The aim of this study was to evaluate the impact of BRAF inhibitors on survival outcomes in patients receiving stereotactic radiosurgery (SRS) for melanoma brain metastases. We prospectively collected treatment parameters and outcomes for 80 patients with melanoma brain metastases who underwent SRS. Thirty-five patients harbored the BRAF mutation (BRAF-M) and 45 patients did not (BRAF-WT). Univariate and multivariate analyses were performed to identify predictors of overall survival. The median overall survival from first SRS procedure was 6.7, 11.2 months if treated with a BRAF inhibitor and 4.5 months for BRAF-WT. Actuarial survival rates for BRAF-M patients on an inhibitor were 54 % at 6 months and 41 % at 12 months from the time of SRS. In contrast, BRAF-WT had overall survival rates of 28 % at 6 months and 19 % at 12 months. Overall survival was extended for patients on a BRAF inhibitor at or after the first SRS. The median time to intracranial progression was 3.9 months on a BRAF inhibitor and 1.7 months without. The local control rate for all treated tumors was 92.5 %, with no difference based on BRAF status. Patients with higher KPS, fewer treated intracranial metastases, controlled systemic disease, RPA Class 1 and BRAF-M patients had extended overall survival. Overall, patients with BRAF-M treated with both SRS and BRAF inhibitors, at or after SRS, have increased overall survival from the time of SRS. As patients live longer as a result of more effective systemic and local therapies, close surveillance and early management of intracranial disease with SRS will become increasingly important.

No abstract

Introduction Age-related macular degeneration, diabetic retinopathy, and glaucoma are vision-threatening diseases that are leading causes of vision loss. Many studies have validated deep learning artificial intelligence for image-based diagnosis of vision-threatening diseases. Our study prospectively investigated deep learning artificial intelligence applications in student-run non-mydriatic screenings for an underserved, primarily Hispanic community during COVID-19. Methods Five supervised student-run community screenings were held in West New York, New Jersey. Participants underwent non-mydriatic 45-degree retinal imaging by medical students. Images were uploaded to a cloud-based deep learning artificial intelligence for vision-threatening disease referral. An on-site tele-ophthalmology grader and remote clinical ophthalmologist graded images, with adjudication by a senior ophthalmologist to establish the gold standard diagnosis, which was used to assess the performance of deep learning artificial intelligence. Results A total of 385 eyes from 195 screening participants were included (mean age 52.43  ±  14.5 years, 40.0% female). A total of 48 participants were referred for at least one vision-threatening disease. Deep learning artificial intelligence marked 150/385 (38.9%) eyes as ungradable, compared to 10/385 (2.6%) ungradable as per the human gold standard ( p < 0.001). Deep learning artificial intelligence had 63.2% sensitivity, 94.5% specificity, 32.0% positive predictive value, and 98.4% negative predictive value in vision-threatening disease referrals. Deep learning artificial intelligence successfully referred all 4 eyes with multiple vision-threatening diseases. Deep learning artificial intelligence graded images (35.6  ±  13.3 s) faster than the tele-ophthalmology grader (129  ±  41.0) and clinical ophthalmologist (68  ±  21.9, p < 0.001). Discussion Deep learning artificial intelligence can increase the efficiency and accessibility of vision-threatening disease screenings, particularly in underserved communities. Deep learning artificial intelligence should be adaptable to different environments. Consideration should be given to how deep learning artificial intelligence can best be utilized in a real-world application, whether in computer-aided or autonomous diagnosis.

No abstract

No abstract