TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers

@article{Mundnich2020TILES2018AL,
  title={TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers},
  author={Karel Mundnich and Brandon M. Booth and Michelle L'Hommedieu and Tiantian Feng and Benjamin Girault and Justin L'Hommedieu and M. Wildman and Sophia Skaaden and Amrutha Nadarajan and Jennifer L Villatte and T. Falk and Kristina Lerman and Emilio Ferrara and Shrikanth S. Narayanan},
  journal={Scientific Data},
  year={2020},
  volume={7}
}
We present a novel longitudinal multimodal corpus of physiological and behavioral data collected from direct clinical providers in a hospital workplace. We designed the study to investigate the use of off-the-shelf wearable and environmental sensors to understand individual-specific constructs such as job performance, interpersonal interaction, and well-being of hospital workers over time in their natural day-to-day job settings. We collected behavioral and physiological data from n  = 212… Expand
Group-specific models of healthcare workers’ well-being using iterative participant clustering
Healthcare workers often experience stress and burnout due to the demanding job responsibilities and long work hours. Ambulatory monitoring devices, such as wearable and environmental sensors,Expand
User-Based Collaborative Filtering Mobile Health System
TLDR
A user-based collaborative filtering mobile health system that predicts users based on the health information from their cohort using mobile devices, wearables, and sensors that demonstrates strong interpretability, predictability, and usability. Expand
Dynamical systems modeling of day-to-day signal-based patterns of emotional self-regulation and stress spillover in highly-demanding health professions
TLDR
Results from this study demonstrate the importance of quantifying oscillatory behaviors from longitudinal ambulatory signals and can potentially deepen the understanding of emotion self-regulation and stress spillover using signal-driven measurements, which complement self-reports and provide estimates of the psychological constructs of interest in a fine-grained time resolution. Expand
Context-Aware Speech Stress Detection in Hospital Workers Using Bi-LSTM Classifiers
TLDR
A context-aware speech-based system for stress detection based on a bidirectional LSTM deep neural network that shows the importance of hospital location and circadian rhythm based contextual cues for stress prediction and shows improvements as high as 14% in F1 scores once context is incorporated. Expand
A multimodal analysis of physical activity, sleep, and work shift in nurses with wearable sensor data
TLDR
The results using data collected from 113 nurses in a large hospital setting, over a period of 10 weeks, indicate that night shift nurses are more sedentary, and report lower levels of life satisfaction than day-shift nurses. Expand
Designing an Interactive Visualization System for Monitoring Participant Compliance in a Large-Scale, Longitudinal Study
TLDR
The iterative design of an interactive visualization system developed for monitoring compliance is described and refined based on changing requirements in an ongoing study and it is found that the visualization system both facilitates the exploratory tasks of monitoring participant compliance and supports asynchronous collaboration among non-co-located researchers. Expand
Having a Bad Day? Detecting the Impact of Atypical Life Events Using Wearable Sensors
TLDR
The impact of positive and negative life events on a number of psychological constructs are explored through a multi-month longitudinal study of hospital and aerospace workers to suggest that automated interventions based on physiological sensing may be feasible to help workers regulate the negative effects of life events. Expand
Pattern Discovery in Time Series with Byte Pair Encoding
TLDR
This work proposes an unsupervised method for learning representations of time series based on common patterns identified within them, which applies to both univariate and multivariate time series and beats state-of-the-art approaches on a real world dataset collected from wearable sensors. Expand
Temporal Dynamics of Workplace Acoustic Scenes: Egocentric Analysis and Prediction
TLDR
This paper proposes a two-stage framework where a recurrent neural network is trained on top of the latent acoustic representations learned by a segment-level neural network and shows the efficacy of the proposed system in predicting sequence of acoustic scenes, highlighting the existence of underlying temporal patterns in the acoustic scenes experienced in workplace. Expand
Investigating Group-Specific Models of Hospital Workers' Well-Being: Implications for Algorithmic Bias
Hospital workers often experience burnout due to the demanding job responsibilities and long work hours. Data yielding from ambulatory monitoring combined with machine learning algorithms can affordExpand
...
1
2
...

References

SHOWING 1-10 OF 78 REFERENCES
A Comparative Study of Stress and Anxiety Estimation in Ecological Settings Using a Smart-shirt and a Smart-bracelet
TLDR
This paper compares the accuracy of two wearable devices, namely a smart-shirt measuring electrocardiograms and asmart-bracelet measuring photoplethysmograms, and several HRV features are extracted and tested as correlates of stress and anxiety. Expand
Breathing Rate Complexity Features for “In-the-Wild” Stress and Anxiety Measurement
TLDR
New non-linear complexity measures computed from four different respiration activity time series are proposed and shown to be complementary to conventional measures of breathing rate and depth and show their discriminatory power for anxiety and stress monitoring in the workplace. Expand
Multimodal Human and Environmental Sensing for Longitudinal Behavioral Studies in Naturalistic Settings: Framework for Sensor Selection, Deployment, and Management
TLDR
An organized snapshot of consumer-grade human sensing technologies that can be used for human behavior research in natural settings is illustrated and a general data collection framework suitable for use with modern consumer sensors is explained, enabling researchers to address many of the described challenges. Expand
Speaker Agnostic Foreground Speech Detection from Audio Recordings in Workplace Settings from Wearable Recorders
TLDR
A convolutional neural network model is proposed to predict foreground regions using a limited set of audio features and it is shown that these models generalize across the proxy corpora collected in house to approximately match the deployment environment. Expand
Stress and Anxiety Measurement "In-the-Wild" Using Quality-aware Multi-scale HRV Features
TLDR
This paper explores the use of motif-based multi-scale HRV features to predict anxiety and stress in-the-wild and proposes a quality-aware feature aggregation method that shows improved stress/anxiety measurement over conventional time- and frequency-domain HRV measures. Expand
Discovering Latent Psychological Structures from Self-Report Assessments of Hospital Workers
TLDR
A computational framework that combines clustering and non-negative matrix factorization was used to extract the latent interplay between psychological constructs along dimensions of health, affect, personality, cognitive ability, and job performance. Expand
Discovering Optimal Variable-length Time Series Motifs in Large-scale Wearable Recordings of Human Bio-behavioral Signals
TLDR
A time series processing pipeline to summarize an optimal set of variable-length motifs in a real-world wearable recording data-set collected in a hospital workplace setting is introduced and the use of the Savitzky-Golay filter for noise removal without significant data distortion is proposed. Expand
Toward Robust Interpretable Human Movement Pattern Analysis in a Workplace Setting
TLDR
This work proposes a technique for clustering and discovering patterns in human movement data by extracting motifs from the time series of durations where participants linger at different locations, and shows this technique intuitively captures local temporal relationships between hospital rooms and also clusters them in a fashion consistent with the room type labels. Expand
TILES audio recorder: an unobtrusive wearable solution to track audio activity
TLDR
The TILES Audio Recorder (TAR) is proposed - an unobtrusive and scalable solution to track audio activity using an affordable miniature mobile device with an open-source app, and shows that performing feature extraction only during speech segments greatly increases battery life. Expand
The RAND 36-Item Health Survey 1.0.
Recently, Ware and Sherbourne published a new short-form health survey, the MOS 36-Item Short-Form Health Survey (SF-36), consisting of 36 items included in long-form measures developed for theExpand
...
1
2
3
4
5
...