FluSense: Harnessing Syndromic Signals of Influenza-Like Illness from Hospital Waiting Room Crowd with Contactless Sensing System

摘要

Influenza is a highly contagious respiratory infection that leads to regular seasonal epidemics. It is a major contributor to morbidity and mortality, and in the United States, since 2010, it has infected between 9.2 million and 60.8 million people and has caused between 12,000 and 56,000 deaths. [2]. Moreover, the economic impact [1] of influenza is estimated to be 47 billion to 150 billion dollars per year in the USA alone. The state-of-the-art disease monitoring and public health surveillance by the Centers for Disease Control and Prevention (CDC) primarily rely on aggregated reports from sentinel reporting sites including hospitals and selected outpatient clinics. Additionally, virologic surveillance aggregates data from elaborated blood and saliva testing from clinical laboratories affiliated with the CDC. While the existing public health surveillance provides highly accurate, specific, and detailed information about confirmed case counts and the relative prevalence of different types and subtypes of a specific infectious disease, there is a substantial lag time in the reporting of these data (as outlined in figure 1). For example, the influenza-like illness related data at CDC is available only 7 to 14 days after the visit itself, and during holiday periods this delay can be extended, which adversely impacts the model's forecast accuracy. More importantly, current public health monitoring programs primarily measure the clinical population (individuals seeking help from hospitals or clinics) and preclinical (individuals remaining outside of the medical database) but symptomatic population remains outside of the view of the institutionalized public health monitoring. The lack of real-time information on the infection process and symptom dynamics experienced by the general population is a fundamental gap that limits our ability to forecast disease trends and mobilize early interventions.