System and Method to Determine ME/CFS and Long COVID Disease Severity Using a Wearable Sensor

TL;DR

UpTime addresses the need for objective biomarkers to quantify ME/CFS and Long COVID severity. It computes the upright-time percentage from a single ankle-worn IMU using Kalman-filtered lower-leg orientation with a threshold θ_c = 39°, and pairs this with a Steps/Day metric derived from local-variance step detection. In a 7-day study with 48 valid participants, UpTime robustly discriminated patients from healthy controls (p-values 0.00004 and 0.01185 for ME/CFS and Long COVID, respectively), outperforming Steps/Day, while Hours of Upright Activity (HUA) provided complementary discrimination and correlated with UpTime (r^2 = 0.68). The findings support UpTime as a scalable, objective outcome measure for clinical trials and treatment monitoring, with HUA and Steps/Day serving as supplementary metrics; however, calibration and etiological uncertainties warrant further validation. Overall, the work demonstrates a practical wearable-based approach to quantify orthostatic intolerance and functional impairment in ME/CFS and Long COVID.

Abstract

Objective: We present a simple parameter, calculated from a single wearable sensor, that can be used to objectively measure disease severity in people with myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) or Long COVID. We call this parameter UpTime. Methods: Prior research has shown that the amount of time a person spends upright, defined as lower legs vertical with feet on the floor, correlates strongly with ME/CFS disease severity. We use a single commercial inertial measurement unit (IMU) attached to the ankle to calculate the percentage of time each day that a person spends upright (i.e., UpTime) and number of Steps/Day. As Long COVID shares symptoms with ME/CFS, we also apply this method to determine Long COVID disease severity. We performed a trial with 55 subjects broken into three cohorts, healthy controls, ME/CFS, and Long COVID. Subjects wore the IMU on their ankle for a period of 7 days. UpTime and Steps/Day were calculated each day and results compared between cohorts. Results: UpTime effectively distinguishes between healthy controls and subjects diagnosed with ME/CFS ($\mathbf{p = 0.00004}$) and between healthy controls and subjects diagnosed with Long COVID ($\mathbf{p = 0.01185}$). Steps/Day did distinguish between controls and subjects with ME/CFS ($\mathbf{p = 0.01}$) but did not distinguish between controls and subjects with Long COVID ($\mathbf{p = 0.3}$). Conclusion: UpTime is an objective measure of ME/CFS and Long COVID severity. UpTime can be used as an objective outcome measure in clinical research and treatment trials. Significance: Objective assessment of ME/CFS and Long COVID disease severity using UpTime could spur development of treatments by enabling the effect of those treatments to be easily measured.

Figures (6)

• Figure 1: System architecture: study participants (SP) goes to research clinic, clinicians set up MMS using the MetaBase app on an iOS or Android device, or MetaProcessor Terminal (CLI), then place MMS with ankle band onto SP. After SP mails MMS back to clinic, clinicians download data from MMS. The CLI compresses the data and sends it to object store, after which investigators can perform analyses on collected data.
• Figure 2: The angle of each lower leg is compared to the critical angle $\theta_c$ to determine uprightness. A critical angle of 39$^{\circ}$ is used for this study. Reproduced from turner-mecfs.
• Figure 3: Labeled IMU and deployment on study subject. (a) IMU device with axis direction markings. (b) IMU placed in flexible band to be worn on ankle. (c) IMU band on subject with IMU on the outside of the ankle.
• Figure 4: Average UpTime and HUA across cohorts. The variable $n$ represents the number of participants who contributed IMU data for a specific day, note that this does not imply a full 24-hour data collection for each participant. For example, in the UpTime graph, on day 6, $n = 48$, while on day 7, $n = 45$. This discrepancy indicates that 3 participants concluded their participation in the study on day 6, and as a result, we do not possess complete 24-hour recordings for these individuals on that day.
• Figure 5: The figure presents grouped t-tests performed at 95% confidence level for UpTime (a), HUA (b) and Steps/Day (c, d) over a specified range of days . In the legend, the error bars represent the 95% confidence intervals for UpTime, HUA, and Steps/Day of each group - ME/CFS, Long COVID, and Control. These intervals are calculated based on the standard error of the mean (SEM).