How close are we to Artificial Intelligence and Machine Learning being utilised in every day work?

AI is the current buzzword that we are all hearing on a daily basis, whether it is in a news article or at a conference, however understanding the implications of this technology, in the short, medium and long term is important to give it some context in relation to our daily work lives. Sarah Bennight, Director of Marketing at Stericycle Communication Solutions is quoted as saying ‘AI is everywhere. Every vendor seems to tout it, and every conference is filled with talk of everything AI. Folks tend to think that you throw in AI, and your paper gets published, your company gets funded, your product gets sold, and your customers’ interests get peaked. And therein lies the problem.

80% of Health executives agree that within the next 2 years, AI will work next to humans in their organisation, as a coworker, collaborator and trusted advisor, however 81% agree that organisations are not prepared to face the societal and liability issues that will require them to explain their AI-based actions and decisions, should issues arise (Accenture, Digital Health Tech Vision 2018).

To me, this sounds like ‘we know it’s coming, we just aren’t sure how we will handle it’, and that is probably true of many challenges we face on a daily basis. We have a vague idea of what is coming up in the near future, but it takes time and effort to dissect that into the day to day business of running an organisation.

One challenge that we have seen here in the Clinical Informatics Research Unit is around data quality, or often the lack of it. We have a team who work with hospitals to extract clinical data sets from Electronic Health Records and merge that with other datasets, in order to allow clinicians to link and query the information, for either research or audit purpose. A huge amount of time is invested in cleaning that data, identifying any outliers in it and addressing them. Even the question of ‘what is an outlier’ needs to be defined up front. Arm measurements can be recorded in CM’s, MM’s or inches (we’ve seen all 3). Alternatively some data points are clearly arbitrary, for example patients who are 1 cm tall and weigh 1 kg, the result of which can often be tracked back to the field being compulsory for someone to complete in the EHR, who doesn’t have that information to hand at the point of completion and just enters those values to reach the next page. Dr Sachin Jain, former CMIO at Merck and now CEO of CareMore Health explain to Forbes in January 2019 ‘The first thing we’ve learned is the importance of having outstanding data to actually base your Machine Learning on. In our own shop, we’ve been working on a few big projects, and we’ve had to spend most of the time just cleaning the data sets before you can even run the algorithm. That’s taken us years just to clean the datasets. I think people underestimate how little clean data there is out there, and how hard it is to clean and link the data.

Bias is another challenge inherent in machine learning. The algorithm will only be as good as the data model that it is trained on, and ensuring that is a big challenge. A worrying quote from Dr Dhruv Khullar in the New York Times said ‘In medicine, unchecked A.I. could create self-fulfilling prophesies that confirm our pre-existing biases, especially when used for conditions with complex trade-offs and high degrees of uncertainty. If, for example, poorer patients do worse after organ transplantation or after receiving chemotherapy for end-stage cancer, machine learning algorithms may conclude such patients are less likely to benefit from further treatment — and recommend against it.

Despite the challenges that lay ahead with AI and ML, the excitement surrounding it is unlikely to go away, and in the future, understanding the algorithms that govern decisions made by computers will be a core component of the governance of any organisation utilising them.

Certainly from an EDGE perspective, I think I am quite safe to say that we will monitor the developments in these technologies over time, and when, or most importantly if the time is right, implement them in a careful and considered manner.

In the meantime, if you want to have a play around with Machine Learning, there is an interesting model that you can use, provided by Microsoft, on the dataset of passengers on the fateful Titanic Voyage that can be found here

Behind the scenes with the Knowledge team

I think it’s a fair statement to make that my team are one of the hardest working and most dedicated teams I’ve had the honor to work with. They work tirelessly behind the scenes to make sure that the system continues to run, support is provided to everyone that needs it and at the same time making improvements left right and center to all aspect of what we do.

You might have heard of the term Kaizen, a Japanese concept for continuous improvement that began as part of the Toyota Production system, as a method to improve product quality. Well, that term pretty much enshrines what our team do every single day by constantly coming up with new ideas and new ways to change what we do for the better.

