Is it better to have a narrow or broad research focus? There are obviously pros/cons to both options (and arguably these aren’t mutually exclusive!), but it’s certainly an interesting thought posed in a recent tweet from @dnepo.
While I’m sure we all have a vague idea of where we sit on that spectrum of broad-narrow focus, there’s nothing like a bit of objective data (like a word cloud) to help us understand this better! While there are some online tools out there, R can make getting, cleaning, and displaying this data very easy and reproducible.
We will aim to cut down on the work required in collecting all your publication data by using google scholar – if you don’t have an account already, make one!
Firstly, we need 3 packages to achieve this:
scholar: to download publications associated with your google scholar account.
tidyverse: to clean and wrangle your publication data into the required format.
wordcloud2: to generate a pretty wordcloud of your publication titles.
Finally, we can generate our word cloud! The code below is generic, so works for anyone so long as you supply the Google Scholar ID (“gscholarid”) and filler words (remove).
# Download dataframe of publications from Google Scholar
scholar::get_publications(id = gscholarid) %>%
# Do some basic cleaning of paper titles
dplyr::mutate(title = stringr::str_to_lower(title),
title = stringr::str_replace_all(title, ":|,|;|\\?", " "),
title = stringr::str_remove_all(title, "\\(|\\)"),
title = stringr::str_remove_all(title, "…"),
title = stringr::str_remove_all(title, "\\."),
title = stringr::str_squish(title)) %>%
# Combine all text together then separate by spaces (" ")
dplyr::summarise(word = paste(title, collapse = " ")) %>%
tidyr::separate_rows(word, sep = " ") %>%
# Count each unique word
dplyr::summarise(freq = n()) %>%
# Remove common filler words
dplyr::filter(! (word %in% remove)) %>%
# Put into descending order
And here we go! I think safe to say I’m surgical focussed, but quite a lot of different topics under that umbrella! Why not run the code here and figure out how your publications break down!
There are several different ways to make maps in R, and I always have to look it up and figure this out again from previous examples that I’ve used. Today I had another look at what’s currently possible and what’s an easy way of making a world map in ggplot2 that doesn’t require fetching data from various places.
TLDR: Copy this code to plot a world map using the tidyverse:
There’s some explanation on what reshaping data in R means, why we do it, as well as the history, e.g., melt() vs gather() vs pivot_longer() in a previous post: New intuitive ways for reshaping data in R
That post shows how to reshape a single variable that had been recorded/entered across multiple different columns. But if multiple different variables are recorded over multiple different columns, then this is what you might want to do:
I’ve just set up a single page website (= online business card) for myself and my husband: https://pius.cloud/ . This post summarises what I did. If you’re looking to get started with something super quickly, then only the first two steps are essential (Creating a website and Serving a website).
Creating a website (using Nicepage) I’ve created websites using various tools such as straight up HTML, WordPress, Hugo+blogdown (this site – riinu.
With news of the lockdown in March came the dawning reality that we wouldn’t be able to deliver our usual HealthyR 2.5 day quick start course in May.
The course is always over-subscribed so we were keen to find a solution rather than cancelling altogether.
HealthyR teaches the Notebook format which is already an online tool hosted by RStudio Cloud – so we knew that bit would work online. But what to do about getting attendees and tutors online, delivering lectures and offering interactive support with coding? Could we recreate our usual classroom environment online?
Never a group to shy away from a technical challenge, and with expertise in online education, we set about researching what online tools could be used.
After trying various options we went with Blackboard Collaborate to provide an online classroom, together with our usual RStudio Cloud to provide the Notebooks interface. Collaborate has a really nice feature of ‘break-out rooms’ where small groups can be assigned a separate online room with a tutor to work through exercises. The tutor can provide support and answer questions, using the screen share option to see exactly what each person might be having difficulty with.
After a few rehearsals to work out what roles to assign all our moderators and attendees, how to send people to the break rooms and recall them back to the main room we were set!
