Biosimilars

COVID-19

Cataract Surgery

Cataract

Cataract Therapeutics

Clinical Diagnosis

Cornea

Dry Eye Awareness

Dry Eye

Gene Therapy

Geographic Atrophy

IOL Advances

Imaging

Glaucoma Awareness

Glaucoma Insights

Therapeutic Glaucoma

Interventional Glaucoma

Ocular Allergy

Ocular Surface Disease

Optic Relief

Optometry

Pediatrics

Pharmacy

Indispensable

Practice Management

Presbyopia

Ptosis

Refractive Surgery

Refractive

Retina

Surgery

Technology

Therapeutics

Understanding Antibiotic Resistance

Workplace

News

All News

Contributors

Money Matters

Media

Expert Interviews

Medical World News

Podcasts

Case Based Roundtable Series

Case of the Quarter

EyeView

Grand Rounds

Insights

Rapid Readout

Viewpoints

What’s Your WhEYE?

Conferences

Conference Coverage

Conference Listing

Events

Publications

Digital Edition

Europe Ophthalmology Times

Modern Retina

Supplements and Featured Publications

Partners

Subscribe

Resources

Job Board

About

Advertise

Privacy

Editorial

Terms and Conditions

Contact Us

Do Not Sell My Personal Information

Ophthalmology Times - Ophthalmology news, articles, and events

Facebook

Instagram

LinkedIn

Spotlight

Clinical

Glaucoma

1rem

Authors

Hyaluronic acid fillers are used for undereye volume correction, detailing aging effects on facial anatomy, common complications, and optimal injection techniques. Imaging tools such as MRI can prove to be beneficial for patient assessment.

Blog: MRI findings of undereye filler and filler migration

Kay Durairaj, MD, FACS, a facial plastic surgeon points out that the use of hyaluronidase in the periorbital region demands a meticulous approach due to the delicate anatomy and high risk of complications. 

Blog: Intervention may be necessary when too much filler is used under the eye 

A recurring feature at the 2024 American Society of Cataract and Refractive Surgery (ASCRS) Annual Meeting in Boston, Massachusetts, was the call for environmentally friendly practices worldwide, with the goal of decreasing the impact of ophthalmic surgeries on the planet.

A driving force in this movement is EyeSustain

 an organization dedicated to the development of such friendly environmental practices, that exists as a global coalition of eye societies providing education and resources to support sustainable practices in ophthalmology.

Here is a sampling of the ASCRS discussions on the topic.

Greening eye care: reducing ophthalmology’s environmental footprint

The presenters, led by first author Sarishka Desai, BA, described the EyeSustain platform and its 5-pronged mission: educate the global ophthalmic community about more sustainable practices, collaborate with industry to reduce our carbon footprint and surgical waste, support research and innovative solutions that reduce ophthalmology’s environmental impact, support advocacy and education about the public health impact of climate change, and collaborate with industry to reduce our carbon footprint and surgical waste.

Desai, of the University of Connecticut School of Medicine in Farmington, and colleagues presented EyeSustain’s approach to reducing the ophthalmic carbon footprint. She was joined in the study by Nitya Devireddy, BS, MPH, of Penn State College of Medicine in Hershey, Pennsylvania; Sofia Miguez, BA, of Yale School of Medicine in New Haven, Connecticut; and Barbara Erny, MD, of the Department of Ophthalmology at Stanford University in California.

The greenhouse gas data associated with health care are startling. Health care is responsible for 4.4% of all global greenhouse gas emissions, 71% of which arise from the manufacturing, use, and disposal of medical supplies. Ophthalmology has the highest procedural volume of any surgical specialty, with 50 million cataract surgeries expected to be performed globally each year by 2050, Desai reported.

In light of the procedural data, the authors highlighted 6 areas that are currently undergoing research and quality improvement initiatives through the EyeSustain system.

 of cataract surgeons and nurses by David Chang and Cassandra Thiel found that 93% of respondents believe that the trash associated with OR procedures is excessive, and that methods to reduce waste should be identified and implemented.

 encouraged regulatory agencies to allow electronic instructions for use be disseminated in lieu of the traditional paper instructions included with each cataract pack.

Ongoing projects spearheaded by EyeSustain members, including medical students and ophthalmology residents, are taking a look at educating surgeons and surgical staff about sustainability and the impact of OR waste, OR water consumption, and evaluation of flash sterilization associated with cataract surgery.

