Aravind Eye Hospitals

Microbial keratitis requires rapid pathogen identification to guide treatment, but culture- and PCR-based diagnostics are slow and resource-intensive. We developed a triple-phase multimodal framework for bacterial-versus-fungal keratitis classification using slit-lamp photographs acquired under blue-light, sclerotic-scatter, and white-light illumination, together with clinical metadata. The model combines cross-modality contrastive learning, modality-specific fine-tuning, and feature-level multimodal ensemble learning for patient-level prediction. We evaluated the framework on a multicenter dataset of 1,645 patients and 17,158 images from India and the United States. The model achieved 85.84% accuracy, 84.46% average F1-score, and 0.885 AUC. Site-specific evaluation showed that pooled results were overly optimistic, whereas resampling- and balance-based re-evaluation provided a more realistic assessment of cross-site generalization. Under all settings, our framework remained the top-performing approach. The code is available at https://github.com/yqwang01/TPMKA and dataset access will be provided subject to University of Michigan data-sharing clearance.

PURPOSE:To compare the epidemiology and phenotypic characteristics of 2 populations of patients with retinopathy of prematurity (ROP) using a quantitative artificial intelligence (AI)-derived vascular severity score (VSS). METHODS:We retrospectively analyzed 2 data sets of ROP images: (1) The iROP data set including 1019 babies and 6552 eye-level examinations developed as part of a large US multicenter cohort study from 2012 to 2020. (2) 8281 consecutive ROP telemedicine examinations from 2363 babies in the Indian Aravind Eye Care System (AECS), from 2019 to 2020. We analyzed all eye examinations using the iROP DL system, which outputs a VSS from 1 to 9. The main outcome was the relationship between the VSS and the zone, stage, and extent of stage 3 in each data set, assessed using generalized estimating equations to account for the correlation from bilateral and repeated examinations. RESULTS:In both data sets, higher VSS was associated with higher stage (P < .001 for all stages in both data sets), higher extent of stage 3 (i-ROP, P =.004, and AECS, P < .001), and a more posterior zone for a given stage of ROP (i-ROP: stage 1, P = .04, stage 2, P < .001, and stage 3, P < .001; AECS: stage 1, P < .001, and stage 3, P < .001). For any given stage, the VSS was lower in the AECS data set than in the i-ROP data set (all P < .001). CONCLUSIONS:In both populations, the VSS was associated with more posterior zone and higher ROP stage/extent, though on average the VSS was lower in the AECS population. A correlation between measured VSS and intraocular vascular endothelial growth factor concentration might explain both findings.

PURPOSE:To survey United States (US) cornea specialists on clinical factors that distinguish between microbial keratitis (MK) organism groups. METHODS:This cross-sectional survey of US cornea specialists assessed whether 61 clinical factors, including history factors, ocular symptoms, and exam findings, distinguished a specific organism group in the typical patient with MK. MK organism groups included gram-positive bacterial keratitis (GPBK), gram-negative bacterial keratitis (GNBK), mold fungal keratitis (MFK), yeast fungal keratitis (YFK), parasitic keratitis (PK), and viral keratitis (VK). The survey was distributed via the Cornea Society's email listserv from March 11, 2024 to May 7, 2024. Descriptive statistical analysis was performed to identify the percentage of specialists identifying a clinical factor as distinguishing a specific MK organism group. RESULTS:A total of 67 specialists completed the survey. There were 20 factors (32.8% of 61) that >75% of specialists identified as distinguishing a specific MK group, including 9 factors for BK (eg copious ocular discharge, loose ocular sutures), 3 factors for FK (eg feathery infiltrate, ocular trauma with organic matter), 5 factors for PK (eg pain out of proportion, perineuritis), and 3 factors for VK (eg reduced/absent corneal sensation, prodromal symptoms). The remaining 41 factors had ≤75% of specialists identify them as distinguishing. CONCLUSIONS:Specialists agreed that 32.5% of clinical factors distinguished different MK organism groups, aligned with prior work demonstrating difficulty with interorganism differentiation. These 20 factors may aid clinicians in their initial MK diagnosis; however, more work is needed to validate their salience in diagnosis.

BACKGROUND:The clinical features of cytomegalovirus (CMV) retinitis have not been well characterized in India, despite the likely high burden of disease. SETTING:Tertiary eye hospital in Madurai, India. METHODS:All patients with a diagnosis of CMV retinitis seen at a single eye hospital from 2007 to 2023 were identified from uvea, retina, and microbiology registries and the hospital administrative database. A standardized chart review was performed. RESULTS:Among 343 patients diagnosed with CMV retinitis, 322 (94%) were HIV positive. Of 213 patients with a documented date of HIV diagnosis, 54 (25%) were unaware of their HIV status until after being diagnosed with CMV retinitis. Of the 159 HIV-positive patients aware of their diagnosis, 33 (21%) were not yet taking antiretroviral therapy at the time of retinitis diagnosis. At the time of CMV retinitis diagnosis, a total of 52 (16%) patients were bilaterally blind and 57 (18%) had retinal detachment in 1 or both eyes. The number of patients presenting with CMV retinitis each year did not change substantially between 2007 and 2023. CONCLUSIONS:Patients diagnosed with CMV retinitis at an eye hospital in south India presented with advanced disease, and were frequently unaware of their HIV diagnosis.