From Early Detection to Disease Profiling

How can machine learning models detect early signs of COVID-19, and be used to profile the post-COVID syndrome? Self-reported symptoms during the SARS-CoV-2 pandemic have shown to be effective in training artificial intelligence (AI) models to identify possible foci of infections. Such models can be further used to early identify SARS-CoV-2 infected individuals, helping to contain the spread of the pandemic and efficiently allocate medical resources. Furthermore, self-reported symptom studies rapidly increased our understanding of SARS-CoV-2 during the pandemic and enabled the monitoring of long-term effects of COVID-19 outside the hospital setting. It is now evident that post-COVID syndrome presents heterogeneous profiles, which need characterization to enable personalized care among the most affected survivors. In this talk, we will be firstly presenting our Hierarchical Gaussian Process model designed for the specific task of early detection of COVID-19, which outperforms the symptoms-based criteria considered in clinical practice for test referencing. Secondly, we will focus on the description and phenotyping of post-COVID symptom profiles, which we have achieved using unsupervised machine learning techniques. Moderator: Tomas Helikar, PhD, University of Nebraska, Lincoln For more details on this topic see: Graham, Mark S., Carole H. Sudre, Anna May, Michela Antonelli, Benjamin Murray, Thomas Varsavsky, Kerstin Klaser, Liane Dos Santos Canas, Erika Molteni, and Marc Modat. "The effect of SARS-CoV-2 variant B. 1.1. 7 on symptomatology, re-infection and transmissibility." MedRxiv 10, no. 2021.01 (2021): 28-21250680. https://pflegefueraufklaerung.de/wp-content/uploads/2021/03/The-effect-of-SARS-CoV-2-variant-B.1.1.7-onsymptomatology-re-infection-and-transmissibility.pdf 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/