In recognition of the fact that medications in the OR represent an estimated $560 million in waste annually, a multisociety position paper

 recently formulated 3 key recommendations: topical drugs in multidose containers can be used for multiple patients in surgical facilities if proper guidelines are followed; topical drugs in multidose containers can be used until the manufacturer’s labeled date of expiration if proper guidelines are followed; and, when applicable, patients should be able to take their partially used medication home for postoperative use.

The Aravind Eye Care system’s low-carbon model from Madurai, India, uses alternate energy sources, transport, infrastructure, and equipment maintenance.

 Studying global systems of eye care and waste produced can provide a deeper understanding of the impact of hospitals and providers on climate change, as well as ideas on how western eye care systems can proactively reduce carbon emissions.

The EyeSustain platform includes ophthalmology-specific action steps for greening offices and clinics in collaboration with the 

Partnerships can be established with large manufacturers to reduce packaging, make instruments reusable, and streamline the manufacturing and distribution processes.

In addition to the impact of practice waste on the environment, EyeSustain also recommends studying the effects of climate change on the incidence rates of ophthalmologic conditions, including cataracts, allergic disease, and glaucoma, among others.

Desai and her colleagues recommended that institutions take the following steps:

Conduct a waste audit to quantify the carbon footprint of an institution’s OR emissions. This includes using the EyeSustain-Zasti Carbon Footprint Calculator, using the Sustainability Index for Disposables in Cataract Surgery calculator for cataract packs to evaluate the item-by-item potential for carbon dioxide savings, and surveying clinical staff to identify areas of perceived excess waste.

Identify key stakeholders at an institution and an enthusiastic, multidisciplinary team and completing the OR Sustainability Pledge (

), which has been completed by ambulatory surgery centers/hospital outpatient departments from 9 countries thus far.

Implement best practices; multisociety recommendations for sustainability are easily accessible at eyesustain.org and My Green Doctor for outpatient/clinic resources and local legislation using the American Academy of Ophthalmology Topical Medical Waste Reduction Act legislative template.

Using phacoemulsification waste to guide changes in surgical sustainability

Adjustments to improve the sustainability of ophthalmic surgical practice can have a large impact when scaled to case volume, according to author Margaret Tharp, BSc, who described this study at the ASCRS meeting. She and her coauthors Stella Protopapas, BA, MPH, and Minka Gill, BSc, are from the Indiana University School of Medicine in Bloomington, whereas David J. Palmer, MD, ABO, is from the Northwestern University Feinberg School of Medicine in Chicago, Illinois.

In their study, they sought to draw connections between results from a 24-hour waste audit at an outpatient surgical center and current resources available from EyeSustain to improve the sustainability of ophthalmic surgical practice.

The authors documented the extensive waste generated from 1 day of surgeries in an institution that included 13 phacoemulsification procedures, 5 plastic surgeries, 3 urologic surgeries, and 5 otolaryngologic cases. The waste products were sorted as medications (eg, propofol, eye drop containers), textiles (eg, surgical gowns, drapes), metals (eg, metal wiring, disposable instruments), and plastics (eg, hard, soft, wrappings).

When the amounts of the waste products were tallied, the authors found that “ophthalmology produced the greatest amount of waste in a single day relative to other operating specialties, despite producing the least amount of waste per case. Most ophthalmic waste was from textiles, hard plastics, and medications,” the authors reported.

The specific 13 phacoemulsification procedures resulted in 95.4 lb of waste broken down as follows: 18.5 lb of hard plastic, 5.5 lb of soft plastic, 8.3 lb of wrapping, 13.5 lb of medications, 41.2 lb of textiles, 6.7 lb of miscellaneous waste, and no metals. Compared with other operating specialties, ophthalmology produced the least amount of waste per case but the greatest amount of waste in total due to the relatively high case volume.

It has been reported that “discarded/unused pharmaceuticals from US cataract surgeries demonstrated waste of [approximately] $150 per case while generating carbon dioxide–equivalent emissions that approximated 25,000 to 100,000 flights from San Francisco, California, to Boston annually.

Small changes can have dramatic results. Tharp and colleagues suggested that the following would have positive consequences.

Revising the use of tetracaine bottles intraoperatively; for example, reusing the bottles between cases or sending the bottles home with patients

Optimizing packaging of surgical supplies and electronic instructions

Utilizing intravenous sedation to limit anesthesia gas carbon dioxide–equivalent emissions

Focusing on cutting waste also creates an opportunity to explore the practices of global leaders in sustainable eye care, such as the efforts of the Aravind Eye Hospitals, which provide similar surgical success rates at a fraction of the waste produced by US practices.