Ahead of the course, attendees were emailed the usual pre-course materials and a log in for their RStudio Cloud accounts, together with an invite to a Collaborate session for each of the 3 days. We split the 20 attendees who had confirmed attendance into groups of 5 and assigned one of our fantastic tutors to each group.
We also set up a an extra break out room with a dedicated tutor which could be used for anyone needing specific one-to-one help.
After the ice-breaker, ‘What’s a new thing you’ve done since lockdown?’ – everything from macrame to margaritas plus tie-dying and a lot of baking – the course got underway with the first lecture.
One or two delegates had some problems with internet connections, and the assigning of breakout rooms took a bit of getting used, but Riinu soon worked out an efficient system and the first coding exercises were underway!
We were delighted that the course received really positive feedback overall – none of us were sure this would work, but it did! The live coding sessions and pop quizzes were particularly popular.
We’ll definitely run HealthyR online again if the lockdown continues. Even after the lockdown, moving online widens access and offers the possibility for our international collaborators to join a course without having to travel.
Thank you to all our attendees who quickly adapted to the online format and to our amazing tutors, Tom, Kenny, Derek, Peter, Katie, Stephen, Michael and Ewen, who provided 3 days of their time to run the course, led as ever, by Riinu.
Collaborate and RStudio Cloud worked very well for me. The breakout rooms were a nice touch to allow discussions.
Clear and easy instructions. Worked seamlessly!
This was a great course. I think in person would have allowed more interaction so I would still keep your original format available after this lockdown is over but well done on adapting and providing an excellent course.
NA – Not Available/Not applicable is R’s way of denoting empty or missing values. When doing comparisons – such as equal to, greater than, etc. – extra care and thought needs to go into how missing values (NAs) are handled. More explanations about this can be found in the Chapter 2: R basics of our book that is freely available at the HealthyR website
This post lists a couple of different ways of keeping or discarding rows based on how important the variables with missing values are to you.
If you’ve been watching the news or twitter over the past
week, you may have seen the appendicitis-related headlines about unnecessary operations
being performed. The RIFT collaborative and Dmitri Nepogodiev have really
spearheaded some cool work looking at who gets unnecessary operations, which
are all well worth a read:
So, when Dmitri asked if I could develop a web application
for risk scoring to help identify those at low risk of appendicitis, I was very
Having quite often used risk calculators in clinical
practice, I started to write a list of what makes a good calculator and how to
make one that can be used effectively. The most important were:
Easy to use
Works on any platform (as NHS IT has a wide
variety of browsers!) and on mobile (some hospitals have great Wi-Fi through
Can be quickly updated
Looks good and gives an intuitive result
Lightweight requiring minimal processing power,
so many users can use simultaneously
Now we use a lot of R in surgical informatics, but Shiny wasn’t going to be the one for this as it’s not that mobile friendly and doesn’t necessarily work on every browser that smoothly (sorry shiny!). Similarly, the computational footprint required to run shiny is too heavy for this. So, using codepen.io and a pug html compiler, I wrote a mobile friendly website (Still a couple of tweaks I’d like to make to make entirely mobile friendly!).
Similarly, I get asked why not an app? Well app development requires developing on multiple platforms (Apple, Android, Blackberry) and can’t be used on those pesky NHS PCs. Furthermore, if something goes out of date or needs to be updated quickly – repairing it will take ages as updates sometimes have to be vetted by app stores etc.
My codepen.io for the calculator:
Codepen.io is a great development tool and allows you to
combine and get inspired by other people’s work too!
I then set up a micro instance on google cloud, installed the pug compiler and apache2, selected a fixed IP and opened the HTTP port to the world and all done! (this set up is a little more involved than this but was straightforward!). The micro instance is very very cheap so it’s not expensive to run. The Birmingham crew then bought a lovely domain appy-risk.org for me to attach it to.