Seeing as so much of this goes on behind the scenes, and probably to a large degree unnoticed, I thought this would be a good opportunity to share with everyone a behind the scenes peek at what we are doing at the moment, and possibly dispel the myth that tech employees just sit around all day on beanbags, listening to David Bowie and drinking Cortado’s. We only do that on Fridays.

For the first time in history the majority of NHS Trusts are working together around a single research project record, bringing their collective information together to form a single view of that research. However, historic imports of data into EDGE from silo’d hospital research management systems has caused many duplicate records to be created in the system, meaning that these need to be reviewed and merged.

Since January our team has merged over 1,500 project records, taking a huge amount of time, care and considerable knowledge to carry out this task in order to help improve the quality of the information within EDGE. As our team come from backgrounds in R&D, Pharmacy, NETSCC, CTA’s and more, their knowledge of research allows them to carry out due diligence when doing these tasks that someone from a non-research background would struggle with. This is a nod to the skills our team hold and use in providing our services, and especially to Jen for her sheer determination to make this happen.

In the thread of continuous improvement, we are currently testing a new more complex automated matching process to studies at they come from CPMS. If this is a success we will release it into the Live system to reduce the burden of duplicate studies for everyone.

Over the past 7 years we have been pushing out a lot of new functionality into EDGE on a monthly basis in the drive to deliver the functions that people want to use. However the support guides in our support section have not quite kept pace with this change. Therefore the whole team are now working on reviewing all 170 guides, updating, re-writing or creating new versions where necessary and generally giving them the attention they deserve.

Currently we are in the process of migrating to a new email support desk system, that will deliver a whole range of improvements across the board when responding to queries and questions, and linking those to the new support articles, so keep an eye out for that. A huge amount of work has gone into setting this up and so again I’d like to thank the team and especially Lawrence for his knowledge and patience.

As well as this we are working closely with the development team on the concepts surrounding EDGE Version 3. It is easy to start dreaming about the new functionality that will be available in the system, however the developers do keep reminding us that, in house building equivalent terms, they are working out how deep to dig the foundations, so our team should refrain from telling them which colour we’d like the feature wall to be in the lounge. All of the new exciting functions will come in good time.

As I always find when writing these blogs, I reach the end of the page and have barely scratched the surface of variety of other projects that we are working on such as data security, integration opportunities, DSP Toolkit compliance, our new Blast Injury Research Network, our work with the WHO and World bank, our health informatics work in Sri Lanka and lastly the work we have done in in delivering an electronic medical record system to a hospital in Ethiopa. For more on these check out our Twitter feed @CIRUSoton

I will cover more in future blogs, but I will finish this one by mentioning our conference. If you haven’t already booked, I would highly recommend looking on our website https://edgeclinical.com/2020-conference . Our draft agenda has been released and is packed full of keynotes, break-outs and worked shops covering everything EDGE and research related. It will be a great opportunity to find out more about what we are doing, what is going on nationally and internationally in terms of research and to come and meet our team and collaborate together around the future challenges facing us all.

EDGEY's trip to Canada

It’s been a busy September for EDGEY who jetted off with James and Tim from the CIRU EDGE team to see his Canadian friends. EDGEY’s first stop was to Toronto to visit Rebecca Xu, James Schoales  and Steven Sundquist from the Canadian Cancer Clinical Trials Network (3CTN).

At 3CTN they discussed how CIRU and EDGE can help with Patient and Public Involvement and involving researchers from rural populations across the Province of Ontario. James Schoales showed the team some fantastic new and innovative ways to utilise the data from EDGE within Power BI to help better understand publications from research based within the 3CTN network.

