The landscape of ophthalmology has observed monumental shifts with the advent of artificial intelligence (AI) technologies. This article is devoted to elaborating on the nuanced application of AI in the diagnostic realm of anterior segment eye diseases, an area ripe with potential yet complex in its imaging characteristics. Historically, AI’s entrenchment in ophthalmology was predominantly rooted in the posterior segment. However, the evolution of machine learning paradigms, particularly with the advent of deep learning methodologies, has reframed the focus. When combined with the exponential surge in available electronic image data pertaining to the anterior segment, AI’s role in diagnosing corneal, conjunctival, lens, and eyelid pathologies has been solidified and has emerged from the realm of theoretical to practical. In light of this transformative potential, collaborations between the Ophthalmic Imaging and Intelligent Medicine Subcommittee of the China Medical Education Association and the Ophthalmology Committee of the International Translational Medicine Association have been instrumental. These eminent bodies mobilized a consortium of experts to dissect and assimilate advancements from both national and international quarters. Their mandate was not limited to AI’s application in anterior segment pathologies like the cornea, conjunctiva, lens, and eyelids, but also ventured into deciphering the existing impediments and envisioning future trajectories. After iterative deliberations, the consensus synthesized herein serves as a touchstone, assisting ophthalmologists in optimally integrating AI into their diagnostic decisions and bolstering clinical research. Through this guideline, we aspire to offer a comprehensive framework, ensuring that clinical decisions are not merely informed but transformed by AI. By building upon existing literature yet maintaining the highest standards of originality, this document stands as a testament to both innovation and academic integrity, in line with the ethos of renowned journals such as Ophthalmology.
- Article type
- Year
- Co-author
Open Access
Intelligent Ophthalmology
Issue
Open Access
Intelligent Ophthalmology
Issue
With the upsurge of artificial intelligence (AI) technology in the medical field, its application in ophthalmology has become a cutting-edge research field. Notably, machine learning techniques have shown remarkable achievements in diagnosing, intervening, and predicting ophthalmic diseases. To meet the requirements of clinical research and fit the actual progress of clinical diagnosis and treatment of ophthalmic AI, the Ophthalmic Imaging and Intelligent Medicine Branch and the Intelligent Medicine Committee of Chinese Medicine Education Association organized experts to integrate recent evaluation reports of clinical AI research at home and abroad and formed a guideline on clinical research evaluation of AI in ophthalmology after several rounds of discussion and modification. The main content includes the background and method of developing this guideline, an introduction to international guidelines on the clinical research evaluation of AI, and the evaluation methods of clinical ophthalmic AI models. This guideline introduces general evaluation methods of clinical ophthalmic AI research, evaluation methods of clinical ophthalmic AI models, and commonly-used indices and formulae for clinical ophthalmic AI model evaluation in detail, and amply elaborates the evaluation methods of clinical ophthalmic AI trials. This guideline aims to provide guidance and norms for clinical researchers of ophthalmic AI, promote the development of regularization and standardization, and further improve the overall level of clinical ophthalmic AI research evaluations.
Open Access
Intelligent Ophthalmology
Issue
To assess the performance of five distinct large language models (LLMs; ChatGPT-3.5, ChatGPT-4, PaLM2, Claude 2, and SenseNova) in comparison to two human cohorts (a group of funduscopic disease experts and a group of ophthalmologists) on the specialized subject of funduscopic disease.
Five distinct LLMs and two distinct human groups independently completed a 100-item funduscopic disease test. The performance of these entities was assessed by comparing their average scores, response stability, and answer confidence, thereby establishing a basis for evaluation.
Among all the LLMs, ChatGPT-4 and PaLM2 exhibited the most substantial average correlation. Additionally, ChatGPT-4 achieved the highest average score and demonstrated the utmost confidence during the exam. In comparison to human cohorts, ChatGPT-4 exhibited comparable performance to ophthalmologists, albeit falling short of the expertise demonstrated by funduscopic disease specialists.
The study provides evidence of the exceptional performance of ChatGPT-4 in the domain of funduscopic disease. With continued enhancements, validated LLMs have the potential to yield unforeseen advantages in enhancing healthcare for both patients and physicians.
Open Access
Clinical Research
Issue
To study retinal microvascular and microstructural alterations in meibomian gland dysfunction (MGD) in severely obese population using optical coherence tomography angiography (OCTA).