Here’s the obligatory increase in CPU usage since publication (slightly higher but as you can tell – it’s quite light:
The following blog post provides a general overview of some of the terms encountered when carrying out logistic regression and was inspired by attending the extremely informative HealthyR+: Practical logistic regression course at the University of Edinburgh.
What is confounding?
What are interaction effects?
How do we detect interactions?
What happens if we overlook interactions?
Why should we be aware of clustered data?
A solution to clustering
What is confounding?
Confounding occurs when the association between an explanatory (exposure) and outcome variable is distorted, or confused, because another variable is independently associated with both.
The timeline of events must also be considered, because a variable cannot be described as confounding if it occurs after (and is directly related to) the explanatory variable of interest. Instead it is sometimes called a mediating variable as it is located along the causal pathway, between explanatory and outcome.
Potential confounders often encountered in healthcare data include for example, age, sex, smoking status, BMI, frailty, disease severity. One of the ways these variables can be controlled is by including them in regression models.
In the Stanford marshmallow experiment, a potential confounder was left out – economic background – leading to an overestimate of the influence of a child’s willpower on their future life outcomes.
Another example includes the alleged link between coffee drinking and lung cancer. More smokers than non-smokers are coffee drinkers, so if smoking is not accounted for in a model examining coffee drinking habits, the results are likely to be confounded.
What are interaction effects?
In a previous blog post, we looked at how collinearity is used to describe the relationship between two very similar explanatory variables. We can think of this as an extreme case of confounding, almost like entering the same variable into our model twice. An interaction on the other hand, occurs when the effect of an explanatory variable on the outcome, depends on the value of another explanatory variable.
When explanatory variables are dependent on each other to tell the whole story, this can be described as an interaction effect; it is not possible to understand the exact effect that one variable has on the outcome without first knowing information about the other variable.
The use of the word dependent here is potentially confusing as explanatory variables are often called independent variables, and the outcome variable is often called the dependent variable (see word clouds here). This is one reason why I tend to avoid the use of these terms.
An interesting example of interaction occurs when examining our perceptions about climate change and the relationship between political preference, and level of education.
We would be missing an important piece of the story concerning attitudes to climate change if we looked in isolation at either education or political orientation. This is because the two interact; as level of education increases amongst more conservative thinkers, perception about the threat of global warming decreases, but for liberal thinkers as the level of education increases, so too does the perception about the threat of global warming.
If interaction effects are not considered, then the output of the model might lead the investigator to the wrong conclusions. For instance, if each explanatory variable was plotted in isolation against the outcome variable, important potential information about the interaction between variables might be lost, only main effects would be apparent.
On the other hand, if many variables are used in a model together, without first exploring the nature of potential interactions, it might be the case that unknown interaction effects are masking true associations between the variables. This is known as confounding bias.
How do we detect interactions?
The best way to start exploring interactions is to plot the variables. Trends are more apparent when we use graphs to visualise these.
If the relationship between two exposure variables on an outcome variable is constant, then we might visualise this as a graph with two parallel lines. Another way of describing this is additive effect modification.
But if the effect of the exposure variables on the outcome is not constant then the lines will diverge. We can describe this as multiplicative effect modification.
Once an interaction has been confirmed,
the next step would be to explore whether the interaction is statistically
significant or not.
Some degree of ambiguity exists surrounding the terminology of interactions (and statistical terms in general!), but here are a few commonly encountered terms, often used synonymously.
Many methods of statistical analysis are intended to be applied with the assumption that, within a data-set, an individual observation is not influenced by the value of another observation: it is assumed that all observations are independent of one another.
This may not be the case however, if you are using data, for example, from various hospitals, where natural clustering or grouping might occur. This happens if observations within individual hospitals have a slight tendency to be more similar to each other than to observations in the rest of the data-set.
Random effects modelling is used if the groups of clustered data can be considered as samples from a larger population.