From Toronto, EDGEY, James and Tim jetted over to Edmonton and then to the city of Calgary in the Province Alberta to meet with the fantastic team at Alberta Innovates led by Tammy Mah-Fraser. Over the course of three days the team heard about some exciting initiative within the province including from the Alberta Supporting Patient Orientated Research unit (AbSPORu). AbSPORu offer support services for researchers looking for assistance with initiating research, gaining access to support services like data analysis, translating research impact and applying for grants. This data is then transposed to EDGE where the study is worked up to opening in collaboration with Alberta Innovates.

The week was rounded off with James speaking at the Alberta Clinical Health Research Conference about the Future of Clinical Research looking at exciting innovations in AI and machine learning and how these may influence more intelligent use of data in Clinical Trials and Health Care.

It was a very informative week across the Atlantic for EDGEY who has returned to the office enthused with some great ideas and user stories to tell.

Blog post written by Tim Gibbons,
International/Specialist Project Manager, CIRU
University of Southampton

EDGE & the CPMS project

It was the 9th October 2015 when an email landed in my inbox inviting me to an initial teleconference with the NIHR Coordinating Centre. It was to discuss a proposed integration between EDGE and CPMS. My usual positive attitude kicked in and I thought ‘Hmmmm, that’ll be a nice project for a year or so, how complicated could it be’. Underestimation is a dangerous thing however, which I have learnt many times, usually when starting DIY projects in my house and telling my wife things like ‘the shower will be fixed in an hour or so’, only for it to still be in pieces on the floor a few days later. So as you can imagine, both to my surprise, and not to my surprise at the same time, 3 and a half years later this interface project is still in progress.

In my rather varied career history, I used to run critical incidents in the Kent Police Control Room, such as firearms incidents and large scale public order events which were constantly evolving and each had many moving parts to take into account. I’m therefore used to pressure and stress, aware of the need to dynamically risk assess the situation constantly, keep in mind the bigger picture whilst also trying to complete the task in hand. This has perhaps stood me in good stead for this integration project.

Despite this being the most complicated project that I have ever worked on, I believe it has actually delivered benefits beyond its original design. It has brought our team, the Clinical Research Networks and the Coordinating Centre around the table on an almost weekly basis, in turning building a very close working relationship with everyone involved and developing a much deeper understanding around how we each function. Although we haven’t been able to engage with every Trust in the integration work, we have always involved as many as possible in the conversations to ensure that everyone has a voice in the changes being made.

As Newton said, every action has an equal and opposite reaction, and this cannot be denied. The concentration of our workforce on delivering the CPMS integration has meant that other aspects of our teams work has had to play second fiddle, often meaning that engagement through platforms like ideascale has reduced, or the ability for our team to set up user groups around areas of special interest.

So on a positive note, we are currently in the throes of recruitment, meaning that soon we will be able to re-continue all of the engagement work that enables us to work alongside you all in understanding your business, your processes, your problems and your aspirations in order to deliver the best solutions possible in EDGE.

CONNECTED EDGE Conference 2019

Firstly, I would like to say a massive thank you to everyone who attended our 2019 conference CONNECTED, which allowed the EDGE community to learn, share, network and to more importantly get connected. There was a real buzz and great atmosphere across the 2 days. It was nice to see people from all over the UK, Canada, Belgium and New Zealand all in the same place, building relationships and connecting through the use of the EDGE system.

The event this year was again hosted by BBC Medical Correspondent Fergus Walsh, who was very popular with our audience, making them laugh as well as not being afraid to ask some challenging questions to our speakers. We had some brilliant keynote speakers with experience ranging from clinical to business intelligence to sponsorship. Clare Meachin, Associate Director of Nursing, NIHR CRN CC and Deputy Chief Operating Officer from CRN South London really stood out to me. She was a confident speaker who reminded our audience why data is so important to research and to the patient with her talk titled “Close to the EDGE- why does all this matter to the patient?”

Throughout both afternoons we hosted a number of breakout and workshop sessions to cover all aspects of EDGE. These were ran by EDGE experts amongst the community as well as by some of our EDGE Knowledge team. There were topics to suit every research job role whether you worked within a support department such as pharmacy or radiology, clinical nursing team or R&D department.

