Development of a Multivariate Digital Biomarker of Vaccine-Induced Inflammation and its Relationship to Immunogenicity

Vaccine-induced inflammation is detectable by identifying changes in an individual’s physiologic parameters when the pre-vaccine baseline normal variation in those parameters is known. We developed a multivariate digital biomarker that incorporates changes in multiple continuously monitored physiologic data streams, and their interactions with each other, as a more sensitive measure of the degree and duration of vaccine induced inflammation. 97 participants wore a torso ECG patch ~5 days before, and ~9 days after a second or booster dose of either available mRNA vaccine. The patch records raw ECG, 3-axis accelerometer, and skin temperature, which are processed using cloud-based analytics to produce 17 source signals at a one-minute intervals. The analytics platform uses a machine learning method of similarity-based modeling (SBM), which learns the dynamic interplay between multivariate input sources. Personalized baseline models of each participant’s unique physiological dynamics are established and applied to effectively remove expected variations, leaving only vaccine-induced differences. These differences are combined into an inflammatory Multivariate Change Index (iMCI), which is updated on a 15-minute basis, allowing for the tracking of the onset, offset and degree of inflammatory change after vaccination. In a substudy of 21 individuals, changes in humoral and cellular immunity will be determined and the association with physiologic manifestations of inflammation explored. Moderator: James A. Glazier, PhD, Indiana University, Bloomington For more information visit: https://www.physiq.com/ If you found this video useful, please check out our other videos on computational modeling, infection and immunology: https://tinyurl.com/GLIMPRINTVideos Please consider joining our IMAG/MSM WG on Multiscale Modeling and Viral Pandemics: https://www.imagwiki.nibib.nih.gov/content/msm-viral-pandemics-meetings Please also consider joining the Global Alliance for Immune Prediction and Intervention: http://glimprint.org/