Twelve MGD patients with severely obese population (PAT group; 24 eyes) and 12 healthy controls (HC group; 24 eyes) were recruited. OCTA images were segmented into five [superior (S), nasal (N), inferior (Ⅰ), temporal (T), and central foveal (C)] or nine [inner superior (IS), outer superior (OS), inner nasal (IN), outer nasal (ON), inner inferior (Ⅱ), outer inferior (OI), inner temporal (IT), outer temporal (OT), and C] subregions. The superficial vessel density (SVD), retinal thickness (RT), foveal avascular zone (FAZ) parameters, and retinal volume were measured.
Visual acuity was significantly different between two groups (0.8±0.17 in PAT group vs 0.2±0.06 in HC group). SVD was significantly lower in PATs in N, T, OS, IN, OT, and ON. The area under the receiver operating characteristic curve (AUC) for T was 0.961 [95% confidence interval (CI): 0.908 to 1.000], for OS was 0.962 (95%CI: 0.915 to 1.000). RT was significantly lower in PATs in IS, OS, OI, OT, ON, IT, IN, and Ⅱ. AUC for OT was 0.935 (95%CI: 0.870 to 0.999), for IS was 0.915 (95% CI: 0.838 to 0.992). Angiography results showed significantly lower area and perimeter of FAZ, SVD of the inner retina and both retinal volume and the average volume thickness in the PAT group.
Vision may be affected in patients with MGD due to changes in retinal microvessels and microstructures. These changes detected by OCTA may be a potential marker for diagnosing MGD in severe obesity.
Open Access
Clinical Research
Issue
To study functional brain abnormalities in patients with hypertensive retinopathy (HR) and to discuss the pathophysiological mechanisms of HR by fractional amplitude of low-frequency fluctuations (fALFFs) method.
Twenty HR patients and 20 healthy controls (HCs) were respectively recruited. The age, gender, and educational background characteristics of the two groups were similar. After functional magnetic resonance imaging (fMRI) scanning, the subjects’ spontaneous brain activity was evaluated with the fALFF method. Receiver operating characteristic (ROC) curve analysis was used to classify the data. Further, we used Pearson’s correlation analysis to explore the relationship between fALFF values in specific brain regions and clinical behaviors in patients with HR.
The brain areas of the HR group with lower fALFF values than HCs were the right orbital part of the middle frontal gyrus (RO-MFG) and right lingual gyrus. In contrast, the values of fALFFs in the left middle temporal gyrus (MTG), left superior temporal pole (STP), left middle frontal gyrus (MFG), left superior marginal gyrus (SMG), left superior parietal lobule (SPL), and right supplementary motor area (SMA) were higher in the HR group. The results of a t-test showed that the average values of fALFFs were statistically significantly different in the HR group and HC group (P<0.001). The fALFF values of the left middle frontal gyrus in HR patients were positively correlated with anxiety scores (r=0.9232; P<0.0001) and depression scores (r=0.9682; P<0.0001).
fALFF values in multiple brain regions of HR patients are abnormal, suggesting that these brain regions in HR patients may be dysfunctional, which may help to reveal the pathophysiological mechanisms of HR.
Open Access
Clinical Research
Issue
This guideline seeks to thoroughly investigate the standardized operational procedures for visual function and imaging examinations prior to vitreoretinal surgery. Preoperative assessments can greatly assist clinicians in determining surgical indications, assessing patient conditions, and offering valuable assistance in formulating surgical strategies and predicting outcomes. Developed by a collaborative team of experts from the Ophthalmic Imaging and Intelligent Medicine Branch of the Chinese Medical Education Association, in conjunction with the Ophthalmic Imaging and Intelligent Medicine Branch of the Chinese Medical Education Association, these guidelines have been formulated through extensive research and evaluation, incorporating the latest technological advancements and studies on a global and domestic scale in vitreoretinal surgery. After extensive deliberations and incorporation of up-to-date clinical data, these guidelines have been developed to assist in standardizing preoperative examinations for vitreoretinal surgery. The overarching goals include improving medical quality, maximizing resource allocation, offering decision-making assistance, and safeguarding patient rights. This document provides a comprehensive analysis of preoperative assessments for vitreoretinal procedures, covering principles, methodologies, and precautions related to a range of diagnostic techniques including ultra-wide-angle fundus imaging, fluorescein angiography, indocyanine green angiography, ophthalmic B-ultrasound examinations, ultrasound biomicroscopy, optical coherence tomography, optical coherence tomography angiography, orbital CT scan, orbital MRI, and ophthalmic electrophysiology tests such as electroretinograms, visually evoked potentials, and visual field testing.
Open Access
Clinical Research
Issue
To elucidate the neuropathological mechanisms underlying diabetic vitreous hemorrhage (DVH) and its correlation with clinical characteristics.
