Artificial intelligence in optometry: predicting the future

Optometrist and researcher Reena Chopra MCOptom discusses her work using AI systems to estimate the progression of wet AMD patients.

Share options

Author: Reena Chopra MCOptom
Date: 20 August 2020

Technology is transforming healthcare. Health records are being digitised, big data is being rapidly aggregated and analysed, and digital communication is transforming the way we connect with patients and deliver healthcare. In the future, it is likely that automation and artificial intelligence (AI) will re-engineer medicine to cope with some of the pressures of increasing demand and strained healthcare systems.

Ophthalmology has become one of the most technologically driven medical specialities. In particular, imaging has transformed our understanding of eye disease. Over the last two decades, the use and availability of optical coherence tomography (OCT) has increased rapidly. During my PhD (part-funded by the College), I explored how we can provide automated, quantitative measurements using a new type of OCT termed ‘binocular OCT’. With new technologies such as this, we can exploit our imaging devices to quickly produce objective data for several aspects of the eye exam, including measurement of strabismus1 and the pupil reactions2, in addition to whole eye imaging3.

Ocular images are information-rich, and conceal a surprising amount of information that even the most experienced clinicians cannot detect. From a fundus photograph alone, AI can identify an individual’s biological sex, cardiovascular risk factors4, and refractive error5. So far, AI has been primed to predict events at the time that the image was taken. But can we develop an early warning system that uses images to predict the future onset of disease?

In our latest work, a collaboration between Moorfields Eye Hospital, DeepMind, and Google Health, we trained an AI-system to predict whether a patient with wet AMD in one eye will develop the condition in their second eye6. Within two years of diagnosis, 20% of patients develop wet AMD in their second eye – often the better-seeing eye that individuals rely on day-to-day. The period before the development of wet AMD may be a critical window for planning of follow-up intervals, and even for potential administration of preventative treatments that are currently in clinical trials.

In the future, it is likely that automation and artificial intelligence will re-engineer medicine to cope with some of the pressures of increasing demand and strained healthcare systems.

For this work, we curated an anonymised dataset from Moorfields of patients receiving treatment for wet AMD in one eye. We used OCT images of the fellow eye at each treatment visit. These images were input into a two-level AI system. The first level segmented the OCT image into several different features, such as drusen, retinal pigment epithelium, and hyperreflective foci. The second level input both the raw OCT and the segmented image from the first level. The output of the system provided an estimate of a patient’s risk of progressing to wet AMD within the ensuing six months.

As this task is not routinely performed in practice, clinician performance for future prediction was unknown. We recruited three ophthalmologists and three optometrists specialising in Medical Retina to make similar predictions, firstly using the OCT alone (akin to the AI-system), and secondly using the OCT, fundus photograph, and all available clinical information (replicating a real-life clinical scenario). We found that clinicians could perform this task but with substantial variability in sensitivity (proportion of positives correctly identified) and specificity (proportion of negatives correctly identified) among them. The AI system had significantly better sensitivity and specificity than five out of six specialists.

One significant benefit of an AI system is that it can be tuned to the clinical application. In the paper, we discuss two operating points based on specific sensitivity and specificity thresholds. This impacts the number of false positives. If one was considering an invasive preventative treatment, the operating point could be tuned to reduce the false positive rate. Whereas, if the system was simply informing follow-up intervals, a more liberal operating point might be chosen where the sensitivity is greater but also allowing more false positives. Another benefit of this system is that it produces segmentation maps as an intermediate step. These maps enable clinicians to visualise the longitudinal changes in macular morphology, and may improve the understanding of disease progression.

These findings demonstrate the potential for AI to help improve the understanding of disease progression and predict the future risk of patients developing sight-threatening conditions. Both automation and AI could also usher in a new era of comprehensive eye care that has the potential to transform the practice of ophthalmology.

Reena Chopra MCOptom

Reena Chopra is an optometrist at Moorfields Eye Hospital, a clinician scientist at Google Health, and is studying a PhD at the UCL Insitute of Ophthalmology.

Back to blogs listing.

Tell us your views...

 

  1. Chopra R, Mulholland PJ, Tailor VK, Anderson RS, Keane PA. Use of a Binocular Optical Coherence Tomography System to Evaluate Strabismus in Primary Position. JAMA Ophthalmol. 2018 Jul 1;136(7):811–7.
  2. Chopra R, Mulholland PJ, Petzold A, Ogunbowale L, Gazzard G, Bremner F, et al. Automated Pupillometry using a Prototype Binocular Optical Coherence Tomography System. Am J Ophthalmol [Internet]. 2020 Feb 27; Available from: http://dx.doi.org/10.1016/j.ajo.2020.02.013
  3. Chopra R, Mulholland PJ, Dubis AM, Anderson RS, Keane PA. Human Factor and Usability Testing of a Binocular Optical Coherence Tomography System. Transl Vis Sci Technol. 2017 Jul;6(4):16.
  4. Poplin R, Varadarajan AV, Blumer K, Liu Y, McConnell MV, Corrado GS, et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng. 2018 Mar;2(3):158–64.
  5. Varadarajan AV, Poplin R, Blumer K, Angermueller C, Ledsam J, Chopra R, et al. Deep Learning for Predicting Refractive Error From Retinal Fundus Images. Invest Ophthalmol Vis Sci. 2018 Jun 1;59(7):2861–8.
  6. Yim J, Chopra R, Spitz T, Winkens J, Obika A, Kelly C, et al. Predicting conversion to wet age-related macular degeneration using deep learning. Nat Med [Internet]. 2020 May 18; Available from: http://dx.doi.org/10.1038/s41591-020-0867-7 
OK
Loading...
Loading...
Loading...