Examining Response to Negative Life Events Through Fitness Tracker Data

Louis Faust, Keith Feldman, Suwen Lin, Stephen M. Mattingly, Sidney D'Mello, Nitesh V. ChawlaFrontiers Digit. Health 2021 · DOI · OpenReview

Introduction

Traditional psychological research into negative life events (NLEs)—such as the loss of a loved one or unemployment—has largely depended on subjective self-reporting. While insightful, these methods often suffer from recall bias and fail to capture the immediate, continuous physiological impact of stress. Given the known bidirectional relationship between mental and physical health, there is a critical need for objective, real-time data. This study addresses this gap by utilizing "passive sensing" from wearable devices to establish a baseline Physiological and Behavioral state (PB-state) and quantify deviations following significant life stressors.

Methods

The study leveraged data from the Tesserae project, which monitored 757 professionals across the United States for one year. Participants wore Garmin Vivosmart-3 devices to track resting heart rate (RHR), moderate-to-vigorous physical activity (MVPA), and sleep duration.

Participant Selection and Cohort

Rigorous filtering was applied to ensure data quality and event significance. Participants were required to have experienced a "significant" negative life event with high confidence in the date and maintained at least 80% wearable wear-time. This resulted in a final study cohort of 45 participants.

Figure 1: Consort diagram illustrating the participant selection process and exclusion criteria.

Computational Analysis

The researchers employed a multi-step analytical framework:

  1. Anomaly Detection: A One-Class Support Vector Machine (OCSVM) was trained on a 60-day "pre-event" window for each individual to define their unique baseline. A 15-day "post-event" window was then evaluated for deviance.
  2. Bayesian Modeling: Bayesian gamma-hurdle regression models were used to estimate the probability that specific coping mechanisms, measured via the "Brief COPE" inventory, mitigated physiological deviations.
  3. Clustering: K-shape clustering categorized participants based on their response trajectories, distinguishing between those who remained stable and those who experienced significant disruption.

Results

The analysis revealed that physical health metrics serve as sensitive objective markers of psychological resilience. Participants categorized in the "impacted" cluster (Cluster 1) exhibited a significant average increase in resting heart rate (+0.66 bpm) and a decrease in daily physical activity (-4.10 minutes) following the event. Using a bootstrapped "no-event" control group, the researchers confirmed that these deviations were significantly stronger than random daily fluctuations (p < 0.014).

Impact of Coping Strategies

A primary finding was the efficacy of proactive coping mechanisms in stabilizing physiological states. Strategies such as "acceptance," "planning," and "active coping" were strongly associated with lower physiological deviation.

Figure 6: Odds ratios for various coping strategies, showing their association with physiological stability following a negative life event.

As shown in Figure 6, "Acceptance" (OR 0.56) and "Planning" (OR 0.59) were among the most effective strategies for mitigating the physical toll of a crisis. "Active coping"—taking direct steps to address the situation—also showed a significant stabilizing effect (OR 0.75). These results suggest that the cognitive process of problem-solving can directly influence the autonomic nervous system, providing a physical buffer against stress.

Discussion

This research demonstrates that wearable fitness trackers can provide a continuous, objective window into an individual's response to trauma. The identification of distinct response trajectories suggests that such technology could eventually function as an early-warning system for mental health decline, allowing for timely intervention.

However, the study is limited by its small sample size (n=45), which may affect the generalizability of the findings. Furthermore, the use of consumer-grade wearables introduces potential measurement inaccuracies compared to clinical equipment. Future research should aim to expand the cohort size and extend the observation window to capture long-term recovery or delayed physiological reactions. Despite these limitations, the study provides a compelling proof-of-concept for using passive sensing to understand the physiological underpinnings of human resilience.

Summary updated

Abstract

p>Negative life events, such as the death of a loved one, are an unavoidable part of life. These events can be overwhelmingly stressful and may lead to the development of mental health disorders. To mitigate these adverse developments, prior literature has utilized measures of psychological responses to negative life events to better understand their effects on mental health. However, psychological changes represent only one aspect of an individual's potential response. We posit measuring additional dimensions of health, such as physical health, may also be beneficial, as physical health itself may be affected by negative life events and measuring its response could provide context to changes in mental health. Therefore, the primary aim of this work was to quantify how an individual's physical health changes in response to negative life events by testing for deviations in their physiological and behavioral state (PB-state). After capturing post-event, PB-state responses, our second aim sought to contextualize changes within known factors of psychological response to negative life events, namely coping strategies. To do so, we utilized a cohort of professionals across the United States monitored for 1 year and who experienced a negative life event while under observation. Garmin Vivosmart-3 devices provided a multidimensional representation of one's PB-state by collecting measures of resting heart rate, physical activity, and sleep. To test for deviations in PB-state following negative life events, One-Class Support Vector Machines were trained on a window of time prior to the event, which established a PB-state baseline. The model then evaluated participant's PB-state on the day of the life event and each day that followed, assigning each day a level of deviance relative to the participant's baseline. Resulting response curves were then examined in association with the use of various coping strategies using Bayesian gamma-hurdle regression models. The results from our objectives suggest that physical determinants of health also deviate in response to negative life events and that these deviations can be mitigated through different coping strategies. Taken together, these observations stress the need to examine physical determinants of health alongside psychological determinants when investigating the effects of negative life events.</p>
BibTeX
@article{faust2021examining,
  author = {Louis Faust and Keith Feldman and Suwen Lin and Stephen M. Mattingly and Sidney D'Mello and Nitesh V. Chawla},
  title = {{Examining Response to Negative Life Events Through Fitness Tracker Data}},
  journal = {Frontiers Digit. Health},
  year = {2021},
  doi = {10.3389/fdgth.2021.659088},
}
Figure