Making reproducible research as natural as breathing

Peter CharltonPeter Charlton is a PhD student at King’s College London working as part of the Hospital of the Future (HotF) project. The overall aim of the HotF project is to provide early identification of hospital patients who are deteriorating. Peter’s work focuses on using wearable sensors to continuously assess patients’ health.

One of the key aims of the HotF project is to develop a technique to continuously monitor a patient’s “respiratory rate”: how often they breathe. Respiratory rate often changes early in the progression of a deterioration, giving advanced warning of a severe event such as a heart attack. However, it is currently measured by hand by counting the number of times a patient breathes in a set period of time. This approach is time-consuming, inaccurate, and only provides intermittent measurements. The alternative approach which I’m working on is to estimate respiratory rate from a small, unobtrusive, wearable sensor.

Wearable sensors are currently routinely used to monitor heart rate and blood oxygenation levels. It turns out that the signals which provide these measurements are subtly influenced by respiration, as demonstrated below. If these subtle changes can be extracted reliably, then we could monitor respiratory rate “for free”, without the need for any additional sensors. This may provide all-important information on changes in a patient’s health, allowing clinicians to identify deteriorating patients earlier.

PeterCharlton_heartratesignal

The heart rate is clearly visible in this signal since each spike corresponds to a heart beat. The spikes also vary in height with each of the four breaths. These subtle changes can be used to estimate respiratory rate.

So what’s all this got to do with reproducible research? Well, over the past few decades over 100 papers have been written describing methods for estimating respiratory rate electronically from signals that are already monitored by wearable sensors. If you read them (it takes a long time) then you find that hundreds of methods have been described. The key questions are: which method is the best, and is it good enough to use in clinical practice? Answering these questions can be a daunting task given how many different methods there are. Very few of the methods are publicly available, so to answer these questions you’d have to implement each of the methods yourself. Even once you have done this, you’d need to try them out on some data. Collecting this data is no easy task. Altogether, reproducing scientist’s previous work on this problem is quite difficult.

I’m hoping that this won’t be such a problem in the future. We have recently implemented many of the methods, collected a benchmark dataset on which to test the methods, and reported the results. All of this is publicly available. What’s more, you can download it all for free, from the methods, to the data, to the article describing the results. So in a few clicks you can catch up, reproduce our research, and start making progress yourself, even producing methods like this:

PeterCharlton_resp_video_gif_red

Well, nearly … I’ve written a tutorial on the methods, which is due to be published in a textbook soon. This work can be reproduced exactly. Since then we have extended the range of publicly available resources by adding more methods, and the new benchmark dataset. This most recent work can’t be reproduced exactly since we had to make a few changes before making it publicly available. I intend to make future work on this topic fully reproducible so that researchers can build on our work. Who knows, perhaps this will contribute towards earlier identification of deteriorating patients in the future.

Moving scenes

Dr David Lloyd is a Clinical Research Fellow at King’s College London and working as part of the iFIND project. The overall aim of the intelligent Fetal Imaging and Diagnosis project is to combine innovative technologies into a clinical ultrasound system that will lead to a radical change in the way fetal screening is performed.

David
David

One of the most important goals of the iFIND project is to build an “atlas” of the fetus: a comprehensive map of fetal anatomy at around 20 weeks gestation (when routine antenatal scans are performed). This means getting the best quality images that we can, from as many women as we can – but as I’m learning, taking pictures of a 20 week fetus while they’re still in the womb really isn’t that easy.

For one thing, they’re very (very) small. The fetal heart, for example, with all of its tiny chambers and valves, is only about 15mm long: less than the size of penny. Ultrasound technology – used in all routine antenatal scans in the UK – is actually fairly good at visualising these tiny structures. It uses very high frequency sound waves which are reflected back (“echo”) from the structures inside the body to produce an image. In fetal ultrasound, the images produced can be excellent; but unfortunately that’s not true for every patient. Ultrasound has to be able to “see” through the body to the parts of the baby we want to image, and that isn’t always easy. It will depend on the age of the baby, how they are lying in the womb, the size of the mother, and many other factors.

