Machine Learning for Multiscale Analysis of Biomedical Data
Dissecting the dynamics between survivors versus non-survivors
Overview: Ebola virus (EBOV) was characterized for the first time in 1976 close to the Ebola River, since then, outbreaks of EBOV among humans have appeared sporadically causing high death tolls. EBOV is one of the most lethal pathogens, killing a large proportion of patients within 5–7 days.
State of the art: Deaths caused by EBOV are predominantly associated with uncontrolled viremia and lack of an effective immune response. However, knowledge of the pathogenesis of the disease and its immune response is still largely fragmented. Existing vaccines provided promising results to tackle EBOV infection, however, the process of finding the optimal dose and timing of injection of an experimental vaccine candidate into clinical trials is time-consuming and expensive.
Our research in Ebola infection aims to:
derive mathematical models to disentangle the multifactorial events between survivors versus non-survivors to Ebola disease
tailor prophylactic and therapeutic vaccines that maximize the probability to survive EBOV infections
develop multiscale models as a virtual disease tool to evaluate therapies and public health policies during Ebola outbreaks
Relevant Publications in this Field:
V.K. Nguyen, Rafael Mikolajczyk, E.A. Hernandez-Vargas. High-Resolution epidemic simulation using within-host infection and contact data. BMC Public Health. 2018[Preprint] [PDF]
V.K. Nguyen and E.A. Hernandez-Vargas. Windows of opportunity for Ebola virus infection treatment and vaccination. Scientific Reports. 7(8975):1-10, 2017[PDF]
V. K. Nguyen, S. C. Binder, A. Boianelli, M. Meyer-Hermann and E. A. Hernandez-Vargas. Ebola Virus Infection Modelling and Identifiability Problems. Frontiers Microbiology. Vol. 6(257): 1-11, 2015[PDF].