 A downside may be that such practices require significant reuse of materials, central sterilization, and stakeholder diligence, which can require complex interventions, according to Tharp. 

EyeSustain’s Surgical Facility Sustainability Pledge can serve as a guide for ophthalmologists to improve the sustainability of their practice in an approachable and lasting manner.

Factors contributing to the carbon footprint of cataract surgery

Omar Taboun, MSc, a medical student at Western University’s Schulich School of Medicine & Dentistry in London, Ontario, Canada, working under the direction of Netan Choudhry, MD, FRCSC, also described the negative impact of cataract surgery on the environment at the ASCRS meeting.

He commented, “We know that climate change can affect human health through various means, such as adverse weather events causing injury and exposure to pollutants [exacerbating] underlying health conditions. As health care providers, it is our responsibility to treat patients for their conditions that may ultimately be influenced by environmental factors. Counterintuitively, the health care sector is itself a greenhouse gas emitter,” Taboun said.

Surgery contributes significant emissions to the environment through the necessary materials and tools used during procedures. In addition, the need to maintain sterility increases waste.

The term footprint indicates the sum of all emissions direct and indirect resulting from this procedure, Taboun explained, the resultant value of which is typically reported in carbon dioxide equivalents

And although cataract surgery requires only a few minutes to complete, the procedural volume has increased exponentially over the past 2 decades,

Taboun and colleagues developed a 2-fold goal: they wanted to increase their understanding of the carbon footprint and waste accumulation to identify the primary contributors and pinpoint areas for improvement to enhance the sustainability of cataract surgery.

They conducted a literature search of PubMed, Google Scholar, and Medline to identify studies related to the carbon footprint and the elements of cataract surgery. The results yielded 6 studies, with 2 being the basis for this discussion,

He highlighted 3 main points extracted from the published data: the lowest footprint published was just under 6 kg of carbon dioxide equivalents; the highest published footprint was just over 180 kg of carbon dioxide; and the major factors contributing to the footprint include procurement of pharmaceuticals and materials, building and energy use, such as heating/cooling, lighting, electricity-powered tools, and travel by patients and staff to the location where the procedure is performed.

Taboun directed attention to centers that already have sustainable practices in place, such as the Aravind Eye Hospital, which reports the lowest footprint. These sustainable practices include the use of multiple operating tables in a single room; reusing gloves, gowns, and various medical equipment;

and using highly efficient autoclave settings.

Importantly, when these changes were implemented in the Aravind Eye Hospital,

 the rates of endophthalmitis remained comparable to other centers: 0.02% vs from 0.04% to 0.07% reported.

Taboun offered 3 ways that surgeons can offset the negative effects of cataract surgery on the environment—by focusing on procurement, energy use, and travel emissions.

Reduce emissions associated with procurement by collaborating with manufacturers to reduce packaging as much as possible and encouraging recycling in every OR.

Reduce building and energy use by incorporating renewable energy, such as solar panels, and more strategic lighting protocols and optimizing energy use within surgical centers.

Establish outreach clinics closer to more populous regions, whereby mostly staff members must travel, and patients less so, which will reduce travel emissions, along with performing bilateral procedures.

“Implementing sustainable practices, although challenging, will allow us to continuously provide this procedure and restore vision for millions of people at less of a cost to the environment,” Taboun said.

1. Chang DF, Thiel CL; Ophthalmic Instrument Cleaning and Sterilization Task Force. Survey of cataract surgeons’ and nurses’ attitudes toward operating room waste

. 2020;46(7):933-940.doi:10.1097/j.jcrs.0000000000000267

2. Schehlein EM, Hovasesian J, Shukla AG, Talley Rostov A, Findl O, Change DF. Reducing ophthalmic surgical waste through electronic instructions for use: a multi-society position paper. 

. 2024;50(3):197-200. doi:10.1097/j.jcrs.0000000000001381

3. Cleaning and Sterilization Task Force. Reducing topical drug waste in ophthalmic surgery: multisociety position paper

. 2022;48(9):1073-1077; doi:10.1097/j.jcrs.0000000000000975

4. Goel H, Wemyss TA, Harris T, et al. Improving productivity, costs and environmental impact in International Eye Health Services: using the ‘Eyeficiency’ cataract surgical services auditing tool to assess the value of cataract surgical services. 

