Background. Solid organ transplant recipients (SOTRs) are less likely to mount an antibody response to SARS-CoV-2 mRNA vaccines. Understanding risk factors for impaired vaccine response can guide strategies for antibody testing and additional vaccine dose recommendations. Methods. Using a nationwide observational cohort of 1031 SOTRs, we created a machine learning model to explore, identify, rank, and quantify the association of 19 clinical factors with antibody responses to 2 doses of SARS-CoV-2 mRNA vaccines. External validation of the model was performed using a cohort of 512 SOTRs at Houston Methodist Hospital. Results. Mycophenolate mofetil use, a shorter time since transplant, and older age were the strongest predictors of a negative antibody response, collectively contributing to 76% of the model's prediction performance. Other clinical factors, including transplanted organ, vaccine type (mRNA-1273 versus BNT162b2), sex, race, and other immunosuppressants, showed comparatively weaker associations with an antibody response. This model showed moderate prediction performance, with an area under the receiver operating characteristic curve of 0.79 in our cohort and 0.67 in the external validation cohort. An online calculator based on our prediction model is available at http:// transplantmodels.com/covidvaccine/. Conclusions. Our machine learning model helps understand which transplant patients need closer follow-up and additional doses of vaccine to achieve protective immunity. The online calculator based on this model can be incorporated into transplant providers' practice to facilitate patient-centric, precision risk stratification and inform vaccination strategies among SOTRs.

Background. A widely accepted severe acute respiratory syndrome 2 (SARS-CoV-2) vaccine could protect vulnerable populations, but the willingness of solid organ transplant recipients (SOTRs) to accept a potential vaccine remains unknown. Methods. We conducted a national survey of 1308 SOTRs and 1617 non-SOTRs between November 11 and December 2, 2020 through the network of the National Kidney Foundation. Results. Respondents were largely White (73.2%), female (61.1%), and college graduates (56.2%). Among SOTRs, half (49.5%) were unsure or would be unwilling to receive a SARS-CoV-2 vaccine once available. Major concerns included potential side effects (85.2%), lack of rigor in the testing and development process (69.7%), and fear of incompatibility with organ transplants (75.4%). Even after the announcement of the high efficacy of the mRNA-1273 vaccine (Moderna Inc.) at the time of survey distribution, likeliness to receive a vaccine only slightly increased (53.5% before announcement versus 57.8% after the announcement). However, 86.8% of SOTRs would accept a vaccine if recommended by a transplant provider. Conclusions. SOTRs reported skepticism in receiving a potential SARS-CoV-2 vaccine, even after announcements of high vaccine efficacy. Reassuringly, transplant providers may be the defining influence in vaccine acceptance and will likely have a critical role to play in promoting vaccine adherence.

T he Omicron variant has caused an unprecedented surge in SARS-CoV-2 infections among vaccinated people in the United States, owing to high transmissibility, immune evasion, and higher circulating antibodies required to achieve neutralization. Vaccine-derived protection is suboptimal among solid organ transplant recipients (SOTRs). [1][2][3][4][5] We studied frequency and severity of COVID-19 breakthrough during the US Omicron wave (December 25, 2021-March 1, 2022 in vaccinated SOTRs, focusing on the effect of preceding antispike antibody level.A total of 1801 >3×-vaccinated SOTRs from our national observational cohort were surveyed about incident COVID-19 during the Omicron wave, of whom 1467 (81%) responded. A subgroup (n = 666) was tested for antispike antibodies on 1 of 2 clinical assays correlated with neutralizing capacity: the Roche Elecsys anti-receptor binding domain (RBD) or Euroimmun antispike (S1) clinical assay. We used the most recent preinfection titer (measured between November 26, 2021, and March 7, 2022) for those reporting incident COVID-19 and titers measured between November 26, 2021, and December 25, 2021, for those reporting no incident COVID-19. Exclusion criteria included receiving monoclonal antibodies within the last 6 mo (n = 82), skipped key survey questions (n = 334), not having a recent titer (n = 654), and previously having . This study was approved by the Johns Hopkins Institutional Review Board; participants provided informed consent electronically.A total of 150 of 1467 (10%) reported a positive PCR or home SARS-CoV-2 antigen test ("confirmed") at a median (interquartile range) 134 (109-146) d since receiving their last vaccine, 25 of 1467 (2%) reported COVID-19 symptoms/suspicion but did not test positive ("suspected"), and 1292 of 1467 (88%) reported no confirmed or suspected COVID-19 during the follow-up period. Two deaths were reported during the follow-up period (both secondary to COVID-19) by family members. Eleven of 173 (6%) SOTRs with confirmed or suspected COVID-19 reported hospitalization for COVID-19. Sixty-four of 173 (37%) reported moderate symptoms (significant fever or shortness of breath), 97 of 173(56%) reported mild cold-like symptoms, and 9 of 173(5%) were asymptomatic (2 did not respond). The most common symptoms were nasal congestion (71%), cough (61%), malaise (58%), headache (57%), and sore throat (57%). There was a greater proportion of lung transplant recipients (24% versus 8%, P < 0.001) and those taking calcineurin-inhibitors (100% versus 86%, P = 0.015) in the COVID-19-confirmed group (Table 1). A sensitivity analysis was performed excluding those with suspected/ unconfirmed COVID-19, and inferences were unchanged, so they were included in the no-COVID-19 group. Letter to the Editor