Telemedicine ushers in new chapter in eye care

Lynda Charters

Research teams in various countries are pioneering different methods of data processing and deep-learning AI to create new models of care.

This article was reviewed by Thulasiraj Ravilla and Dr Angus Turner.

New image analysis and artificial intelligence (AI) technologies have dramatically increased the options for opthalmological diagnosis and care in different settings, from cities to the most remote communities. Dr Mingguang He, a professor of ophthalmic epidemiology at the University of Melbourne in Australia, has described his work in deploying AI in a telemedicine service to provide clinical care.

“Ophthalmology is a highly image-driven specialty,” he said, adding that it lends itself to telemedicine and AI platforms. Dr He used about 70,000 images to train a neuron algorithm that focuses on identifying diabetic retinopathy (DR), age-related macular degeneration (AMD) and glaucoma. Establishing the AI platform involved data harvesting images and labelling diseases and their severity in those images.

Regarding the DR screening classification, internal data validation indicated that the accuracy of the AI algorithm was good; validation of the accuracy in multiple ethnic groups was also very impressive.1 The team repeated this work for glaucoma classification2 and achieved excellent accuracy. They also achieved very good accuracy for AMD.3

Related: AI-enabled radar: Pushing boundaries of glaucoma diagnosing, monitoring

A heat map study4 of deep-learning technology proved that AI can accurately classify diseases based on similar features used by clinicians. Dr He’s team then established websites to which clinicians could upload clinical images with diagnosed diseases to see how well AI did in identifying them.

“Most studies reported robust accuracy of the AI classification. Many require real-world validation,” Dr He explained. “The current project targets four major diseases, and many are trying to create more algorithms to make the diagnosis more accurate or include more diseases.”

He continued: “Another area of interest is making an automated care model. Deploying AI in the real world in medicine is challenging and involves more than the neural network, such as many medicolegal issues and patient and doctor interactions.”

Singapore: new models of care

Dr Gavin Tan, associate professor at Duke-NUS Medical School, Singapore National Eye Center, Singapore, has created a new model of care for DR screening. “In ophthalmology, [we have embraced] multimodal digital imaging: that is, fundus and slit-lamp imaging and optical coherence tomography, all of which can be delivered remotely to facilitate decision making,” Dr Tan said.

Dr Tan and his team combined teleophthalmology, AI and standard fundus cameras to evolve from the traditional prints or slides to digital media. As he described, the DR diagnosis did not require additional clinical data, the technology provided robust outcomes and cost-effectiveness, and there was less resistance to change by ophthalmologists. In addition, the AI training was easy because of the extensive available clinical data.

Related: Measuring visual fields with cloud-based AI platform

The Singapore Integrated DR Programme, the bones of which were image capture sites, transmission to a reading centre for grading and the sending of reports to primary care physicians, covers 150,000 diabetic patients. All the image data collected were used as a basis for the AI program, which was seen to make its decisions in a similar way to clinicians, Dr Tan said, with an accuracy of 93.6%.5

The AI program was integrated into the team’s clinical screening system. The primary grading system is currently being replaced with the AI linear system (SELENA), although the images belonging to patients who are being referred for care are still graded by human evaluators, to maintain the highest sensitivity and specificity.

In addition to screening, the programme includes two-way video consults; one-way virtual clinics in which physicians can review notes and future management is implemented if needed; and home-monitoring devices used by patients to cut travel time and make appointments as needed.

Dr Tan’s group has also established a virtual clinic to monitor stable retinal disease that has blossomed as a result of COVID-19. Patients are classified as having high-intensity active disease requiring monthly treatment, or as having stable disease – the latter representing 30–50% of the population. The virtual clinic allows history taking, visual acuity (VA) measurements, and imaging remotely, followed by review by technicians and by physicians for management if needed.

Related: Technology 'perfect' for pediatric neuro-ophthalmology diagnoses

The AI system, in many cases, can be better than physicians in identifying peripheral pathologies such as proliferative DR. In addition, the imaging clinics can be combined with video consultations, as Dr Tan did with the glaucoma service at the Singapore National Eye Center.

Looking to the future, Dr Tan and his colleagues are looking to start trials whereby patients’ VA can be measured using mobile applications. They have also started home-monitoring applications that do not require patients to travel for evaluation.

An application called Alleye (Oculocare Medical Inc.) is a pilot home-monitoring device that lets patients determine whether their VA has deteriorated asymptomatically, facilitating early recognition of recurrent disease. Alleye was tested in about 700 patients with several diseases. Over 6 months, 33 patients had triggers, seven of which were significant, and five had disease progression.

Related: 60 years of laser technology

Dr Tan concluded, “Digital technology can transform eye care. Telehealth and AI are highly connected, synergistic technology platforms. Teleophthalmology is successful in screening for DR. AI in ophthalmology shows good performance for specific tasks.”

He added: “Real-world application requires further development and integration. Mobile devices and home monitoring have long-term potential in future eye care.”

