This post may contain paid links to my personal recommendations that help to support the site!
You’ve probably heard of the possible use of R in healthcare but one question still remains: How is R used in healthcare?
Well, I’ve done my research and found some definitive REAL uses of R in healthcare.
Here’s a short answer:
R is used in healthcare mainly for statistical studies and data science. R is used across several applications within the healthcare field, such as genomics, clinical research, epidemiology, healthcare optimization, and more. However, R can also be used beyond applications in healthcare.
Now that you’re aware of how R is used in healthcare, you’re likely to be curious about how exactly R was used!
I’ve put together 7 of such use cases and here they are:
7 REAL Use Cases of R in Healthcare You Should Know
- Population Genomics in Bioinformatics
- Statistical Analysis in Clinical Research
- Disease Spread Tracking
- Healthcare Business Optimization
- Breast Cancer Prediction using Machine Learning
- Computational Drug Discovery
- Vaccine Distribution Management
1. Genomics Processing in Bioinformatics
The use of R is really crucial when it comes to processing genomic data, especially in bioinformatics!
If you’re not familiar with bioinformatics, allow me to explain:
Bioinformatics is the use of computing and programming concepts to solve and make sense of biology.
Curious to know if bioinformatics is a data science? Check out this article here!
How is R used in genomics then? Well, R is actually one of the most commonly used open-sourced statistical tools in genomic studies.
A common package found in R called Bioconductor, is well-known for its extensive processing functions for genomic data.
Here’s a quick video explaining the use of Bioconductor for genomic data:
Many of such genomic analyses are then used for applications in real life.
For example, by analyzing genomic data, you can discover if you’re more susceptible to a certain disease.
There are even commercial companies that can help you analyze your biological data to help you understand your body better. I’m pretty sure R is used in their processing pipelines as well.
R is crucial in handling such large biological datasets because it is a powerful high-level programming language.
That means that many of the ready-made functions in base R are able to process data easily.
Another commonly used programming language in healthcare is Python. Curious to know more?
Read more about 5 uses of Python in healthcare in my other article here.
2. Statistical Analysis in Clinical Research
If you’ve learned some R programming, you’ve probably heard of its amazing statistical capabilities.
R has some of the best statistical packages and functions that make them perfect for analyzing data for clinical research.
As such, R is used very commonly among researchers across the biological research field. Users of R for research range from clinicians to biomedical researchers.
Curious to know more about the use of R in clinical trials?
Check out this introduction video below:
Want to read more on the use of R in clinical research?
Read this VERY in-depth presentation from a Biostatistician, Adrian Olszewski, to give you a fuller picture of everything!
Need some actual real-life applications instead?
In this article published on RStudio, the R programming language was used to drive agility in clinical reporting in GSK!
I’ve also embedded their presentation video below:
The webinar is well presented by Andy Nicholls from GSK and I definitely recommend checking it out!
Also, for those of you who are curious, you check out their code on Github over here.
Here’s another example: Merck, a pharmaceutical firm, used R to help optimize their clinical trial processes.
Read more about it here!
3. Disease Spread Tracking
Another really exciting use for R is in the field of epidemiology, specifically for tracking the spread of disease.
The COVID-19 pandemic is by far the largest disease to spread across our globe in recent years.
In one particular example, R was used to help in the tracking of COVID-19.
In this example, an R-Shiny portal was created to model and track the spread of COVID-19.
Check out their portal over here.
In this study, an R package, EpiModel, was developed to create a model that helps to predict infectious diseases.
EpiModel provides tools for models to analyze infectious disease transmission in R.
It’s also made to help students learn disease spread modeling!
4. Hospital Resource Optimization
R is a commonly used programming language within hospitals and healthcare institutes.
Some of the most common uses of R in hospitals are:
- Data processing
- Automating manual processes
- Data visualization
Data processing is done in R in hospitals to prepare summary reports. Hospitals generate a large amount of data everyday.
R has many useful packages that can help with data transformation such as data.table and dplyr. These packages let you reshape and clean data according to the healthcare reporting needs.
Automating manual processes
R is also great for automating manual processes such as the preparation of PowerPoint presentations. This is achieved using the officer package, which allows manipulation of Microsoft documents.
In this example, automation of hand hygiene compliance and monitoring was used in a study by using R.
