ABSTRACT
Purpose: To evaluate the performance of artificial intelligence (AI) systems embedded in a mobile, handheld retinal camera, with a single retinal image protocol, in detecting both diabetic retinopathy (DR) and more-than-mild diabetic retinopathy (mtmDR). Design: Multicenter cross-sectional diagnostic study, conducted at 3 diabetes care and eye care facilities. Participants: A total of 327 individuals with diabetes mellitus (type 1 or type 2) underwent a retinal imaging protocol enabling expert reading and automated analysis. Methods: Participants underwent fundus photographs using a portable retinal camera (Phelcom Eyer). The captured images were automatically analyzed by deep learning algorithms retinal alteration score (RAS) and diabetic retinopathy alteration score (DRAS), consisting of convolutional neural networks trained on EyePACS data sets and fine-tuned using data sets of portable device fundus images. The ground truth was the classification of DR corresponding to adjudicated expert reading, performed by 3 certified ophthalmologists. Main Outcome Measures: Primary outcome measures included the sensitivity and specificity of the AI system in detecting DR and/or mtmDR using a single-field, macula-centered fundus photograph for each eye, compared with a rigorous clinical reference standard comprising the reading center grading of 2-field imaging protocol using the International Classification of Diabetic Retinopathy severity scale. Results: Of 327 analyzed patients (mean age, 57.0 ± 16.8 years; mean diabetes duration, 16.3 ± 9.7 years), 307 completed the study protocol. Sensitivity and specificity of the AI system were high in detecting any DR with DRAS (sensitivity, 90.48% [95% confidence interval (CI), 84.99%-94.46%]; specificity, 90.65% [95% CI, 84.54%-94.93%]) and mtmDR with the combination of RAS and DRAS (sensitivity, 90.23% [95% CI, 83.87%-94.69%]; specificity, 85.06% [95% CI, 78.88%-90.00%]). The area under the receiver operating characteristic curve was 0.95 for any DR and 0.89 for mtmDR. Conclusions: This study showed a high accuracy for the detection of DR in different levels of severity with a single retinal photo per eye in an all-in-one solution, composed of a portable retinal camera powered by AI. Such a strategy holds great potential for increasing coverage rates of screening programs, contributing to prevention of avoidable blindness. Financial Disclosures: F.K.M. is a medical consultant for Phelcom Technologies. J.A.S. is Chief Executive Officer and proprietary of Phelcom Technologies. D.L. is Chief Technology Officer and proprietary of Phelcom Technologies. P.V.P. is an employee at Phelcom Technologies.
ABSTRACT
Uveitis is a disease complex characterized by intraocular inflammation of the uvea that is an important cause of blindness and social morbidity. With the dawn of artificial intelligence (AI) and machine learning integration in health care, their application in uveitis creates an avenue to improve screening and diagnosis. Our review identified the use of artificial intelligence in studies of uveitis and classified them as diagnosis support, finding detection, screening, and standardization of uveitis nomenclature. The overall performance of models is poor, with limited datasets and a lack of validation studies and publicly available data and codes. We conclude that AI holds great promise to assist with the diagnosis and detection of ocular findings of uveitis, but further studies and large representative datasets are needed to guarantee generalizability and fairness.
Subject(s)
Artificial Intelligence , Uveitis , Humans , Machine Learning , Uveitis/diagnosis , Delivery of Health Care , UveaABSTRACT
ABSTRACT Purpose: To evaluate contrast sensitivity in non-high-risk, treatment-naïve proliferative diabetic retinopathy patients treated with panretinal photocoagulation and intravitreal injections of ranibizumab) versus panretinal photocoagulation alone. Methods: Sixty eyes of 30 patients with bilateral proliferative diabetic retinopathy were randomized into two groups: one received panretinal photocoagulation and ranibizumab injections (study group), while the other received panretinal photocoagulation alone (control group). All eyes were treated with panretinal photocoagulation in three sessions according to the Early Treatment Diabetic Retinopathy Study guidelines. Contrast sensitivity measurements were performed under photopic conditions (85 cd/m2) with the Visual Contrast Test Sensitivity 6500 chart, allowing for the evaluation of five spatial frequencies with sine wave grating charts: 1.5, 3.0, 6.0, 12.0, and 18.0 cycles per degree (cpd). Outcomes were measured in contrast sensitivity threshold scores among and within groups, from baseline to 1, 3, and 6 months. Results: Fifty-eight eyes (28 in the study group and 30 in the control group) reached the study endpoint. A comparative analysis of changes in contrast sensitivity between the groups showed significant differences mainly in low frequencies as follows: at month 1 in 1.5 cpd (p=0.001) and 3.0 cpd (p=0.04); at month 3 in 1.5 cpd (p=0.016), and at month 6 in 1.5 cpd (p=0.001) and 3.0 cpd (p=0.026) in favor of the study group. Conclusions: In eyes of patients with non-high-risk proliferative diabetic retinopathy, panretinal photocoagulation treatment with ranibizumab appears to cause less damage to contrast sensitivity compared with panretinal photocoagulation treatment alone. Thus, our evaluation of contrast sensitivity may support the use of ranabizumab as an adjuvant to panretinal photocoagulation for the treatment of proliferative diabetic retinopathy.
