How to innovate

Where do new ideas come from? Collaboration is a good place to start when it comes to innovation, as we discovered when we talked to our medical client about their wound care provision.

Progress doesn’t always come from a clearly delineated problem. Sometimes it’s more a case of “here’s a few issues we’re facing, here’s where we think we’d like to end up in the future” and together we take it from there.

After learning more about our client’s business, we had a few ideas about how applying AI to how they currently worked could help them. We knew AI could help not just in the short term, improving the way customers used their products, but also to fast-track them to a future where they take the lead in delivering data-driven patient outcomes.

The idea involved building a bespoke AI application, which used computer vision/image recognition to help customers identify the right wound dressing to use. It would speed up diagnosis, identify appropriate treatment, and ultimately, improve patient outcomes. By working together – their industry knowledge along with our technical expertise – we were able to help our client innovate in their sector.

The challenge

There were two main issues. Firstly, how to ensure the client’s wound care products were being used correctly, for the optimum results? Was there a way to help clinicians identify the right dressing for a wound, in real time? The second, larger issue was how to move forward from simply making and selling a product for clinicians to use, and instead offer their customers real added value to achieve more data-driven decision-making in healthcare?

Current practice relies on a clinician visually assessing a wound to decide which dressing to use. Efficacy can vary, depending on the experience of the clinician, availability of product, nature and type of tissue in the wound, and a number of other factors. Without a visual record of each wound treated, it’s also hard to make any meaningful or standardised analysis of treatment and success rates in the longer term.

Could a collaborative approach to innovation using AI solve these issues?

The solution

We built a custom AI solution to assist with wound hygiene. We wrote algorithms to segment and classify images of wounds, identifying and categorising metrics like the extent and type of wound tissue - e.g. infection, maceration, slough etc.

The tricky part was not only to identify whether these tissue types were present, but also to identify exactly where on the wound they occurred, labelling the boundaries of each tissue type on the image itself. Using pre-labelled training data for supervised learning, the algorithm could then identify and advise the appropriate course of treatment and dressing. Clever stuff.

Of course, having a human in the loop is still important, so we built in a feedback system for users to either accept or reject recommendations, which over time further improves the accuracy of the system. Correct classifications strengthened the data set; rejected ones were queued for manual review by clinicians.

All this data allowed for much more meaningful reporting on patient outcomes. With complete and standardised records of wounds and wound care, users could now more accurately compare treatments, and predict the time it should take a patient to heal.

With this knowledge, you also become much better able to predict supply and demand of wound care products, and forecast more effectively. All round? It means a tighter grasp of how patient outcomes impact commercial decisions, for both users and suppliers of medical technology.

Our system opens up a whole new set of possibilities for our client, to offer data-driven and AI enabled benefits to their own customers, setting them ahead of the competition.

We know this is how it all starts, and when we say ‘all’, what we mean is the future of healthcare and medical tech. Taking the leap into AI to solve your short-term problem is the first step on the way to innovating in ways you’ve not even thought of yet.

Maybe we should talk about what AI could look like in your business?

Our other case studies:

Making better decisions

How AI improved personalised healthcare using genetic data

If you identify a gap in your services, could AI be used to speed up the decision making process on what a potential solution or product could look like? That’s exactly what we helped our healthcare company client to achieve.

Reaching big goals with simple automation

How OCR unlocks possibilities in medical tech

Sometimes the way to achieve the really clever, complicated stuff is to actually do one very simple thing first.

AI as a Service

Filtering explicit content quickly and cost effectively.

How common is the problem you need to solve? When our client came to us asking for help filtering out inappropriate adult content from their site, we were pretty confident they weren’t the first to need this tech.

Do more with your data

Speed up reporting with data warehousing

How much more could you be doing with your data? This was the question we asked our client, Regital, a digital agency specialising in programmatic advertising, when they asked us to help speed up their reporting processes.

Automate to improve

How AI helped enable faster benefits and council tax claims

Lots of clients know that AI can probably help speed up their processes, but aren’t sure what is possible, or how to start. Demonstrating how automation can improve efficiency for local government.