Universal risk phenotype of US counties for flu-like transmission to improve county-specific COVID-19 incidence forecasts

The spread of a communicable disease is a complex spatio-temporal process shaped by the specific transmission mechanism, and diverse factors including the behavior, socio-economic and demographic properties of the host population. While the key factors shaping transmission of influenza and COVID-19 are beginning to be broadly understood, making precise forecasts on case count and mortality is still difficult. In this study we introduce the concept of a universal geospatial risk phenotype of individual US counties facilitating flu-like transmission mechanisms. We call this the Universal Influenza-like Transmission (UnIT) score, which is computed as an information-theoretic divergence of the local incidence time series from an high-risk process of epidemic initiation, inferred from almost a decade of flu season incidence data gleaned from the diagnostic history of nearly a third of the US population. Despite being computed from the past seasonal flu incidence records, the UnIT score emerges as the dominant factor explaining incidence trends for the COVID-19 pandemic over putative demographic and socio-economic factors. The predictive ability of the UnIT score is further demonstrated via county-specific weekly case count forecasts which consistently outperform the state of the art models throughout the time-line of the COVID-19 pandemic. This study demonstrates that knowledge of past epidemics may be used to chart the course of future ones, if transmission mechanisms are broadly similar, despite distinct disease processes and causative pathogens.Author summary: Accurate case count forecasts in an epidemic is non-trivial, with the spread of infectious diseases being modulated by diverse hard-to-model factors. This study introduces the concept of a universal risk phenotype for US counties that predictably increases the risk of person-to-person transmission of influenza-like illnesses; universal in the sense that it is pathogen-agnostic provided the transmission mechanism is similar to that of seasonal influenza. We call this the Universal Influenza-like Transmission (UnIT) score, which accounts for unmodeled effects by automatically leveraging subtle geospatial patterns underlying the flu epidemics of the past. It is a phenotype of the counties themselves, as it characterizes how the transmission process is differentially impacted in different geospatial contexts. Grounded in information-theory and machine learning, the UnIT score reduces the need to manually identify every factor that impacts the case counts. Applying to the COVID-19 pandemic, we show that incidence patterns from a past epidemic caused by an appropriately-chosen distinct pathogen can substantially inform future projections. Our forecasts consistently outperform the state of the art models throughout the time-line of the COVID-19 pandemic, and thus is an important step to inform policy decisions in current and future pandemics.