nference, the artificial intelligence (AI)-driven health technology company, today announced publication of a study in the Journal of Stroke and Cerebrovascular Diseases that analyzed Mayo Clinic health records with nference AI software to suggest that cerebral venous sinus thrombosis (CVST) is not significantly linked to COVID-19 vaccines. The journal publishes peer-reviewed original papers on basic and clinical science related to the fields of stroke and cerebrovascular diseases.

Authors of the study from nference and the Mayo Clinic, "Cerebral venous sinus thrombosis (CVST) is not significantly linked to COVID-19 vaccines or non-COVID vaccines in a large multi-state US health system," investigated the frequency of CVST symptoms in individuals who received a combined total of more than 132,000 doses of FDA-authorized COVID-19 vaccines, as well as individuals who received more than 771,000 doses of one of 10 FDA-approved non-COVID-19 vaccines. The results show that CVST cannot be significantly associated with any COVID-19 vaccination, and that there has been no significant increase in CVST incidence rates following COVID-19 vaccination.

"This study comes at a critical moment in the pandemic and provides independent evidence that it is generally safe to be vaccinated against COVID-19. Our real-world, independent analysis, conducted with Mayo Clinic physicians, proves that anecdotal reports about the dangers of CVST as a result of COVID-19 vaccines are not generalizable. The real threat is the continued global emergence of SARS-CoV-2 variants, and continued mass vaccination is humanity's best bet to eradicate COVID-19 across our planet," said Venky Soundararajan, PhD, co-founder and chief scientific officer of nference.

Mayo Clinic and nference researchers analyzed lab tests, unstructured clinical notes, and structured health records to quantify CVST prevalence with and without vaccines, something that would not be possible without machine-augmented large-scale EHR curation. In the process of conducting these studies, nference employed its leading-edge augmented intelligence software, nferX?, which uses proprietary neural networks for automatically curating the context and sentiment embedded in the text of physician notes, and an ensemble of machine learning models that then rapidly synthesize and process these insights with various other disparate biomedical data sources in previously incompatible formats. The company's real-time software for real-world evidence curation-at-scale will continue to monitor and enable rapid up-to-date safety, effectiveness, and durability assessments of vaccines as new and updated information becomes available including to emergent strains of concern globally.

"We were able to quickly gather and synthesize records, tests and key patient data to efficiently report these findings," added Andrew Badley, MD, co-author of the study, and Mayo Clinic's enterprise chair of the department of molecular medicine and enterprise chair of COVID-19 task force. 

The innovative and powerful AI technology implemented by nference during the COVID-19 pandemic has enabled discoveries with a wide range of implications that contribute to a greater understanding of the SARS-CoV-2 virus and the COVID-19 disease, which are ultimately advancing a plethora of applications in patient care and informing important public health policy decisions. 

About nference

Through its powerful augmented intelligence software nferX?, nference is transforming health care by making biomedical knowledge computable. The platform partnership with Mayo Clinic has given nference an opportunity to fully de-identify and synthesize more than 100 years of institutional wisdom, producing real-world evidence in real time by converting large amounts of knowledge into deep insights that advance discovery and development of diagnostics and therapeutics. nference is headquartered in Cambridge, Massachusetts and has operations in Rochester, Minnesota; Toronto, Canada; and Bangalore, India.