JMIR Publications

ABSTRACT

Background:

The burden of influenza-like illness (ILI) is typically estimated via hospitalizations and deaths. However, ILI-associated morbidity not requiring hospitalization remains poorly characterized.

Objective:

The main objective was to characterize ILI burden using commercial wearable sensor data and investigate the extent to which these data correlate with self-reported illness severity and duration. Furthermore, we aimed to determine if ILI-associated changes in wearable sensor data differed between care-seeking and non-care-seeking populations, as well as between those with confirmed influenza infection and those with ILI symptoms only.

Methods:

This study comprised participants enrolled in either FluStudy2020 or the Home Testing of Respiratory Illness (HTRI) study; both studies were similar in design and were conducted between December 2019 and October 2020 in the United States. Participants self-reported ILI-related symptoms and healthcare-seeking behaviors via daily surveys for 120 days, in addition to bi-weekly and monthly surveys. Participants completed self-administered influenza test kits when instructed, based upon self-reported symptoms. Wearable sensor data were recorded for 120 and 150 days for FluStudy2020 and HTRI, respectively. The following day-level wearable sensor features were assessed: total daily steps, active time (time spent with >50 steps per minute), sleep duration, sleep efficiency, and resting heart rate (RHR). For each wearable sensor feature, day-by-day and cumulative ILI burden were determined during the ILI period (Days −4 to +9 relative to symptoms onset), as well as the time to return to baseline (TTRB) ILI-related changes in wearable sensor data were compared between participants who sought care versus those who did not, and between influenza-positive participants versus those with symptoms only. Correlative analyses were performed between wearable sensor data and patient-reported outcomes.

Results:

After combining the FluStudy2020 and HTRI data sets, the final ILI population comprised 2435 participants. Compared with healthy days (baseline), participants with ILI exhibited significantly reduced total daily steps, total active time, and sleep efficiency, as well as increased sleep duration and RHR. Deviations from baseline typically began before symptom onset and were greater in participants who sought healthcare versus those who did not, and in influenza-positive participants versus those with symptoms only. During an ILI event, wearable sensor data changes consistently varied with patient-reported outcomes.

Conclusions:

Our results underscore the potential of wearable sensors to not only discriminate between individuals with and without influenza infections, but also between care-seeking and non-care-seeking populations, which may have future application in healthcare resource planning. Clinical Trial: NCT04245800