RESUMO Objetivos: Avaliar a sensibilidade ao contraste em pacientes virgens de tratamento com retinopatia diabética proliferativa de não alto risco, submetidos a panfotocoagulação retiniana com injeções intravítreas de ranibizumabe versus panfotocoagulação isolada. Métodos: Sessenta olhos de 30 pacientes foram randomizados em dois grupos: um submetido a panfotocoagulação com injeções de ranibizumabe (grupo estudo), e o outro submetimedo a panfotocoagulação isolada (grupo controle). Todos olhos foram tratados em 3 sessões de laser, seguindo recomendação do Early Treatment Diabetic Retinopathy Study (ETDRS). Avaliação da sensibilidade ao contraste foi realizada sob condições fotópicas (85 cd/m2) com tabela Visual Contrast Test Sensitivity 6500, permitindo avaliação de cinco frequências espaciais medidas com redes senoidais: 1.5, 3.0, 6.0, 12.0 e 18.0 ciclos por grau de ângulo visual (cpd). Foram realizadas medidas dos limiares de sensibilidade ao contraste intra e entre grupos na visita inicial, no 1º, 3º, e 6º mês de seguimento. Resultados: Cinquenta e oito olhos, 28 do grupo estudo e 30 do grupo controle, atingiram o término do estudo. Análise comparativa da SC entre os grupos mostrou diferença estatisticamente significante, nas baixas frequências espaciais, no 1º mês em 1.5 cpd (p=0,001) e 3.0 cpd (p=0,04), no 3º mês em 1.5 cpd (p=0,016) e no 6º mês em 3.0 cpd (p=0,026) a favor do grupo estudo. Conclusão: O tratamento com panfotocoagulação associada a injeção de ranibizumabe parece causar menos danos a sensibilidade ao contraste quando comparada com panfotocoagulação isolada em olhos com retinopatia diabética proliferativa de não alto risco. Dessa forma, os resultados apresentados podem justificar a associação do ranibizumabe à panfotocoagulação nestes pacientes.
ABSTRACT
PURPOSE: To evaluate contrast sensitivity in non-high-risk, treatment-naïve proliferative diabetic retinopathy patients treated with panretinal photocoagulation and intravitreal injections of ranibizumab) versus panretinal photocoagulation alone. METHODS: Sixty eyes of 30 patients with bilateral proliferative diabetic retinopathy were randomized into two groups: one received panretinal photocoagulation and ranibizumab injections (study group), while the other received panretinal photocoagulation alone (control group). All eyes were treated with panretinal photocoagulation in three sessions according to the Early Treatment Diabetic Retinopathy Study guidelines. Contrast sensitivity measurements were performed under photopic conditions (85 cd/m2) with the Visual Contrast Test Sensitivity 6500 chart, allowing for the evaluation of five spatial frequencies with sine wave grating charts: 1.5, 3.0, 6.0, 12.0, and 18.0 cycles per degree (cpd). Outcomes were measured in contrast sensitivity threshold scores among and within groups, from baseline to 1, 3, and 6 months. RESULTS: Fifty-eight eyes (28 in the study group and 30 in the control group) reached the study endpoint. A comparative analysis of changes in contrast sensitivity between the groups showed significant differences mainly in low frequencies as follows: at month 1 in 1.5 cpd (p=0.001) and 3.0 cpd (p=0.04); at month 3 in 1.5 cpd (p=0.016), and at month 6 in 1.5 cpd (p=0.001) and 3.0 cpd (p=0.026) in favor of the study group. CONCLUSIONS: In eyes of patients with non-high-risk proliferative diabetic retinopathy, panretinal photocoagulation treatment with ranibizumab appears to cause less damage to contrast sensitivity compared with panretinal photocoagulation treatment alone. Thus, our evaluation of contrast sensitivity may support the use of ranabizumab as an adjuvant to panretinal photocoagulation for the treatment of proliferative diabetic retinopathy.
