Exploring AI with Reena Chopra

The Hospital Optometrists Annual Conference (HOAC) will return this month as an online event, with a day of CET-accredited webinars and peer discussions.

Hosted by the AOP, the virtual event will take place on Saturday 25 September and will be supported by Menicon and No7 Contact Lenses.

The webinar programme offers the opportunity to earn four interactive CET points, with sessions looking at topics ranging from ocular oncology referral, emergency eye care, and new perspectives on glaucoma, to the use of artificial intelligence (AI) in predicting eye disease.

The AOP has highlighted that webinar sessions are open to all, including hospital optometrists and those who are considering working in the hospital environment, as well as those practising in other settings.

To get an insight into the webinar topics set to be explored, OT spoke to Reena Chopra, research optometrist at Moorfields Eye Hospital, who will be leading the session: Artificial intelligence to predict disease from ocular images.

The session will cover advances in classifying and predicting eye disease and systemic disease from ocular images using artificial intelligence, and how this area of technology relates to the clinical management of patients.

Ask the speaker: Reena Chopra, research optometrist at Moorfields Eye Hospital

Could you tell us what the focus of your session at HOAC on Artificial intelligence to predict disease from ocular images will be?

Imaging is becoming an essential component of the eye exam both within specialist centres and in the community – however these images can be quite complex to interpret and in many countries there are simply not enough experts to review all of these images. This session will cover the use of artificial intelligence (AI) to address this problem, by using AI to classify eye disease from ophthalmic images. We will additionally cover more recent uses of AI to uncover new signals within eye images to provide a deeper understanding of disease progression and the relationship between the eye and the body.

I’m excited by the prospect of using AI to support clinicians and research

With your research having demonstrated the potential for AI to help improve the understanding of disease progression and predict risk in patients with wet age-related macular degeneration (AMD), what do you think might be next for either the application of this, or for further research?

Our work builds upon promising early work to develop predictive models for wet AMD based on retinal photographs and optical coherence tomography scans. Before this can be deployed within clinical practice, it is essential to validate that the AI performance is maintained in different populations and using different devices. Robust clinical evaluation also needs to take place, akin to how we might test new therapeutics – we need to ensure the AI is safe, effective, and positively impacts quality of care and patient outcomes.

Where do you see the key applications for AI in predicting disease in optometry and ophthalmology?

I’m excited by the prospect of using AI to support clinicians and researchers. These systems could help detect disease earlier and inform the clinical understanding of their progression. A prediction system could be used to inform appropriate follow-up intervals to effectively manage high-risk patients. Preventative treatments are also undergoing clinical trials – although these are not clinically available yet – AI systems may have a role in identifying patients that might benefit most from these therapies.

What do you hope attendees will take away from the session?

That the utility of AI is not in automating our work, but in its ability to support clinicians, detecting disease earlier, and improving patient outcomes.

To read more about the future of AI in optometry, take a look at OT’s interview with Reena Chopra and ophthalmologist Pearse Keane.