Age-related macular degeneration (AMD) is a leading cause of blindness. The main risk factor is advancing age, with the severity of vision loss ranging from mild to severe. There is a 25% risk of early AMD and 8% risk of late AMD in patients over the age of 75, with the number of cases expected to increase because of the aging population. Diagnosis of the disease requires a dilated fundus examination. Physicians should be aware of the symptoms, risk factors, and treatment options for AMD to refer appropriately for ophthalmologic evaluation. Early detection can be helpful to prevent disease progression.

Applying artificial intelligence (AI) for systematic literature review holds great potential for enhancing evidence-based medicine, yet has been limited by insufficient training and evaluation. Here, we present LEADS, an AI foundation model trained on 633,759 samples curated from 21,335 systematic reviews, 453,625 clinical trial publications, and 27,015 clinical trial registries. In experiments, LEADS demonstrates consistent improvements over four cutting-edge large language models (LLMs) on six literature mining tasks, e.g., study search, screening, and data extraction. We conduct a user study with 16 clinicians and researchers from 14 institutions to assess the utility of LEADS integrated into the expert workflow. In study selection, experts using LEADS achieve 0.81 recall vs. 0.78 without, saving 20.8% time. For data extraction, accuracy reached 0.85 vs. 0.80, with 26.9% time savings. These findings encourage future work on leveraging high-quality domain data to build specialized LLMs that outperform generic models and enhance expert productivity in literature mining.

We report a case of acute macular neuroretinopathy (AMN) following routine annual inactivated influenza vaccination. Projection-resolved optical coherence tomography angiography (PR-OCTA) was used to analyze the retinal capillary flow within the AMN lesion. Our patient reported visual symptoms of her right eye nine days after routine annual influenza vaccination. Multimodal imaging revealed small vessel peripheral vasculitis and AMN in the affected eye. Infectious, immunologic, and hypercoagulable etiologies were investigated and excluded. PR-OCTA B-scans within the AMN lesion demonstrated reduced flow in the deep capillary plexus (DCP) at baseline with relatively improved flow signal in the DCP on follow up, 3 weeks later. We report a new association of AMN following routine inactivated influenza immunization. Recent influenza vaccination should be included in the differential diagnosis for patients presenting with AMN. PR-OCTA demonstrated compromised DCP flow in the AMN lesion which has not been previously described.

Clinical informatics, decision support for health professionals, electronic health records, and ehealth infrastructures.

Purpose: Neovascular age-related macular degeneration (nv-AMD) is the leading cause of blindness in individuals 55 years and older. The advent of anti-vascular endothelial growth factor (anti-VEGF) therapy has greatly altered the visual acuity (VA) prognosis in these patients. While many studies have described treatment outcomes, few have explored the impact of early detection on VA outcomes. Patients and Methods: This retrospective cohort study consisted of treatment-naïve eyes with nv-AMD (ICD9 diagnosis code 362.52) that were treated with bevacizumab, ranibizumab, and aflibercept by four physician investigators in a large urban tertiary center from March 2008 to October 2015. Eyes were categorized by baseline VA into good (20/50 or better), intermediate (20/50– 20/200), and poor (20/200 or worse) initial VA. VA and optical coherence tomography (OCT) findings were evaluated throughout the treatment period. Results: 224 eyes were evaluated. Of eyes with good, intermediate, and poor initial VA, 14.1%, 37.2%, and 58.3% showed an increase in 2 or more lines of vision on LogMAR, respectively [p < 0.001], while 71.8%, 40.7%, and 16.7% of eyes had a final VA of 20/50 or better, respectively [p < 0.001]. Average final Snellen VA in eyes with good, intermediate, and poor initial VA was 20/47, 20/96, and 20/277, respectively. Change in VA for good, intermediate, and poor initial VA groups was ΔLogMAR of +0.117, +0.041, and − 0.230, respectively. Of eyes with good, intermediate, and poor baseline VA, 42.3%, 20.9%, and 20.0%, respectively, showed resolution of fluid on OCT [p = 0.003]. Conclusion: Patients with good initial VA were more likely to maintain good vision and show resolution of fluid on OCT through follow-up. Patients with poor initial VA tended to gain more vision, however, had poorer final VA. This underscores the importance of early detection and treatment of nv-AMD in maintaining superior outcomes.