R has very customizable data visualization options. This is done through the use of the ggplot2 package.
ggplot2 is a wonderful package that allows you to create custom visualizations in a modular approach. This makes it useful for reporting charts and trends in a hospital setting.
Curious to know more about the use of data analytics and visualization in healthcare?
Make sure you read this other article I wrote on data analytics in healthcare here.
5. Breast Cancer Prediction using Machine Learning
Here’s a really impactful application of R in healthcare!
In this study, a dataset was analyzed to predict breast cancer using machine learning in R.
Several models were used to predict but the Cubist model proved to show the highest prediction score of 0.976 or 97%.
In another study, machine learning in R was also applied to predict breast cancer. This time, genomic and hospital datasets were used in the prediction.
The h2o package was used in R to allow models to run faster in parallel.
The study concluded that in the hospital dataset, the best model was DL, and in the genomic dataset from TCGA, the best model was the XGBoost algorithm.
Here’s the Github link for the study.
6. Computational Drug Discovery
R can also be used for drug discovery. The Rcpi package is commonly used package in R that allows drugs to be tested computationally to see if they’re useful.
This study shows the usage of the Rcpi package as a platform for drug discovery.
This arc diagram above shows the network of possible drug-target interactions, made from the Rcpi package in R. The results of the interactions is then predicted using Random Forest model.
This proves that R is indeed a powerful language that combines chemical and biological data to help in drug discovery.
7. Managing COVID Vaccine Distribution
Our last application for R is for the tracking of vaccine distribution.
R has a really neat and quick way to have all it’s functionalities in a simple webapp. This webapp platform is called R Shiny.
Throughout the COVID-19 pandemic, R Shiny was used to manage COVID vaccines in West Virginia by Data Driven West Virginia!
Check out the video below from RStudio for more info:
The tool enabled data-driven distribution plans in an efficient way, that matched demand with supply well.
Here’s a video demonstration of the R Shiny tool.
Check out the full blog post over here!
Or you can read more on the use of R in public health over here.
How is Python Used in Healthcare?
Python is used in healthcare mainly through data science. Python is used to create machine learning algorithms in data science within healthcare, which are used in medical diagnostics, hospital operations, genomic studies, drug discovery, and predictive prognosis. However, Python is used in software production as well.
Read more in this article here.
How is Data Analytics Used in Healthcare?
Here are 13 Ways Data Analytics is Used in Healthcare:
- Medical Cost Reduction
- Clinical Risk Prediction
- Hospital Resource Allocation
- Drug Discovery
- Genomic Studies
- Patient Safety Improvement
- Fraud Prevention
- In-Hospital Mortality Prediction
- Medical Computer Vision
- Claim Denial Reduction
- Outpatient No-Show Prediction
- Disease Spread Mapping
- Fall-Risk Reduction
Read more in this article here.
That’s all the 7 uses for R in healthcare I’ve found to be the most impactful!
I’m very certain that there are many other uses out there but I hope that these examples have given you a better picture of R in healthcare.
Thanks for reading!
My Favorite Learning Resources:
My Recommended Learning Platforms!
|Learning Platform||What’s Good About the Platform?|
|1||Coursera||Certificates are offered by popular learning institutes and companies like Google & IBM|
|2||DataCamp||Comes with an integrated coding platform, great for beginners!|
|3||Pluralsight||Strong focus on data skills, taught by industry experts|
|4||Stratascratch||Learn faster by doing real interview coding practices for data science|
|5||Udacity||High-quality, comprehensive courses|
My Recommended Online Courses + Books!
|1||Data Analytics||Google Data Analytics Professional Certificate||–|
|2||Data Science||IBM Data Science Professional Certificate||–|
|3||Excel||Excel Skills for Business Specialization||–|
|4||Python||Python for Everybody Specialization||Python for Data Analysis|
|5||SQL||Introduction to SQL||SQL: The Ultimate Beginners Guide: Learn SQL Today|
|6||Tableau||Data Visualization with Tableau||Practical Tableau|
|7||Power BI||Getting Started with Power BI Desktop||Beginning Microsoft Power BI|
|8||R Programming||Data Science: Foundations using R Specialization||Learning R|
|9||Data Visualization||–||Big Book of Dashboards|
More Articles For You
- Jenness SM, Goodreau SM, Morris M. EpiModel: An R Package for Mathematical Modeling of Infectious Disease over Networks. J Stat Softw. 2018;84:8. doi:10.18637/jss.v084.i08