Why should we be aware of clustered data?
Gathering insight into the exact nature of differences between groups may or may not be important to your analysis, but it is important to account for patterns of clustering because otherwise measures such as standard errors, confidence intervals and p-values may appear to be too small or narrow. Random effects modelling is one approach which can account for this.
A solution to clustering
The random effects model assumes that having allowed for the random effects of the various clusters or groups, the observations within each individual cluster are still independent. You can think of it as multiple levels of analysis – first there are the individual observations, and these are then nested within observations at a cluster level, hence an alternative name for this type of modelling is multilevel modelling.
There are various terms which are used when referring to random effects modelling, although the terms are not entirely synonymous. Here are a few of them:
There are two main types of random effects models:
Random intercept model
Random slope and intercept model
To finish, here is a quick look at some of the key differences between confounding and interaction.
If you would like to learn more about these terms and how to carry out logistic regression in R, keep an eye on the HealthyR page for updates on courses available.
TLDR: You can teach R on people’s own laptops without having them install anything or require an internet connection.
Members of the Surgical Informatics team in Ghana, 2019. More information: surgicalinformatics.org
Running R programming courses on people’s own laptops is a pain, especially as we use a lot of very useful extensions that actually make learning and using R much easier and more fun. But long installation instructions can be very off-putting for complete beginners, and people can be discouraged to learn programming if installation hurdles invoke their imposter syndrome.
We almost always run our courses in places with a good internet connection (it does not have to be super fast or flawless), so we get our students all set up on RStudio Server (hosted by us) or https://rstudio.cloud (a free service provided by RStudio!).
You connect to either of these options using a web browser, and even very old computers can handle this. That’s because the actual computations happen on the server and not on the student’s computer. So the computer just serves as a window to the training instance used.
Now, these options work really well as long as you have a stable internet connection. But for teaching R offline and on people’s own laptops, you either have to:
make sure everyone installs everything correctly before they attend the course
Download all the software and extensions, put them on USB sticks and try to install them together at the start
start serving RStudio from a your computer using Local Area Network (LAN) created by a router
Now, we already discussed why the first option is problematic (gatekeeper for complete beginners). The second option – installing everything at the start together – means that you start the course with the most boring part. And since everyone’s computers are different (both by operating systems as well as different versions of the operating systems), this can take quite a while to sort. Therefore, queue in option c) – an RStudio Server LAN party.
A computer with more than 4GB of RAM. macOS alone uses around 2-3GB just to keep going, and running the RStudio Server docker container was using another 3-4 GB, so you’ll definitely need more than 4GB in total.
A network router. For a small number of participants, the same one you already have at home will work. Had to specify “network” here, as apparently, even my Google search for “router” suggests the power tool before network routers.
Docker – free software, dead easy to install on macOS (search the internet for “download Docker”). Looks like installation on the Windows Home operating system might be trickier. If you are a Windows Home user who is using Docker, please do post a link to your favourite instructions in the comments below.
Internet connection for setting up – to download RStudio’s docker image and install your extra packages.
My MacBook Pro serving RStudio to 10 other computers in Ghana, November 2019.
Running RStudio using Docker is so simple you won’t believe me. It honestly is just a single-liner to be entered into your Terminal (Command Prompt on Windows):
This will automatically download a Docker image put together by RStudio. The one called verse includes all the tidyverse packages as well as publishing-related ones (R Markdown, Shiny, etc.). You can find a list of the difference ones here: https://github.com/rocker-org/rocker
Then open a browser and go to localhost:8787 and you should be greeted with an RStudio Server login! (Localhost only works on a Mac or Linux, if using Windows, take a note of your IP address and use that instead of localhost.) More information and instructions can be found here: https://github.com/rocker-org/rocker/wiki/Using-the-RStudio-image
Tip: RStudio suggests port 8787, which is what I used for consistency, but if you set it up on 80 you can omit the :80 as that’s the default anyway. So you can just go to localhost (or something like 127.0.0.0 if using Windows).
