Individually Tuned Causal Models of Disease Progression

Situation Awareness in health care involves two dif-ferent sets of concerns that are only exacerbated in a pandemic. First is the societal: who is exposed, who is infected, when and how they interact with others, and how can we reduce the severity of impact (epidemiological). Second is the personal: what happens or will happen to each person, and how we can improve that result (individual). This paper is about the latter. It describes an approach to building and maintaining models of disease progression using advanced mathematical methods. These models will be tuned to individual patients, based on the existing and arriving measurement data, as the disease is progressing. The initial models will be generic representations, based on medical expertise, of the current understanding of the various ways the disease can progress. The models will be changed, adjusted separately for each individual patient, according to the newly arriving measurements. This paper describes the technical approach, the purpose and style of modeling we propose, and what we can expect to learn from the application of these methods. The target disease for these first experiments is COVID-19.