. 2021 ;6(1):e000642. doi:10.1136/bmjophth-2020-000642. 2021

5. US EPA O. Greenhouse gas equivalencies calculator. United States Environmental Protection Agency. Updated January 2024. https://www.epa.gov/energy/greenhouse-gas-equivalencies-calculator

6. Gadani H, Vyas A. Anesthetic gases and global warming: [otentials, prevention and future of anesthesia. 

. 2011;5(1):5-10. doi:10.4103/0259-1162.84171

7. Thiel CL, Schehlein E, Ravilla T, et al. Cataract surgery and environmental sustainability: waste and lifecycle assessment of phacoemulsification at a private healthcare facility. 

. 2017;43(11):1391-1398. doi:10.1016/j.jcrs.2017.08.017

8. Pandey D, Agrawal M, Pandey JS. Carbon footprint: current methods of estimation. 

. 2011 ;178(1-4):135-160. doi:10.1007/s10661-010-1678-y

9. Pandey D, Agrawal M, Pandey JS. (2011). Carbon footprint: current methods of estimation. 

. 2011;178(1-4):135-160. doi:10.1007/s10661-010-1678-y

10 Rachmiel R, Trope GE, Chipman ML, Buys YM. Cataract surgery rates in Ontario, Canada, from 1992 to 2004: more surgeries with fewer ophthalmologists. 

11. Morris DS, Wright T, Somner JEA, Connor A. The carbon footprint of cataract surgery. 

. 2013;27(4):495-501. doi:10.1038/eye.2013.

12. Latta M, Shaw C, Gale J. The carbon footprint of cataract surgery in Wellington. 

13. Ravindran RD, Venkatesh R, Chang DF, Sengupta S, Gyatsho J, Talwar B. Incidence of post-cataract endophthalmitis at Aravind Eye Hospital: outcomes of more than 42,000 consecutive cases using standardized sterilization and prophylaxis protocols. 

. 2009;35(4):629-636. doi:10.1016/j.jcrs.2009.01.002

14, Pershing S, Lum F, Hsu S, et al. Endophthalmitis after cataract surgery in the United States: a report from the Intelligent Research in Sight registry, 2013-2017. 

. 2020;127(2):151-158. doi:10.1016/j.ophtha.2019.08.026

Organization eyes green practices, shifting ophthalmology landscape.

Minimizing the carbon footprint of ophthalmic surgeries

Floretina Charles Wykoff, MD, PhD

FLORetina meeting and International Congress on OCT Angiography, En Face OCT and Advances in OCT (ICOOR)

 spoke with Charles Wykoff, MD, PhD. Throughout FLORetina ICOOR, he's presenting on a number of topics, including diabetic retinopathy—the subject of his conversation with the Eye Care Network.

Editor's note: The below transcript has been lightly edited for clarity.

 The FLORetina International Congress on OCT, Angiography and Advances in OCT is holding its annual meeting in Florence. At the meeting, Dr Charles Wyckoff is presenting Diabetic Retina Imaging: New Biomarkers. Thanks for joining me today. First, give me an overview of what you'll be presenting.

: David, great to be here with you, and excited for the FLORetina meeting. It's a great, great meeting in Europe. So, talking about retinal non-perfusion in the context of diabetic retinopathy, and it's a simple presentation. We're addressing three sorts of questions that come up a lot about retinal non-perfusion, and I'll just go through each of those three with you.

So, the first is our understanding and awareness of the presence of retinal non perfusion. Is that clinically useful information? And I think the answer is yes. And the brief summary of that is, you know, originally we had the ETDRS [Early Treatment Diabetic Retinopathy Study] which is our prognostic scale for diabetic retinopathy. We also learned from the original ETDRS trial that angiographic risk factors, including retinal non-perfusion, provide additional prognostic information. And more recently, DRCR AA and PANORAMA trial have shown us that a greater amount of retinal non-perfusion at baseline correlates with a higher likelihood of disease progression through 1 in 2 years of followup. So, the answer is yes. From a prognostication perspective, the presence of non-perfusion, the amount of non-perfusion is important.