India: Telemedicine to service millions

Thulasiraj Ravilla, director of operations for Aravind Eye Care System (AECS) in Madurai, India, has described how he and his team used telemedicine to provide eyecare to millions of Indian patients. “Eyecare services tend to be urban-centric; our challenge was to bridge the divide to reach patients everywhere,” he said.

Mr Ravilla developed a four-pronged approach to achieve his goal: focus on community need, comprehensive and high-quality eye examinations, closing the care loop to ensure appropriate intervention, and remote management. “We see three roles for technology: support the caregiving process, manage all associated processes from finance to human resources and monitor the entire process,” he said.

AECS first built an electronic medical record (EMR) in the cloud for simultaneous collaboration between ophthalmologists and the remote vision technicians in rural vision centres. All patient information, including history and investigations, is entered live into the EMR. This information, combined with real-time conversation with the technician and patient through a telemedicine link, facilitates diagnosis and enables the ophthalmologist to generate the appropriate prescription for spectacles or medicines.

“This technology-supported design closes the care loop within the local setting, and thus enables better adherence by the patients,” Mr Ravilla said. The vision centres also use AI in the system: a retinal image is uploaded into the cloud and a reading is generated in seconds, giving the severity of the diabetic retinopathy. This technology, as it evolves, can also be used to monitor chronic disease progression.

Related: Responding, adapting to COVID-19 protocols in the UK

Mr Ravilla estimated that the network of 79 vision centres covers 6.9 million people. In addition, AECS also has a mobile screening van with a RetCam Shuttle (Clarity Medical Systems, Inc.) to screen for retinopathy of prematurity; using custom-built software, the images are uploaded to the base hospital for review.

“Technology is emerging as a great enabler and makes it possible for millions of people to get good eyecare locally. However, the technology needs to be robust, reliable, simple to learn and use, and inexpensive, in order to make financial sense in rural remote settings, where the scale is low,” he emphasised.

Western Australia: accessing remote Indigenous communities

Western Australia has a sparse population spread over vast distances, with some patients travelling 10 hours to obtain surgical services, said Dr Angus Turner, of the Lions Eye Institute in Perth, Australia. Dr Turner stressed the challenge of accessing these individuals, who have the same needs as everyone elsewhere but with higher prevalence of disorders because of the gaps in services.

The traditional service had patients travelling hours to reach a specialist for a diagnosis of a cataract, for example, then returning home and waiting 1–2 years for a cataract procedure. Eliminating the preoperative and postoperative visits in this scenario was key to patients obtaining the needed services.

Optometry and ophthalmology work hand-in-hand in Western Australia. The optometry service is extensive in the Indigenous population and optometrists visit the primary care settings. “This is key to our telehealth service. The optometrists perform the evaluations and provide the intimate knowledge about what I need to do surgically or what is required to manage individual patients,” Dr Turner said.

Related: Putting new technologies into practice not perfect science

Telehealth in Australia has focused on diabetic retinal screening for decades and has more recently introduced real-time video consultations. A mobile van service provides specialist outreach services, and the examination equipment is carried from place to place to facilitate those services.

The video consultations began in 2011 as a result of the Medicare Initiative and optometry was included in 2015. The system allows the optometrist to evaluate the patient at one end with the video running with the specialist viewing it at the other end.

Dr Turner explained that the initial barriers to the consultation were not technology and cost, but rather the availability of an on-call specialist, the scheduling of two health professionals and the patient in a room at the same time, and the alignment of the EMR and the images.

COVID-19 has presented a complication, with travel restrictions imposed during the pandemic. Resident optometrists have set up clinics in hospitals and used the dormant equipment, while telephone interviews, especially for blind patients, have been used more. As a result, consultations during 2020 increased by 47% with telehealth.

References
1. Li Z, Keel S, Liu C, et al. An automated grading system for detection of vision-threatening referable diabetic retinopathy on the basis of color fundus photographs. Diabetes Care. 2018;41:2509-2516.
2. Li Z, He Y, Keel S, et al. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology. 2018;125:1199-1206.
3. Keel S, Li Z, Scheetz J, et al. Development and validation of a deep-learning algorithm for the detection of neovascular age-related macular degeneration from colour fundus photographs. Clin Exp Ophthalmol. 2019;47:1009-1018.
4. Keel S, Wu J, Lee PY, et al. Visualizing deep learning models for the detection of referable diabetic retinopathy and glaucoma. JAMA Ophthalmol. 2019;137:288-292.
5. Ting DSW, Cheung CYL, Lim G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017;318:2211-2223.
Mingguang He, MD, PhD
e: mingguang@unimelb.edu.au
This article was adapted from the telehealth presentations during the eyeRISE 2021 virtual symposium. Dr He has no financial interest in this subject matter.
Thulasiraj Ravilla, MBA
e: thulsi@aravind.org
Mr Ravilla has no financial interest in this subject matter.
Angus Turner, MD
e: angus.turner@uwa.edu.au
Dr Turner has no financial interest in this subject matter.
Gavin Tan, MD
e: gmstansw@nus.edu.sg
Dr Tan has no financial interest in this subject matter.

Related Content: Retina | Glaucoma | Ang2 inhibition for retinal disease