NYC Data Science Academy.

"Exploring healthcare systems of OECD countries"


Glocalization is a term that combines the words "globalization" and "localization" to describe the adaptation of global products or services to accommodate the needs of people in a specific locale1. When I read about this word, it immediately triggered me the memories of some mangers saying: "We need to understand the market to position our product...", "What do we know about this country?" or "The director will visit our country and he wants to have a quick overview of it...". In the healthcare industry, understanding the market's needs is a must.

Nowadays it is very easy to find information by country. For example, the OECD (Organization for Economic Co-operation and Development) is an excellent source. Its "Health at a Glance" report, provides the latest comparable data and trends on different aspects of the performance of health systems in OECD countries.

I find this report very enriching, but sometimes it is difficult to link different topics or parameters. For example, from the charts below, you can see one chart shows the total number of days length stay in a hospital, and in a different chart the total number of beds. So the question is: can we find any relationship or any pattern if we combine them?

Finding insigths

Using OECD Healthcare data and having the goal on how support the business strategies, I designed the "Healthcare Explorer". It was developed using Shiny R package.

It is an application where the information is shown in an interactive and condensed way, allowing the users to discover patterns and insights about healthcare systems in OECD countries.


Healthcare Explorer

The application is divided in two sections:

By Country:

This tab gives you an easy access on how countries compare against others. You can select different years using the "Year" menu.

Four plots display information related to specific topics:

  •  Doctors - Remuneration vs number of consultations per day.  Currently this plot it only shows information for 2011. You can select four different types of doctors (GP Self- employed, GP Salaried, Specialist Self-Employed, and Specialist Salaried )
  • Hospitals - Length of stay vs Total number of beds
  • Spending / Resources - Health Expenditure vs Total number of medical units. The type of medical device can be selectable (MRI or CT)
  • Population - Total Population vs Life Expectancy

Each gray dot represents a country. Select "Country" menu to highlight one country and compare it against the rest of the countries.

To have more information for an specific point(s), hover over it and the information of the country and its values will be displayed.

The design of this layout is based on Patrick Tehubijuluw work.



By Year

This tab shows the trends of a country for two categories:

  • Medical devices - Provides number of CT/MRI units and exams per year. Dashed lines are the average of all countries.
  • Healthcare professionals - Provides the trend of the number of doctors and nurses and number of graduates per year.



The outcomes

Here are some interesting insights that I found and some ideas of how they could be converted into market strategies for the healthcare industry:

General Practitioners Salaried - 2011:

  • Slovak Rep. and Finland have similar remuneration but Slovak Rep. has 4 times more consultations
  • Hungary - has the lowest remuneration and the max number of consultations per day
  • Denmark - has the highest remuneration and one of the lowest number of consultations


It appears to have a robust HC system, with big population and high life expectancy rates.It has the highest number of medical devices and number of beds and the longest stays in hospitals.

However this also shows how Japan's healthcare system sustainability is in question2.



The hospital stay length, number of beds, MRI and CT units and its %GDP show a solid HC system.

Number of CT and MRI exams and units are above the average (2012). Review maintenance contracts and EOL equipment as an strategy.


There is an important growth in the number of professionals and graduates, so focusing on key opinion leaders and students could be a good strategy to increase brand preference.


Iceland, Luxembourg and Estonia:

Number of MRI/CT exams are above the average. However, number of devices does not show the same growth. Estonia has a low GDP% so selling new or state-of-the-art MRI/CT could not be the best strategy. Using a model of charge per exam, plus attractive maintenance contracts should be considered as an selling strategy.

Considerable decrease in doctor graduates, but there is an important growth in total number of doctors and nurses.

Noticeable increase in MRI exams and also in CT units. Strong GDP%, low MRI and CT number of units compared to the population size. Good opportunity to place new equipment.

Where are the graduates?
From the charts, the number of graduates are at least 5 times more than the number of professionals. I would be interesting to validate where the rest of the graduates are, if there is a immigration effect, or if the numbers of professionals are not totally reflected.


Go and try it!

There are lots of valuable insights you can get out from this tool. Now, I invite you to play with it and have fun!

Click here to open it!

Future work

  • Collect more data of remuneration per year.
  • Make dynamic charts to show transitions through years.
  • Include more data sources from OECD database
  • Include market trends from COCIR.

References & Notes

Data was extracted in July 2015 from OECD Data Health


1.Deloitte, "2014 Global health care outlook Shared challenges,shared opportunities"

2.McKinsey, "Improving Japan's health care system"

About Author

Related Articles

Leave a Comment

No comments found.

View Posts by Categories

Our Recent Popular Posts

View Posts by Tags

#python #trainwithnycdsa 2019 2020 Revenue 3-points agriculture air quality airbnb airline alcohol Alex Baransky algorithm alumni Alumni Interview Alumni Reviews Alumni Spotlight alumni story Alumnus ames dataset ames housing dataset apartment rent API Application artist aws bank loans beautiful soup Best Bootcamp Best Data Science 2019 Best Data Science Bootcamp Best Data Science Bootcamp 2020 Best Ranked Big Data Book Launch Book-Signing bootcamp Bootcamp Alumni Bootcamp Prep boston safety Bundles cake recipe California Cancer Research capstone car price Career Career Day citibike classic cars classpass clustering Coding Course Demo Course Report covid 19 credit credit card crime frequency crops D3.js data data analysis Data Analyst data analytics data for tripadvisor reviews data science Data Science Academy Data Science Bootcamp Data science jobs Data Science Reviews Data Scientist Data Scientist Jobs data visualization database Deep Learning Demo Day Discount disney dplyr drug data e-commerce economy employee employee burnout employer networking environment feature engineering Finance Financial Data Science fitness studio Flask flight delay gbm Get Hired ggplot2 googleVis H20 Hadoop hallmark holiday movie happiness healthcare frauds higgs boson Hiring hiring partner events Hiring Partners hotels housing housing data housing predictions housing price hy-vee Income Industry Experts Injuries Instructor Blog Instructor Interview insurance italki Job Job Placement Jobs Jon Krohn JP Morgan Chase Kaggle Kickstarter las vegas airport lasso regression Lead Data Scienctist Lead Data Scientist leaflet league linear regression Logistic Regression machine learning Maps market matplotlib Medical Research Meet the team meetup methal health miami beach movie music Napoli NBA netflix Networking neural network Neural networks New Courses NHL nlp NYC NYC Data Science nyc data science academy NYC Open Data nyc property NYCDSA NYCDSA Alumni Online Online Bootcamp Online Training Open Data painter pandas Part-time performance phoenix pollutants Portfolio Development precision measurement prediction Prework Programming public safety PwC python Python Data Analysis python machine learning python scrapy python web scraping python webscraping Python Workshop R R Data Analysis R language R Programming R Shiny r studio R Visualization R Workshop R-bloggers random forest Ranking recommendation recommendation system regression Remote remote data science bootcamp Scrapy scrapy visualization seaborn seafood type Selenium sentiment analysis sentiment classification Shiny Shiny Dashboard Spark Special Special Summer Sports statistics streaming Student Interview Student Showcase SVM Switchup Tableau teachers team team performance TensorFlow Testimonial tf-idf Top Data Science Bootcamp Top manufacturing companies Transfers tweets twitter videos visualization wallstreet wallstreetbets web scraping Weekend Course What to expect whiskey whiskeyadvocate wildfire word cloud word2vec XGBoost yelp youtube trending ZORI