In keeping with the CONNECTED theme we tried out some new aspects to the conference this year. We added a QR code to each delegate badge so that connecting would be easier. Following a quick download of an app and a scan of a code you would be able to save details of someone you spoke to instantly to your phone. We also colour coded each delegate badge to help identify other members of the EDGE community working in a similar job role. These colours were then used in the ‘Get Connected’ zone, a designated space for connecting after lunchtime.  

The networking dinner took place on the first night, where not only did delegates receive some delicious food but they also took part in our traditional EDGE quiz, followed by a special awards ceremony which showcased some of the fantastic work that certain individuals and organisations have been doing with EDGE. We then had some music from a band called the Altitudes to finish off what was a great evening.

Overall, it was a successful conference and we are all very happy with how it went. We are looking forward to planning next year’s event so keep a look out for the 2020 news! Oh, and one last thing. For those of you who spoke and received an EDGEY, please look after with care! 

Exploration of EDGE Functionality

Our use of technology and the role it plays in our lives is increasing, both in and out of the workplace, with it even reaching levels of addiction in some instances, case in point where the World Health Organisations now includes a classification of ‘Gaming Disorder’ in their new International Classification of Disease (ICD-11). 

This raises an important question about how effectively we use technology and how that technology benefits us in return, especially within the workplace where most often the technology is provided to us, rather than being chosen by us. The Health Secretary Matt Hancock is a big advocate of digital technology and has already expressed a strong desire to unlock its full potential in the NHS, after describing it as the “worlds most frustrating place to work for its IT” at the Health and Care Innovation Expo in Manchester. 

Here in the Clinical Informatics Research Unit, our Knowledge Officers spend a lot of time working with hospitals and research organisations to ensure that the systems they use provide them with maximum benefit, helping them to understand the full range of functions available. This includes how they can utilize it in different ways in order to streamline processes and improve operational efficiencies, or in layman’s terms just making it more useful and helpful. 

Every organization uses the system differently, and subsequently every organisation will experience different benefits. This is not to say that the system is different between organisations, it is after all the same system, instead it is down to the heterogeneity of each organisation, notably which other systems are already being used, and how, in this case, EDGE has been implemented. 

Part of what we do as a team, and as a community is to share best practice and we see this in so many different areas, most recently with primary care and pharmacy groups being created, and this cooperative working is not limited to the NHS. Colleagues using EDGE from Canada are just as willing to share their work and are just as receptive to the innovations from the UK because, lets face it, we are all trying to provide the best environment and best infrastructure to provide opportunities for patients to take part in research. 

Something that I have noticed on my travels is that there are sometimes functions in EDGE that people didn’t realise were there, or maybe didn’t see how they could really benefit them. This is where I intend to offer out some advice on different aspects of how the system can be used over the next few months, to ensure that people can make the most of the system and ultimately to make sure that the technology is effective, is benefiting peoples work and ultimately reduces the view that the NHS, or other healthcare providers are ‘frustrating places to work for its IT’. 

In this first instalment, I bring some work from Gaurika Kapoor, Operations Manager at Alder Hey Clinical Research Facility, in which she has created an Entity on EDGE for the purposes of collecting data for their NIHR CRF Annual Reports. This is going to be used to standardise their approach to capturing the information and providing a central place for reporting. 

This has now been published into the Global Library, for all EDGE Admins to download if they so wish and can be found on EDGE by going to LIBRARY > ENTITIES > ADD GLOBAL ENTITY > click ‘CRF’. 

Once you click on it a copy will be downloaded into your library, allowing you to add, edit or delete sections in order to use it for your own data collection requirements. *And just to clarify, changing your version of it will not affect anyone else’s copy. 

There are many other Entities available in this library which have been shared by organisations who believe they would be useful to others, so go and check it out and see if anything you like. On a side note, over time this library has become quite busy, so I will add a ‘to do’ to my list and see if we can clean this up a bit. 

Thanks for reading and keep watching out for the next series, where I will go into more depth around other functions that you could use in EDGE.