Clinical automation, a snapshot

In the third of their series of blogs about Optometry Tomorrow 2017, Clinical Adviser Daniel Hardiman-McCartney and Head of Research Martin Cordiner discuss how clinical automation is about to impact practice.

Share options

Author: Daniel Hardiman-McCartney MCOptom, Clinical Adviser and Martin Cordiner, Head of Research
Date: 14 March 2017

What does automation mean? You may be thinking robots, automated refraction booths or sight testing smartphone apps, some of which may be with us over the next few years. But in this blog we would like to step away from robots and think about how automation is starting to change clinical practice right now and will form part of the incremental journey to clinical automation. Although we will see that knowing how to program the machines is crucial.

Software has been developed that can detect retinopathy from a retinal photo: in fact the software has been around for almost a decade, but only now are we seeing the results from large trials assessing its accuracy and cost effectiveness. Adnan Tufail and colleagues have recently published a study that confirmed two programs could assess diabetic retinal images. The software can automatically assess the image and assign one of the following categories to each one: upgradable; retinopathy, maculopathy, pre-proliferative or proliferative (and as reliably as a good human grader with a 95% confidence interval).

So not only is the software available, it is now independently validated, and is likely to become part of the diabetic screening pathway within the next couple of years. With 4.5 million people living with diabetes in the UK, such software could free up a lot of clinical time and expertise, not to mention the huge potential for grading in parts of the world where there is a shortage of skilled practitioners.

But how about combining test information? A challenge facing those who work in glaucoma triage is putting together the results from a handful of tests into one objective outcome. The Glaucoma Automated Test Evaluation (or GATE) study, a recently published health technology assessment, investigated whether the diagnosis of glaucoma patients could be objectively made and automated. It concluded that technologies can be an effective aid to diagnosis and, when combining imaging, IOP and VA, a cost-effective substitute to current medical triage. However, unlike diabetic retinopathy, where there is a compelling case for automation now, in glaucoma the benefits of automation are currently more nuanced, as the specificity (more about sensitivity and specificity) of the software is not as high. The study also looked at the cost effectiveness of automated triage and found the benefit to be marginal, however a drop in the price of newer imaging technologies such as OCT could make the case more compelling. 

When it comes to AMD, though, there is more research to be done on our own performance. It may surprise many optometrists reading this to hear that currently the sensitivity and specificity of various AMD tests are not independently validated, and as such their cost effectiveness is unclear. The Early Detection of Neovascular AMD (or EDNA) trial is due to be published in 2020 and aims to determine what the optimum non-invasive test strategy would be to robustly detect neovascular AMD. The study evaluates the sensitivity and specificity in the diagnosis of neovascular AMD of evaluating VA, patient visual self-assessment, fundus assessment, Amsler and OCT, comparing these against the gold standard of ophthalmologist examination. The EDNA study will give the robust information we need to decide what methods are most effective, but also how cost effective they may be, but this is crucial prior to exploring further the viability of automation for AMD.

This brief peek at the current research around three different areas of potential automation suggests a somewhat mixed picture for different conditions. It is interesting to consider how much useful information could potentially be mined from retinal photos and how much more we need to do in order to robustly introduce OCT into eye care pathways. To find out more, Prof Craig Ramsay, a lead author of the GATE and EDNA studies will be presenting at Optometry Tomorrow 2017 on Monday 20th March at 11:30am.


Optometry Tomorrow 2017


Daniel Hardiman-McCartney FCOptom
Clinical Adviser, The College of Optometrists

Daniel graduated from Anglia Ruskin University, where he won the Haag Strait prize for best dissertation. Before joining the College, he was Managing Director of an independent practice in Cambridge and a visiting clinician at Anglia Ruskin University. He has also worked as a senior glaucoma optometrist with Addenbrooke’s Hospital in Cambridge, with Newmedica across East Anglia and as a diabetic retinopathy screening optometrist. Daniel was a member of Cambridgeshire LOC from 2007 to 2015 and a member of the College of Optometrists’ Council from 2009 to 2014, representing its Eastern region.  

He is Clinical Adviser to the College of Optometrists for four days each week, dividing the remainder of his time between primary care practice and glaucoma community clinics. Daniel is a passionate advocate of the profession of optometry, committed to supporting all members of the profession and ensuring patient care is always at the heart of optometry. He was awarded Fellowship by Portfolio in December 2018.

Martin Cordiner
Head of Research, College of Optometrists

Martin graduated with a Masters in Modern History from York University in 2005, having completed his BA there in 2003. Since then he has worked in project management in higher education before joining the College and its fledgling research department in 2009, where he now supports the Director of Research and manages the research team to implement all elements of the College’s Research Strategy. 


Return to blog listing

Enter a comment below