Since the outbreak of COVID-19, telemedicine utilization, particularly in its synchronous form (telephone and live video consultations), has increased exponentially across all areas of healthcare, especially in ophthalmology.
According to data from NHS Digital, ophthalmology is the outpatient speciality in numerous countries with the largest number of attendances. Ophthalmology may be a field that is particularly susceptible to the spread of COVID-19 due to the large patient load and physician reliance on close proximity patient evaluation. That is why digitalization has become a crucial aspect of this sphere.
The Problem of Preventable Blindness Caused by Low Diagnostic Standards
In pre-pandemic times, doctors would apply rapid assessment of avoidable blindness (RAAB), which is not the most accurate method of diagnosis. It might lead to inefficient use of medical services and cost the patient money for a trip that might not have been necessary, negatively affecting sustainability and the economy. Prehospital screening of referrals between ophthalmologists and optometrists was already becoming more prevalent, and asynchronous models have shown that over half of specialist referrals are unnecessary.
Digitalization in Ophthalmology
Health care providers, politicians, and commissioners have recently made digitalization available to reduce social interaction. Several telemedicine models have arisen in ophthalmology, and prehospital evaluation skills have improved significantly.
This is a technique for evaluating patients and guiding them to the best course of treatment. To facilitate prehospital triage, institutions have innovatively used the resources at their disposal. Some have chosen a store-and-forward strategy, combining phone consultations with clinical photos sent by email when necessary. Others opt for online video-based consultations. China has employed intelligent chatbot prescreening, slit-lamp imaging, and massive virtual live consultations. These capabilities are expected to expand with improvements in natural language processing and their application in conjunction with machine learning to enhance the scrutiny of recommendations.
A concept of outreach “spokes” where patients can go, ideally in the local community, and the data collected is transferred to a secondary care “hub” restricts in-person attendance in hospitals during the epidemic. This hub-and-spoke structure and store-and-forward strategy were already in place before the epidemic, but they have gained popularity since then. This strategy depends on strong infrastructure support, including secure communications and electronic health record systems that can show recorded pictures and combine data from the spokes with that from the hub.
This is an easy, affordable, and practical addition to teleconsultations for eye care. Printed optotypes, online tools, and mobile applications are the three main categories of self-testing tools. Web-based mediums may need to be paid for to access findings, even though they can generate accurate results with clinical validity.
Optotypes that have been printed nearly mimic visual evaluation in a clinical context. This approach is appealing since it is straightforward and economical, but it significantly depends on variables under the operator’s control.
The mobile app market has expanded rapidly since smartphones became generally accessible in roughly 2007. According to research, adults and children may get findings from vision-testing applications that are on par with printed optotypes.
AI for Automated Medical Image Analysis (OCT)
Artificial intelligence (AI) is anticipated to provide ophthalmologists with new automated options for identifying and treating ocular illnesses from the front to the rear of the eye. This transition is fueled partly by the recent increase in interest from major organizations in the digital world like Google and IBM in AI’s medicinal potential. But, according to ophthalmologists participating in these efforts, computerized analytics are being considered the road toward more effective and objective ways to evaluate the stream of pictures that contemporary eye care techniques create.
Currently, the most frequent use of AI in ophthalmology is the analysis of OCT scan. This is the imaging technique known as optical coherence tomography. OCT is non-invasive and employs light waves to create images of the retina in cross-section. An ophthalmologist can view each of the different layers of the retina using OCT. They can map and gauge their thickness in this way. These digital measures definitely aid the diagnosis.
AI is used for OCT scans analysis in the following ways.
- It differentiates between pathological and non-athological scans rapidly and
- It determines severe scans without any chance for human errors
- AI can detect more than 100 retinal conditions as of today, including some rare conditions.
The development of AI-based technologies to better diagnose or assess additional ocular disorders, such as pediatric cataract, keratoconus, glaucoma, corneal ectasia, and oculoplastic reconstruction, goes beyond merely the retina.
These algorithms can improve and increase objectivity across various situations, from screening to complete management. Doctors often disagree, but an AI system always provides the same response, according to Michael D. Abramoff, MD, Ph.D., a pioneer in the study of AI in ophthalmology and a professor at the University of Iowa in Iowa City.
This is a sponsored post
Digital Health Buzz! aims to be the destination of choice when it comes to what’s happening in the digital health world. We are not about news and views, but informative articles and thoughts to apply in your business.