Twenty-one individuals with DVH (male/female 12/9; mean age 52.29±11.66y) were selected, alongside 21 appropriately matched controls with diabetes mellitus (DM). Voxel-based morphometry (VBM) techniques were employed to identify aberrant functional regions in the brain. Receiver operating characteristic (ROC) curves were utilized for classification based on the average VBM values of the two groups, and Pearson correlation analysis was conducted to assess the relationship between average VBM values in distinct brain regions and clinical manifestations.
Relative to the DM controls, DVH patients exhibited reduced VBM values in the right superior temporal pole, the right superior temporal gyrus, the right medial orbital frontal gyrus, and the left superior frontal gyrus. Furthermore, ROC curve analysis of these four brain regions in DVH patients demonstrated a high degree of accuracy, as indicated by the area under the curve. The average VBM value in each of these regions exhibited a negative correlation with both the duration of DVH and the score on the Hospital Anxiety and Depression Scale (HADS).
Pathological alterations in four distinct brain regions are observed in patients with DVH, potentially reflecting neuropathological changes associated with this condition.
Open Access
Clinical Research
Issue
Non-specific orbital inflammation (NSOI) is a non-infectious orbital inflammation. Although it is often considered the most common diagnosis in orbital biopsies, it is an exclusionary diagnosis that requires ruling out systemic disease or other possible causes. Its characteristics include acute orbital signs and symptoms, including pain, proptosis, periorbital edema, chemosis, diplopia, and visual impairment. The clinical manifestations and histological findings of NSOI are heterogeneous, without specific diagnostic criteria or treatment guidelines, which poses significant challenges for diagnosis and treatment. This guideline provides a detailed description of the definition, classification, diagnosis, and treatment of NSOI.
Open Access
Clinical Research
Issue
To study functional brain abnormalities in patients with eye trauma (ET) and to discuss the pathophysiological mechanisms of ET.
Totally 31 ET patients and 31 healthy controls (HCs) were recruited. The age, gender, and educational background characteristics of the two groups were similar. After functional magnetic resonance imaging (fMRI) scanning, the subjects’ spontaneous brain activity was evaluated with the functional connectivity (FC) method. Receiver operating characteristic (ROC) curve analysis was used to classify the data. Pearson’s correlation analysis was used to explore the relationship between FC values in specific brain regions and clinical behaviors in patients with ET.
Significantly increased FC between several regions was identified including the medial prefrontal cortex (MPFC) and left hippocampus formations (HF), the MPFC and left inferior parietal lobule (IPL), the left IPL and left medial temporal lobe (MTL), the left IPL and right MTL, and the right IPL and left MTL. No decreased region-to-region connectivity was detected in default mode network (DMN) sub-regions in patients with ET. Compared with HCs, ET patients exhibited significantly increased FC between several paired DMN regions, as follows: posterior cingulate cortex (PCC) and right HF (HF.R, t=2.196, P=0.032), right inferior parietal cortices (IPC.R) and left MTL (MTL.L, t=2.243, P=0.029), and right MTL (MTL.R) and HF.R (t=2.236, P=0.029).
FC values in multiple brain regions of ET patients are abnormal, suggesting that these brain regions in ET patients may be dysfunctional, which may help to reveal the pathophysiological mechanisms of ET.
Open Access
Clinical Research
Issue
To establish a meaningful standard for diagnosing ocular metastasis (OM) in menopausal breast cancer (BC) women, and explore the relationship between CA-153, CA-125, apolipoprotein A, and OM.
A total of 1362 menopausal female BC patients with OM volunteered to take part in this study between July 2012 and July 2022. Women with BC who are menopausal were found to have an OM incidence of 1.6%. Furthermore, CA-153, CA-125, and apolipoprotein A (Apo A) all contributed to OM in women with BC who are postmenopausal according to binary logistic regression. Receiver operating curve (ROC) analysis was used to assess the diagnostic value of OM in patients with BC.
Both CA-153 and CA-153+CA-125 showed a higher sensitivity of 95.45%, whereas CA-153+Apo A illustrated the highest specificity of 99.02%. Moreover, CA-153 and CA-153+CA-125 had higher areas under the curve (AUC) of 0.973.
The data indicate that the serum concentrations of CA-153 exhibited the most significant predictors of the diagnosis of OM in menopausal women with BC. The current study researches the utility of risk factors in predicting of OM in menopausal BC women and put forward the latest suggestions on their clinical application.
京公网安备11010802044758号