Real-time analysis of a mass vaccination effort via an Artificial Intelligence platform confirms the safety of FDA-authorized COVID-19 vaccines

As the COVID-19 vaccination campaign unfolds as one of the most rapid and widespread in history, it is important to continuously assess the real world safety of the FDA-authorized vaccines. Curation from large-scale electronic health records (EHRs) allows for near real-time safety evaluations that were not previously possible. Here, we advance context- and sentiment-aware deep neural networks over the multi-state Mayo Clinic enterprise (Minnesota, Arizona, Florida, Wisconsin) for automatically curating the adverse effects mentioned by physicians in over 108,000 EHR clinical notes between December 1st 2020 to February 8th 2021. We retrospectively compared the clinical notes of 31,069 individuals who received at least one dose of the Pfizer/BioNTech or Moderna vaccine to those of 31,069 unvaccinated individuals who were propensity matched by demographics, residential location, and history of prior SARS-CoV-2 testing. We find that vaccinated and unvaccinated individuals were seen in the the clinic at similar rates within 21 days of the first or second actual or assigned vaccination dose (first dose Odds Ratio = 1.13, 95% CI: 1.09-1.16; second dose Odds Ratio = 0.89, 95% CI: 0.84-0.93). Further, the incidence rates of all surveyed adverse effects were similar or lower in vaccinated individuals compared to unvaccinated individuals after either vaccine dose. Finally, the most frequently documented adverse effects within 7 days of each vaccine dose were arthralgia (Dose 1: 0.59%; Dose 2: 0.39%), diarrhea (Dose 1: 0.58%; Dose 2: 0.33%), erythema (Dose 1: 0.51%; Dose 2: 0.31%), myalgia (Dose 1: 0.40%; Dose 2: 0.34%), and fever (Dose 1: 0.27%; Dose 2: 0.31%). These remarkably low frequencies of adverse effects recorded in EHRs versus those derived from active solicitation during clinical trials (arthralgia: 24-46%; erythema: 9.5-14.7%; myalgia: 38-62%; fever: 14.2-15.5%) emphasize the rarity of vaccine-associated adverse effects requiring clinical attention. This rapid and timely analysis of vaccine-related adverse effects from contextually rich EHR notes of 62,138 individuals, which was enabled through a large scale Artificial Intelligence (AI)-powered platform, reaffirms the safety and tolerability of the FDA-authorized COVID-19 vaccines in practice.

Mapping each pre-existing conditions association to short-term and long-term COVID-19 complications

Understanding the relationships between pre-existing conditions and complications of COVID-19 infection is critical to identifying which patients will develop severe disease. Here, we leverage 1.1 million clinical notes from 1,903 hospitalized COVID-19 patients and deep neural network models to characterize associations between 21 pre-existing conditions and the development of 20 complications (e.g. respiratory, cardiovascular, renal, and hematologic) of COVID-19 infection throughout the course of infection (i.e. 0-30 days, 31-60 days, and 61-90 days). Pleural effusion was the most frequent complication of early COVID-19 infection (23% of 383 complications) followed by cardiac arrhythmia (12% of 383 complications). Notably, hypertension was the most significant risk factor associated with 10 different complications including acute respiratory distress syndrome, cardiac arrhythmia and anemia. Furthermore, novel associations between cancer (risk ratio: 3, p=0.02) or immunosuppression (risk ratio: 4.3, p=0.04) with early-onset heart failure have also been identified. Onset of new complications after 30 days is rare and most commonly involves pleural effusion (31-60 days: 24% of 45 patients, 61-90 days: 25% of 36 patients). Overall, the associations between pre-COVID conditions and COVID-associated complications presented here may form the basis for the development of risk assessment scores to guide clinical care pathways.

Pre-existing conditions are associated with long-COVID patients hospitalization, despite confirmed clearance of SARS-CoV-2 virus

The current diagnostic gold-standard for SARS-CoV-2 clearance from infected patients is two consecutive negative PCR test results. However, there are anecdotal reports of hospitalization from protracted COVID complications despite such confirmed viral clearance, presenting a clinical conundrum. We conducted a retrospective analysis of 266 COVID patients to compare those that were admitted/re-admitted post-viral clearance (hospitalized post-clearance cohort, n=93) with those that were hospitalized pre-clearance but were not re-admitted post-viral clearance (non-hospitalized post-clearance cohort, n=173). In order to differentiate these two cohorts, we used neural network models for the augmented curation of comorbidities and complications with positive sentiment in the EHR physician notes. In the year preceding COVID onset, acute kidney injury (n=15 (16.1%), p-value: 0.03), anemia (n=20 (21.5%), p-value: 0.02), and cardiac arrhythmia (n=21 (22.6%), p-value: 0.05) were significantly enriched in the physician notes of the hospitalized post-clearance cohort. This study highlights that these specific pre-existing conditions are associated with amplified hospitalization risk in COVID patients, despite their successful SARS-CoV-2 viral clearance. Our finding that pre-COVID anemia amplifies risk of post-COVID hospitalization is particularly concerning given the high prevalence and endemic nature of anemia in many low- and middle-income countries (per the World Bank definition; e.g. India, Brazil), which are unfortunately also seeing high rates of SARS-CoV-2 infection and COVID-induced mortality. This study motivates follow-up prospective research into the specific risk factors we have identified that appear to predispose some patients towards the after effects of COVID-19. Article summary - Strengths and limitations of this studyO_LIThis is the first study at a major healthcare center analyzing risk factors for post-viral clearance hospitalization of COVID-19 patients. C_LIO_LIThis analysis uses augmented curation methods to identify complications and comorbidities from the physician notes, rather than relying upon ICD codes. C_LIO_LIThe statistical analysis identifies specific comorbidities in the year preceding PCR diagnosis of SARS-CoV-2 which are associated with increased rates of post-viral clearance hospitalization. C_LIO_LIThe dataset used for this study is limited to a single healthcare system, so the underlying clinical characteristics of the study population are biased to reflect the clinical characteristics of individuals that receive medical treatment in certain regions of the United States (Arizona, Florida, Minnesota). C_LIO_LIIn this study, we use the first of two consecutive negative PCR tests to estimate the viral clearance date for each patient, however the true viral clearance date for each patient is unknown. C_LI

Multi-pronged human protein mimicry by SARS-CoV-2 reveals bifurcating potential for MHC detection and immune evasion

The hand of molecular mimicry in shaping SARS-CoV-2 evolution and immune evasion remains to be deciphered. We identify 33 distinct 8-mer/9-mer peptides that are identical between SARS-CoV-2 and human proteomes, along similar extents of viral mimicry observed in other viruses. Interestingly, 20 novel peptides have not been observed in any previous human coronavirus (HCoV) strains. Four of the total mimicked 8-mers/9-mers map onto HLA-B*40:01, HLA-B*40:02, and HLA-B*35:01 binding peptides from human PAM, ANXA7, PGD, and ALOX5AP proteins. This mimicry of multiple human proteins by SARS-CoV-2 is made salient by the targeted genes being focally expressed in arteries, lungs, esophagus, pancreas, and macrophages. Further, HLA-A*03 restricted 8-mer peptides are shared broadly by human and coronaviridae helicases with primary expression of the mimicked human proteins in the neurons and immune cells. This study presents the first comprehensive scan of peptide mimicry by SARS-CoV-2 of the human proteome and motivates follow-up research into its immunological consequences.