March 26, 2026npj Digital Medicine1 citationsOpen Access
Digital physiological biomarkers predict within-person symptom changes in complex chronic illness
Key Result
Adding morning biometric data to prior-day symptom reports significantly improved the prediction of evening symptom exacerbations, increasing model AUC from 0.73-0.83 to 0.82-0.85.
Key Points
- This research aims to determine how digital biomarkers predict daily symptom fluctuations in individuals with complex chronic illness.
- Conducted a 60-s morning PPG assessment alongside evening symptom reports from a large sample.
- Analyzed data from 4244 participants, averaging 125 biometric observations each.
- Examined the relationship between biometric fluctuations (HR, HRV) and reported symptoms like fatigue and brain fog.
- Found that morning increases in HR and decreases in HRV correlate with worsening evening symptom reports.
- Models incorporating morning biometrics showed significantly improved predictive performance (AUC up to 0.85) compared to those without.
- Morning biometrics significantly enhanced the model fit and variance explained in predicting symptom changes.
Study Design
Type
Observational (n=4,244)
Structured PICO
Does daily morning biometric monitoring improve the prediction of evening symptom exacerbations in people with complex chronic illnesses?
P
Population
People aged ≥ 18 years with self-identified complex chronic illnesses such as Long COVID (LC), ME/CFS, or other causes of energy limitation using the Visible application
I
Intervention
Daily morning biometric monitoring (heart rate, heart rate variability, and respiratory rate) via 60-second photoplethysmography (PPG) combined with prior-day symptom reports
C
Comparator
Prior-day symptom reports alone
O
Outcome
Daily changes in evening symptom reports of crash, fatigue, and brain fogpatient reported
Daily morning biometric monitoring of heart rate and heart rate variability using mobile health tools provides incremental, statistically significant improvements in predicting real-time symptom exacerbations in individuals with complex chronic illnesses.
Main Result
Effect estimate: AUC 0.82-0.85
p-value: p=<0.001
Limitations
- Retrospective study design with limited demographic information
- Lack of standardized diagnostic criteria for ME/CFS
- Potential inconsistencies from using different measurement devices (smartphone cameras vs armbands)
- Uncontrolled real-world nature of resting measurements
Abstract
Altered heart‑rate variability (HRV) and resting heart rate (HR) are common in many complex chronic conditions. Mobile and wearable technologies now provide real-time, valid measurements of HRV and HR, advancing symptom monitoring and management. The current study integrates a 60-s morning PPG assessment with evening symptom severity reports, yielding a high-density mobile health dataset (n = 4244) with an average of 125 biometric observations per participant. We examined whether within-person fluctuations in HR, HRV, and respiratory rate predicted daily changes in crash, fatigue, and brain fog symptoms and secondarily evaluated model predictive performance. Model fit and variance explained were highest in models that included morning biometrics in addition to prior-day symptom reports and covariates. Within-person increases in HR and decreases in HRV in the morning were associated with worsening symptom reports in the evening. Walk-forward cross-validation showed a statistically significant improvement in model performance when morning biometrics were added to prior-day symptom reports (AUC = 0.82–0.85 vs. 0.73–0.83). These findings represent the prospective utility of mobile health tools for precision monitoring and prediction of real-time symptom exacerbations in complex chronic illness.