MRI, which uses a strong magnetic field and radio waves to produce images, isn’t so limited. It can see the structures inside the body regardless of whether there’s bone, muscle or fat in the way; and in some cases it can give us even more detailed images than ultrasound. Importantly, it is also one of the few imaging techniques that is safe to use in pregnancy. The problem? MRI isn’t great with small, moving targets – like we see in the fetus.

So that’s why we ask our iFIND volunteers to have both an ultrasound and an MRI scan. By combining the strengths of these two technologies, we hope to get the best of both worlds to produce the most accurate fetal atlas we can.

blue_fetuses
Of course though, even that isn’t quite so simple. Fetal movements – like twisting, rolling, stretching and kicking – are a particularly tricky problem, even when we use both technologies together .

Watch this MRI clip from one of our volunteers. Unfortunately there’s not much you can do when your patient decides to start breakdancing half way through a scan! At least, you’d think there wasn’t… but amazingly even that may not be an insurmountable problem. In the last few months I’ve been involved with some of the work of Bernhard Kainz and his colleagues, who have devised clever algorithms to automatically correct for small fetal movements during MRI and produce usable images.

These techniques show a huge amount of potential, and are an example of how the iFIND project is helping to generate exciting new technologies on its way to the ultimate goal: to improve the way we see developing babies in the womb.

Read previous posts about the iFIND project written by David Lloyd.

My trip to Parliament

Communicating your research to various audiences is a key skill for PhD students and early career researchers. One audience that biomedical engineering PhD student Simone Rivolo wanted to work with was policy makers and taking part in the SET for Britain competition was one way of doing this. Simone was shortlisted from hundreds of applicants to appear in Parliament and this is his take on the experience.

“Dear Simone, you have been selected to present your research at the Houses of Parliament.” Wow..Me? At Parliament? Seriously?

Let’s start from the beginning. How often do you read about how important it is to promote your research? How crucial it is to engage as many people as possible? I am up for it! Following advice from Alice, our Comms Manager, I submitted an application for the competition SET for Britain, which gives early-career scientists the opportunity to present their research to Members of both Houses of Parliament at Westminster, and I have been selected ! Let’s go to Parliament !

First step: buy a suit, shirt and tie, since the average PhD student looks are not much appreciated within Parliament. Done!
Second step: prepare a poster to present your research to MPs. Therefore, make it attractive but most importantly keep it simple. That’s hard, really hard. After a few sessions where my supervisor and I try to explain what we do in our scientific (dry, technical, probably boring) way, and Alice stares at us thinking “what didn’t you understand about keep it simple?”, the poster is ready.

Simone presenting his poster
Me presenting my poster

Here I am, on 9th March 2015 entering Parliament for the first time (and probably the last). It is huge, so many things going on, so many people running around. I slowly find my way to the conference room, hang my poster and nervously wait for the event to start. Will the MPs be interested? What will they ask? Will they find what I do cool?

The first MP walks towards me, looks at the poster and says, “it looks really nice, is it innovative?”. I didn’t expect this question. I smile and guide him through my poster convincing him about the originality of my work. After breaking the ice, everything flows naturally and a lot of MPs are interested in my work. Most of them have a relative or friend who had coronary heart disease (roughly my research topic) and would like to know what I am doing, how we can defeat it, where the research is leading us. That’s so nice, everyone is looking at you like you are The Expert, The Scientist! This doesn’t happen much during my PhD.

The 2 hours of the event quickly finish and I have a little time to enjoy the buffet, with all sorts of food and drinks (not bad being an MP).

It was an amazing experience. It teaches you a lot about how to communicate your research, how to engage people, how to keep their attention. It is so different from a conference. Everyone is relaxed, interested and positive. Nobody tries to put you down.

I strongly recommend everyone to submit next year and enjoy a trip to Parliament!