Citations

Background and Objective: This study aimed to characterize clinical characteristics and visual outcomes of patients with hemorrhagic choroidal detachments. Patients and Methods: Single-center retrospective case series of patients with hemorrhagic choroidal detachments from January 1, 2003, to December 31, 2020 at Mayo Clinic. Patients were categorized as appositional or non-appositional based on ultra-sonography. Results: Among 39 cases with hemorrhagic choroidal detachments, 15 (38%) were appositional and 24 (62%) were non-appositional. There was a significant difference between the appositional and non-appositional groups in mean initial logMAR visual acuity (VA) (2.8 [ SD = 0.20] vs 2.2 [ SD = 0.78], P < .001). However, no difference was observed in final logMAR VA (1.9 [ SD = 1.2] vs 1.5 [ SD = 1.1], P = .30). Comparison between surgical ( N = 9) versus non-surgical ( N = 5) hemorrhagic appositional choroidal detachments cases revealed no differences in outcomes. Comparison between anticoagulated ( N = 21) versus nonanticoagulated ( N = 18) patients with hemorrhagic choroidal detachments also revealed no differences in outcomes. Conclusion: Patients with appositional and nonappositional hemorrhagic choroidal detachments did not differ significantly with regards to visual outcome. Surgical intervention was not associated with improved final vision in this cohort.

Background: The rapid adoption of digital pathology and artificial intelligence (AI) in oncology creates multiple opportunities for precision diagnostics but also creates an urgent need for evidence-based standards to ensure safe and effective implementation. Goal: This article, developed by the Digital Pathology Association, presents recommendations for digital pathology as well as the validation and clinical utility of AI-enabled digital pathology tools in clinical practice. This guidance addresses analytical and clinical validation, algorithm reliability, and criteria for establishing clinical utility attributed to test use. Key recommendations emphasize separate validation of scanning processes and AI algorithms, concordance studies to support interscanner generalizability, rigorous assessment of accuracy and reliability in real-world settings, and clear description of algorithmic use limitations. These recommendations further provide frameworks for when AI may replace or augment existing diagnostic approaches, such as biomarker scoring, cancer diagnosis, and prognostic risk assessment. Conclusions: By considering payer, regulatory, and clinical perspectives, the recommendations promote transparency, trust, and reproducibility in digital pathology while encouraging value-based care delivery. We support responsible innovation in computational pathology, ensuring that AI applications achieve not only technical performance goals but also deliver measurable clinical benefit to patients.