Martin Bendszus

Background and purpose Population‐based studies suggest severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) vaccines may trigger neurological autoimmunity including immune‐mediated thrombotic thrombocytopenia. Long‐term characterization of cases is warranted to facilitate patient care and inform vaccine‐hesitant individuals. Methods In this single‐center prospective case study with a median follow‐up of 387 days long‐term clinical, laboratory and imaging characteristics of patients with neurological autoimmunity diagnosed in temporal association (≤6 weeks) with SARS‐CoV‐2 vaccinations are reported. Results Follow‐up data were available for 20 cases (central nervous system demyelinating diseases n = 8, inflammatory peripheral neuropathies n = 4, vaccine‐induced immune thrombotic thrombocytopenia n = 3, myositis n = 2, myasthenia n = 1, limbic encephalitis n = 1, giant cell arteritis n = 1). Following therapy, the overall disability level improved (median modified Rankin Scale at diagnosis 3 vs. 1 at follow‐up). The condition of two patients worsened despite immunosuppressants possibly related to their autoimmune diagnoses (limbic encephalitis n = 1, giant cell arteritis n = 1). At 12 months’ follow‐up, 12 patients achieved complete clinical remissions with partial responses in five and stable disease in one case. Correspondingly, autoimmune antibodies were non‐detectable or titers had significantly lowered in all, and repeat imaging revealed radiological responses in most cases. Under vigilant monitoring 15 patients from our cohort underwent additional SARS‐CoV‐2 vaccinations (BNT162b2 n = 12, mRNA‐1273 n = 3). Most patients ( n = 11) received different vaccines than prior to diagnosis of neurological autoimmunity. Except for one short‐lasting relapse, which responded well to steroids, re‐vaccinations were well tolerated. Conclusions In this study long‐term characteristics of neurological autoimmunity encountered after SARS‐CoV‐2 vaccinations are defined. Outcome was favorable in most cases. Re‐vaccinations were well tolerated and should be considered on an individual risk/benefit analysis.

Background To assess whether artificial intelligence (AI)-based decision support allows more reproducible and standardized assessment of treatment response on MRI in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden using the Response Assessment in Neuro-Oncology (RANO) criteria. Methods A series of 30 patients (15 lower-grade gliomas, 15 glioblastoma) with availability of consecutive MRI scans was selected. The time to progression (TTP) on MRI was separately evaluated for each patient by 15 investigators over two rounds. In the first round the TTP was evaluated based on the RANO criteria, whereas in the second round the TTP was evaluated by incorporating additional information from AI-enhanced MRI sequences depicting the longitudinal changes in tumor volumes. The agreement of the TTP measurements between investigators was evaluated using concordance correlation coefficients (CCC) with confidence intervals (CI) and P-values obtained using bootstrap resampling. Results The CCC of TTP-measurements between investigators was 0.77 (95% CI = 0.69,0.88) with RANO alone and increased to 0.91 (95% CI = 0.82,0.95) with AI-based decision support (P = .005). This effect was significantly greater (P = .008) for patients with lower-grade gliomas (CCC = 0.70 [95% CI = 0.56,0.85] without vs. 0.90 [95% CI = 0.76,0.95] with AI-based decision support) as compared to glioblastoma (CCC = 0.83 [95% CI = 0.75,0.92] without vs. 0.86 [95% CI = 0.78,0.93] with AI-based decision support). Investigators with less years of experience judged the AI-based decision as more helpful (P = .02). Conclusions AI-based decision support has the potential to yield more reproducible and standardized assessment of treatment response in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden, particularly in patients with lower-grade gliomas. A fully-functional version of this AI-based processing pipeline is provided as open-source (https://github.com/NeuroAI-HD/HD-GLIO-XNAT).