For those of you who have never seen or used RStudio Server, this is what it looks like:
Rstudio Server is almost identical to RStudio Desktop. Main difference is the “Upload” button in the Files pane. This one is running in a Docker container, served at port 8787, and accessed using Safari (but any web browser will work).
The Docker single-liner above will create a single user with sudo rights (since I’ve included -e ROOT=TRUE). After logging into the instance, you can then add other users and copy the course materials to everyone using these scripts: https://github.com/einarpius/create_rstudio_users Note that the instance is running Debian, so you’ll need very basic familiarity with managing file permissions on the command line. For example, you’ll need to make the scripts executable with chmod 700 create_users.sh.
Then connect to the same router you’ll be using for your LAN party, go to router settings and assign yourself a fixed IP address, e.g., 22.214.171.124. Once other people connect to the network created by this router (either by WiFi or cable), they need to type 126.96.36.199:8787 into any browser and can just start using RStudio. This will work as long as your computer is running Docker and you are all connected to the same router.
I had 10 people connected to my laptop and, most of the time, the strain on my CPU was negligible – around 10-20%. That’s because it was a course for complete beginners and they were mostly reading the instructions (included in the training Notebooks they were running R code in). So they weren’t actually hitting Run at the same time, and the tasks weren’t computationally heavy. When we did ask everyone to hit the “Knit to PDF” button all at the same time, it got a bit slower and my CPU was apparently working at 200%. But nothing crashed and everyone got their PDFs made.
Why are you calling it a LAN party?
My friends and I having a LAN party in Estonia, 2010. We would mostly play StarCraft or Civilization, or as pictured here – racing games to wind down at the end.
LAN stands for Local Area Network and in most cases means “devices connected to the same WiFi*”. You’ve probably used LANs lots in your life without even realising. One common example is printers: you know when a printer asks you to connect to the same network to be able to print your files? This usually means your computer and the printer will be in a LAN. If your printed accepted files via any internet connection, rather than just the same local network, then people around the world could submit stuff for your printer. Furthermore, if you have any smart devices in your home, they’ll be having a constant LAN party with each other.
The term “LAN party” means people coming together to play multiplayer computer games – as it will allow people to play in the same “world”, to either build things together or fight with each other. Good internet access has made LAN parties practically obsolete – people and their computers no longer have to physically be in the same location to play multiplayer games together. I use the term very loosely to refer to anything fun happening on the same network. And being able to use RStudio is definitely a party in my books anyway.
But it is for security reasons (e.g., the printer example), or sharing resources in places without excellent internet connection where LAN parties are still very much relevant.
* Overall, most existing LANs operate via Ethernet cables (or “internet cables” as most people, including myself refer to them). WiFi LAN or WLAN is a type of LAN. Have a look at your home router, it will probably have different lights for “internet” and “WLAN”/“wireless”. A LAN can also be connected to the internet – if the router itself is connected to the internet. That’s the main purpose of a router – to take the internet coming into your house via a single Ethernet cable, and share it with all your other devices. A LAN is usually just a nice side-effect of that.
Docker, containers, images
Docker image – a file bundling an operating system + programs and files Docker container – a running image (it may be paused or stopped)
List of all your containers: docker ps -a (just docker ps will list running containers, so the ones not stopped or paused)
When you run rstudio/verse for the first time it will be downloaded into your images. The next time it will be taken directly from there, rather than downloaded. So you’ll only need internet access once.
Stop an active container: docker stop container-name
Start it up again: docker start container-name
Save a container as an image (for versioning or passing on to other people):
docker commit container-name pository:tag
For example: docker commit rstudio-server rstudio/riinu:test1
Rename container (by default it will get a random label, I’d change it to rstudio-server):
docker rename happy_hippo rstudio-server
You can then start your container with: docker start rstudio-server