And then the second question is, is reperfusion possible? Right. That's sort of the Holy Grail here in diabetic retinopathy. And while the clinical reality is that it is very uncommon to see reperfusion, absent perfusion, with or without anti VEGF therapy, you know, the clinical reality is progressive retinal non-perfusion that accumulates over time, and I'll show some images of that. But it's interesting, because if you look in the literature and you take a deep dive, there are multiple papers going back to the 1980s that have beautifully documented areas of non-perfusion that are then revascularized, with or without treatment of different kinds. And so it's certainly possible, although not common clinically with our anti-VEGFs. What is interesting, though, about all of our clinical trials—RHINE and RISE ... VISTA showed this—all of them, in posthoc analyses, they showed that more frequent anti-VEGF dosing led to a slowing of disease progression. So, you accumulated less retinal non-perfusion when you dose patients frequently with renovisumab or afflibercept. This was studied directly in the RECOVERY trial. That was a prospective trial that randomized 40 patients to either monthly or quarterly aflibercept, all with PDR and large areas of non-perfusion. And we saw that with monthly dosing through 1 year, the primary endpoint of retinal non-perfusion was stable between the baseline and year 1 endpoint, showing you could stabilize retinal mono perfusion with monthly dosing, whereas in the quarterly group dose patients, we saw a meaningful increase in the area of retinal non-perfusion by about 29%. So anti-VEGF therapy does not frequently cause revascularization, but it may slow progressive retinal non-perfusion when dosed frequently.

And the final question is, you know, what could the future of retinal non-perfusion look like? And fortunately for patients, there are a lot of pharmacotherapies that are being considered and being explored in a development perspective, for reperfusing areas of non-perfusion would be the most amazing thing. But they're really being overall, pursued to decrease ischemia by increasing local perfusion, and a few of those are in human development. The one that's furthest along is actually a biologic targeting a pathway called the semaphorin pathway. It's targeting a molecule called Semaphorin 3A, which is an anti-angiogenic, vaso-repulsive cytokine. And the thought here is that if you block Semaphorin 3A, you may be able to allow intraretinal revascularization through a VEGF-induced VEGF-dependent pathway. So there's a controlled Phase 2 trial, ongoing, pursuing that new fastening molecule. That's what I'm touching on at Floretina, an exciting space in diabetic retinopathy.

: What can all this mean for patients diagnosed with diabetic retinopathy?

: I think the most important thing from a patient perspective is make sure you're getting a routine eye exam with diabetes. If you have diabetes, we know most people with diabetes, probably worldwide, are not receiving appropriate eye care screening. And then when there is pathology—diabetic retinopathy, I think has a low threshold to at least consider initiation of therapy, right? There are pluses and minuses initiating therapy at all the different stages, but it's worth being able to have that conversation with someone that can adequately treat you if needed.

: And you kind of touched upon this, but where do you see this going in the next, say, 3 to 5 years?

: We have some very good therapies for the vision-threatening complications of diabetic retinopathy, right? Diabetic macular edema and proliferative diabetic retinopathy. All of which work better, in my opinion, when you treat the diseases earlier in the disease course. But I think we're still missing a key component of the treatment of diabetic retinopathy, which would be a treatment of the underlying pathophysiology. And I think retinal non-perfusion is at the core of that pathophysiologic drive in this disease process. So, it'd be great to have therapeutics that can directly treat that core pathophysiology. And it's still a dream of finding a medicine to cause reperfusion of damaged areas of retina. But I think it's possible. There's a few biologically possible mechanisms here that are being explored in humans, and I think over time, we'll hopefully find new therapeutics that can help us in that regard.

Diabetic retinopathy management is evolving with a focus on retinal non-perfusion. Retinal non-perfusion is a significant prognostic factor, with greater non-perfusion correlating with disease progression. While reperfusion is rare, frequent anti-VEGF therapy can slow non-perfusion progression. Future therapies aim to address underlying pathophysiology, with promising developments targeting the semaphorin pathway to enhance revascularization. Routine eye exams and early intervention remain crucial for patients with diabetes. The next few years may see advancements in therapies that directly address retinal non-perfusion and its pathophysiological drivers.

Ahead of this year's Floretina meeting and International Congress on OCT Angiography, En Face OCT and Advances in OCT (ICOOR), David Hutton of Ophthalmology Times spoke with Charles Wykoff, MD, PhD. At FLORetina ICOOR, he presented on a number of topics, including diabetic retinopathy—the subject of his conversation with the Eye Care Network.

FLORetina ICOOR 2024: Charles Wykoff, MD, PhD, discusses diabetic retinopathy and reperfusion

Artificial intelligence (AI), particularly large language models (LLMs) like GPT-4o, is emerging as a potential tool for enhancing diagnostic accuracy in healthcare. This study evaluated the diagnostic performance of GPT-4o compared to human ophthalmologists in glaucoma cases, exploring its strengths and limitations.

