AI in Neuro-Ophthalmology: Current Practice and Future Opportunities.

BACKGROUND: Neuro-ophthalmology frequently requires a complex and multi-faceted clinical assessment supported by sophisticated imaging techniques in order to assess disease status. The current approach to diagnosis requires substantial expertise and time. The emergence of AI has brought forth innovative solutions to streamline and enhance this diagnostic process, which is especially valuable given the shortage of neuro-ophthalmologists. Machine learning algorithms, in particular, have demonstrated significant potential in interpreting imaging data, identifying subtle patterns, and aiding clinicians in making more accurate and timely diagnosis while also supplementing nonspecialist evaluations of neuro-ophthalmic disease. EVIDENCE ACQUISITION: Electronic searches of published literature were conducted using PubMed and Google Scholar. A comprehensive search of the following terms was conducted within the Journal of Neuro-Ophthalmology: AI, artificial intelligence, machine learning, deep learning, natural language processing, computer vision, large language models, and generative AI. RESULTS: This review aims to provide a comprehensive overview of the evolving landscape of AI applications in neuro-ophthalmology. It will delve into the diverse applications of AI, optical coherence tomography (OCT), and fundus photography to the development of predictive models for disease progression. Additionally, the review will explore the integration of generative AI into neuro-ophthalmic education and clinical practice. CONCLUSIONS: We review the current state of AI in neuro-ophthalmology and its potentially transformative impact. The inclusion of AI in neuro-ophthalmic practice and research not only holds promise for improving diagnostic accuracy but also opens avenues for novel therapeutic interventions. We emphasize its potential to improve access to scarce subspecialty resources while examining the current challenges associated with the integration of AI into clinical practice and research.

MICK (Mobile Integrated Cognitive Kit) App for Concussion Assessment in a Youth Ice Hockey League.

BACKGROUND: Visual symptoms are common after concussion. Rapid automatized naming (RAN) tasks are simple performance measures that demonstrate worse time scores in the setting of acute or more remote injury. METHODS: We evaluated the capacity for the Mobile Universal Lexicon Evaluation System (MULES) and Staggered Uneven Number (SUN) testing to be feasibly administered during preseason testing in a cohort of youth ice hockey athletes using a novel computerized app, the Mobile Integrated Cognitive Kit (MICK). Participants from a youth hockey league underwent preseason testing. RESULTS: Among 60 participants, the median age was 13 years (range 6-17). The median best time for the MULES was 49.8 seconds (range = 34.2-141.0) and the median best time for the SUN was 70.1 (range = 36.6-200.0). As is characteristic of timed performance measures, there were learning effects between the first and second trials for both the MULES (median improvement = 10.6 seconds, range = -32.3 to 92.0, P < 0.001, Wilcoxon signed-rank test) and SUN (median improvement = 2.4 seconds, range= -8.0 to 15.1, P = 0.001, Wilcoxon signed-rank test). Age was a predictor of best baseline times, with longer (worse) times for younger participants for MULES (P < 0.001, rs = -0.67) and SUN (P < 0.001, rs = -0.54 Spearman rank correlation). Degrees of learning effect did not vary with age (P > 0.05, rs = -0.2). CONCLUSIONS: Vision-based RAN tasks, such as the MULES and SUN, can be feasibly administered using the MICK app during preseason baseline testing in youth sports teams. The results suggest that more frequent baseline tests are necessary for preadolescent athletes because of the relation of RAN task performance to age.

Early reflector localization improves the accuracy of localization and excision of a previously positive axillary lymph node following neoadjuvant chemotherapy in patients with breast cancer.

PURPOSE: Clipped axillary lymph node (CALN) localization after neoadjuvant chemotherapy (NAC) for axillary node positive breast cancer can be difficult due to significant shrinkage or disappearance of the CALN after NAC. This study compares wire localization to a radar-based localization system utilizing a reflector that can be placed before or during NAC, in the months before definitive surgery, to facilitate accurate localization and excision of the CALN. METHODS: Between 2016 and 2019, women with T0-4 N1-3 M0 breast cancer who underwent NAC followed by axillary surgery with planned excision of a biopsy positive or clinically suspicious axillary node via wire or reflector localization were identified. A retrospective chart review was performed comparing successful localization and CALN retrieval by each localization technique. RESULTS: Ninety-nine patients met inclusion criteria. Forty-two patients underwent wire localization while 57 patients underwent reflector localization of the CALN. Successful identification of the CALN by wire or reflector was equivalent (83.3% vs 84.2%, respectively). Twenty-two reflectors placed before or during early/mid NAC (early placement) had 100% successful CALN localization and retrieval in the OR. Placement of wire or reflector localization devices within 8 weeks of surgery (late placement) only resulted in 79.2% localization success (p = .02). CONCLUSION: This study suggests a benefit of axillary lymph node reflector placement in the early NAC setting. Early reflector placement allows for more accurate excision of the CALN during axillary surgery after NAC as compared to placement of localization wires or reflectors in the few weeks prior to surgery.

Robust immune responses are observed after one dose of BNT162b2 mRNA vaccine dose in SARS-CoV-2-experienced individuals.

The use of coronavirus disease 2019 (COVID-19) vaccines will play the major role in helping to end the pandemic that has killed millions worldwide. COVID-19 vaccines have resulted in robust humoral responses and protective efficacy in human trials, but efficacy trials excluded individuals with a prior diagnosis of COVID-19. As a result, little is known about how immune responses induced by mRNA vaccines differ in individuals who recovered from COVID-19. Here, we evaluated longitudinal immune responses to two-dose BNT162b2 mRNA vaccination in 15 adults who had experienced COVID-19, compared to 21 adults who did not have prior COVID-19. Consistent with prior studies of mRNA vaccines, we observed robust cytotoxic CD8+ T cell responses in both cohorts after the second dose. Furthermore, SARS-CoV-2­naive individuals had progressive increases in humoral and antigen-specific antibody-secreting cell (ASC) responses after each dose of vaccine, whereas SARS-CoV-2­experienced individuals demonstrated strong humoral and antigen-specific ASC responses to the first dose but these responses were not further enhanced after the second dose of the vaccine at the time points studied. Together, these data highlight the relevance of immunological history for understanding vaccine immune responses and may have implications for personalizing mRNA vaccination regimens used to prevent COVID-19, including for the deployment of booster shots.

Robust immune responses after one dose of BNT162b2 mRNA vaccine dose in SARS-CoV-2 experienced individuals.

The use of COVID-19 vaccines will play the major role in helping to end the pandemic that has killed millions worldwide. COVID-19 vaccines have resulted in robust humoral responses and protective efficacy in human trials, but efficacy trials excluded individuals with a prior diagnosis of COVID-19. As a result, little is known about how immune responses induced by mRNA vaccines differ in individuals who recovered from COVID-19. Here, we evaluated longitudinal immune responses to two-dose BNT162b2 mRNA vaccination in 15 adults who recovered from COVID-19, compared to 21 adults who did not have prior COVID-19 diagnosis. Consistent with prior studies of mRNA vaccines, we observed robust cytotoxic CD8+ T cell responses in both cohorts following the second dose. Furthermore, SARS-CoV-2-naive individuals had progressive increases in humoral and antigen-specific antibody-secreting cell (ASC) responses following each dose of vaccine, whereas SARS-CoV-2-experienced individuals demonstrated strong humoral and antigen-specific ASC responses to the first dose but muted responses to the second dose of the vaccine at the time points studied. Together, these data highlight the relevance of immunological history for understanding vaccine immune responses and may have significant implications for personalizing mRNA vaccination regimens used to prevent COVID-19, including booster shots.