Big data is all around us, but how can it be best used to enhance the veterinary profession?
“It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts” – Sherlock Holmes, A Scandal in Bohemia
When the ancient Incas wanted to store data, they used khipus, or ‘talking knots’, to encode numeric information with pieces of string. Creating khipus was a laborious task and it took at least a year to master the basic skills, but once this expertise was gained, these ‘data archives’ could be used for tax records, census data, or even the organisation of the military.
Today, according to IBM, 2.5 quintillion bytes of data are created worldwide, every 24 hours. The sources of these data are varied and ubiquitous, rapidly becoming integral to just about every aspect of our lives. From Fitbits to CCTV cameras, society is being observed, measured and analysed in ways that can often seem like science fiction. Throw in the long trail of digital breadcrumbs that you leave as you use your mobile phone, credit cards and social media accounts, and you can be sure that Big Brother has you in his gaze.
With this deluge of data, however, comes a long list of challenges, such as how to store it, how to analyse it, and how to share it. Often, such questions must be answered quickly, as once a stream of ‘big data’ is tapped, haemorrhaging or misusing such a commodity can be disastrous for the commercial or scientific questions in mind. The answers come in the form of a multitude of IT tools, programming languages and data management processes, which many industries are rapidly corralling in order to steer themselves into the 21st century.
The veterinary industry is no exception, being awash with data ranging from clinical notes and blood test results to medical imagery. Organisations such as SAVSNET and VetCompass are working hard to collect and share such data, leading to the publication of a wealth of clinically relevant papers, but it’s early days and the task at hand is immense.
The collection and analysis of future data will be crucial to many industries, but what many organisations fail to realise is that they may be sitting on a wealth of valuable data already. For some this will be in the form of paper records, meticulously kept for years or even decades. For others, the data will already be digitised, archived away and destined to reside forever on some long forgotten hard-drive.
Our mindset should be that this is a great waste rather than a minor shame, because such data could, beyond simply providing interesting insights, lead to a direct improvement in patient care. In other words, such dormant data could save lives. Couple this with the potential financial gain stemming from the related business analytics, and you start to see the benefits of disturbing this digital sleeping-giant.
Many people are realising that the world’s latent data is potentially valuable. Take, for example, the History of Medicine Corpus Annotation (HIMERA) project. This is an attempt to annotate digitised medical records stretching back to 1840, with the aim of employing text-mining techniques to unearth lost data on disease. Such knowledge can then be merged with modern records, expanding the breadth and depth of medical understanding.
This raises a question for you. What data do you have that’s currently sitting in a filing cabinet, Excel spreadsheet or in your practice database that you’ve never looked at? These data could answer the following questions for your practice, just to name a few,
• What is the breakdown of disease types you’ve seen over the last 10 years?
• What treatments were given and under what circumstances?
• How many cases were seen again? Are there any patterns here?
• How do these diseases change over time? Are any of them seasonal?
• How about geospatially? What happens when you plot disease type according to client postcode?
Perhaps such data will show nothing of interest, or maybe it will simply reinforce existing hunches and suspicions. But more likely, it will offer a unique perspective and understanding that was previously unavailable, bespoke to your practice.
Data is said to be the commodity of the 21st century, but as of today, there is a chronic underappreciation of what many organisations have locked away. I would encourage you to take a look at what you have and consider what questions you could ask of this valuable, untapped resource. As the veterinary profession moves towards a future of increased research for practicing vets, there can be no doubt that the need to exploit such data looms large on the horizon.
If you’re not sure where to start, Avacta would be more than happy to work with any practices that would like to explore their data further. All data could be anonymised and any analysis placed under strict confidentiality. Projects could range from simple exploratory analysis to more detailed studies, perhaps with scientific publication in mind.
If you are a veterinary surgeon and you’d like to discuss this further please contact us.
If you are part of the veterinary profession and would like to receive regular information regarding veterinary data or other articles specific to your areas of interest then please click here