The primary aim was to assess GPT-4o’s performance in primary and differential diagnoses of glaucoma relative to human ophthalmologists. While GPT-4o demonstrated potential in generating comprehensive differential diagnoses, it fell short in primary diagnosis accuracy and completeness, highlighting the current limitations of AI as a standalone diagnostic tool.

According to a group of Chinese researchers, the prospective, observational study was conducted at a tertiary care ophthalmology center. Twenty-six glaucoma cases, encompassing both primary and secondary types, were selected from publicly available databases and institutional records. These cases were analyzed by GPT-4o and three ophthalmologists with varying levels of experience.

Diagnostic accuracy and completeness were evaluated using 10-point and 6-point Likert scales, respectively. Statistical analyses, including Kruskal–Wallis and Mann–Whitney U tests, revealed significant differences in performance:


GPT-4o achieved a mean accuracy score of 5.500 (p < 0.001), significantly lower than the highest-performing ophthalmologist, Doctor C, who scored 8.038 (p < 0.001). Completeness scores for GPT-4o were also inferior (3.077, p < 0.001) compared to the lowest-scoring ophthalmologist, Doctor B (3.615, p < 0.001).


In contrast, GPT-4o demonstrated comparable accuracy to the ophthalmologists for differential diagnoses, scoring 7.577 versus Doctor A (7.615) and Doctor C (7.673) (p < 0.0001). Notably, GPT-4o achieved the highest completeness score (4.096), outperforming Doctor C (3.846), Doctor A (2.923), and Doctor B (2.808) (p < 0.0001).

Primary diagnosis involves cognitive reasoning and prioritization of clinical information, areas where GPT-4o underperformed compared to human ophthalmologists. These findings align with prior research showing that while AI models like ChatGPT have improved in general medicine and certain specialties, they continue to struggle in highly specialized fields such as neuro-ophthalmology and ocular pathology.

Conversely, GPT-4o’s superior performance in differential diagnosis reflects its capacity to reference extensive databases and generate exhaustive lists of potential diagnoses. However, this comprehensive approach may overwhelm clinicians, increasing the risk of cognitive bias and misdiagnosis.

The study’s limitations include its small sample size (n = 26) and case selection, which emphasized a broad range of glaucoma subtypes over real-world prevalence patterns. Future studies should address these constraints by utilizing larger, more representative datasets.

“Recognizing this limitation, future research with a larger, more representative sample that aligns with real-world prevalence rates would improve the applicability of these findings across diverse clinical settings,” the researchers noted.

According to the researchers, the findings underscore the importance of improving AI models for primary diagnosis by incorporating clinician feedback, enhancing training datasets, and exploring more sophisticated reasoning algorithms. Evaluating AI’s utility in primary care or non-specialist settings, where it might serve as an adjunct to optometrists or general practitioners, is another avenue for future research.

GPT-4o demonstrated promise as a complementary tool for differential diagnosis in glaucoma cases but remains inadequate for primary diagnosis. The study also highlighted concerning gaps in diagnostic accuracy among human ophthalmologists, emphasizing the need for continuous self-evaluation and transparent communication with patients.

“Future advancements in AI may eventually enhance diagnostic accuracy, but until then, it should be viewed as a complementary tool, not a replacement for human expertise,” the researchers concluded.

 A comparative study of GPT-4o and human ophthalmologists in glaucoma diagnosis. 

, 30385 (2024). Published December 5, 2024. Accessed December 6, 2024. https://doi.org/10.1038/s41598-024-80917-x

Artificial intelligence, specifically large language models like GPT-4o, shows potential in enhancing diagnostic accuracy in healthcare, particularly in differential diagnosis of glaucoma. A study compared GPT-4o's performance to human ophthalmologists, revealing its limitations in primary diagnosis accuracy and completeness. While GPT-4o excelled in generating comprehensive differential diagnoses, it struggled with primary diagnosis, highlighting the need for AI improvement. The study's small sample size and case selection limit its applicability, suggesting future research should focus on larger, more representative datasets and explore AI's role in primary care settings.

According to researchers, GPT-4o demonstrates potential in generating comprehensive differential glaucoma diagnoses but falls short in primary diagnostic accuracy, underscoring its role as a complementary tool rather than a standalone diagnostic solution.

Kay Durairaj, MD, FACS

Articles

Latest Updated Articles