Acceptance and Perception of Artificial Intelligence Usability in Eye Care (APPRAISE) for Ophthalmologists: A Multinational Perspective.

Background: Many artificial intelligence (AI) studies have focused on development of AI models, novel techniques, and reporting guidelines. However, little is understood about clinicians' perspectives of AI applications in medical fields including ophthalmology, particularly in light of recent regulatory guidelines. The aim for this study was to evaluate the perspectives of ophthalmologists regarding AI in 4 major eye conditions: diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and cataract. Methods: This was a multi-national survey of ophthalmologists between March 1st, 2020 to February 29th, 2021 disseminated via the major global ophthalmology societies. The survey was designed based on microsystem, mesosystem and macrosystem questions, and the software as a medical device (SaMD) regulatory framework chaired by the Food and Drug Administration (FDA). Factors associated with AI adoption for ophthalmology analyzed with multivariable logistic regression random forest machine learning. Results: One thousand one hundred seventy-six ophthalmologists from 70 countries participated with a response rate ranging from 78.8 to 85.8% per question. Ophthalmologists were more willing to use AI as clinical assistive tools (88.1%, n = 890/1,010) especially those with over 20 years' experience (OR 3.70, 95% CI: 1.10-12.5, p = 0.035), as compared to clinical decision support tools (78.8%, n = 796/1,010) or diagnostic tools (64.5%, n = 651). A majority of Ophthalmologists felt that AI is most relevant to DR (78.2%), followed by glaucoma (70.7%), AMD (66.8%), and cataract (51.4%) detection. Many participants were confident their roles will not be replaced (68.2%, n = 632/927), and felt COVID-19 catalyzed willingness to adopt AI (80.9%, n = 750/927). Common barriers to implementation include medical liability from errors (72.5%, n = 672/927) whereas enablers include improving access (94.5%, n = 876/927). Machine learning modeling predicted acceptance from participant demographics with moderate to high accuracy, and area under the receiver operating curves of 0.63-0.83. Conclusion: Ophthalmologists are receptive to adopting AI as assistive tools for DR, glaucoma, and AMD. Furthermore, ML is a useful method that can be applied to evaluate predictive factors on clinical qualitative questionnaires. This study outlines actionable insights for future research and facilitation interventions to drive adoption and operationalization of AI tools for Ophthalmology.

Stem cell transplantation impairs dendritic cell trafficking and herpesvirus immunity.

Long-term survivors after hematopoietic stem cell transplantation are at high risk of infection, which accounts for one-third of all deaths related to stem cell transplantation. Little is known about the cause of inferior host defense after immune cell reconstitution. Here, we exploited a murine syngeneic BM transplantation (BMT) model of late infection with murine gammaherpesvirus 68 (MHV-68) to determine the role of conventional DC (cDC) trafficking in adaptive immunity in BMT mice. After infection, the expression of chemokine Ccl21 in the lung is reduced and the migration of cDCs into lung draining lymph nodes (dLNs) is impaired in BMT mice, limiting the opportunity for cDCs to prime Th cells in the dLNs. While cDC subsets are redundant in priming Th1 cells, Notch2 functions in cDC2s are required for priming increased Th17 responses in BMT mice, and cDC1s can lessen this activity. Importantly, Th17 cells can be primed both in the lungs and dLNs, allowing for increased Th17 responses without optimum cDC trafficking in BMT mice. Taken together, impaired cDC trafficking in BMT mice reduces protective Th1 responses and allows increased pathogenic Th17 responses. Thus, we have revealed a previously unknown mechanism for BMT procedures to cause long-term inferior immune responses to herpes viral infection.

First-Onset Herpesviral Infection and Lung Injury in Allogeneic Hematopoietic Cell Transplantation.

Rationale: "Noninfectious" pulmonary complications are significant causes of morbidity and mortality after allogeneic hematopoietic cell transplant. Early-onset viral reactivations or infections are common after transplant. Whether the first-onset viral infection causes noninfectious pulmonary complications is unknown. Objectives: To determine whether the first-onset viral infection within 100 days after transplant predisposes to development of noninfectious pulmonary complications. Methods: We performed a retrospective review of 738 allogeneic hematopoietic cell transplant patients enrolled from 2005 to 2011. We also established a novel bone marrow transplantation mouse model to test whether herpesviral reactivation after transplant causes organ injury. Measurements and Main Results: First-onset viral infections with human herpesvirus 6 or Epstein-Barr virus within 100 days after transplant increase the risk of developing idiopathic pneumonia syndrome (adjusted hazard ratio [aHR], 5.52; 95% confidence interval [CI], 1.61-18.96; P = 0.007; and aHR, 9.21; 95% CI, 2.63-32.18; P = 0.001, respectively). First infection with human cytomegalovirus increases risk of bronchiolitis obliterans syndrome (aHR, 2.88; 95% CI, 1.50-5.55; P = 0.002) and grade II-IV acute graft-versus-host disease (aHR, 1.59; 95% CI, 1.06-2.39; P = 0.02). Murine roseolovirus, a homolog of human herpesvirus 6, can also be reactivated in the lung and other organs after bone marrow transplantation. Reactivation of murine roseolovirus induced an idiopathic pneumonia syndrome-like phenotype and aggravated acute graft-versus-host disease. Conclusions: First-onset herpesviral infection within 100 days after allogeneic hematopoietic cell transplant increases risk of pulmonary complications. Experimentally reactivating murine roseolovirus causes organ injury similar to phenotypes seen in human transplant recipients.