Dataset Information

Assessment of Fatigue Using Wearable Sensors: A Pilot Study

ABSTRACT:

Background

Fatigue is a broad, multifactorial concept encompassing feelings of reduced physical and mental energy levels. Fatigue strongly impacts patient health-related quality of life across a huge range of conditions, yet, to date, tools available to understand fatigue are severely limited.

Methods

After using a recurrent neural network-based algorithm to impute missing time series data form a multisensor wearable device, we compared supervised and unsupervised machine learning approaches to gain insights on the relationship between self-reported non-pathological fatigue and multimodal sensor data.

Results

A total of 27 healthy subjects and 405 recording days were analyzed. Recorded data included continuous multimodal wearable sensor time series on physical activity, vital signs, and other physiological parameters, and daily questionnaires on fatigue. The best results were obtained when using the causal convolutional neural network model for unsupervised representation learning of multivariate sensor data, and random forest as a classifier trained on subject-reported physical fatigue labels (weighted precision of 0.70 ± 0.03 and recall of 0.73 ± 0.03). When using manually engineered features on sensor data to train our random forest (weighted precision of 0.70 ± 0.05 and recall of 0.72 ± 0.01), both physical activity (energy expenditure, activity counts, and steps) and vital signs (heart rate, heart rate variability, and respiratory rate) were important parameters to measure. Furthermore, vital signs contributed the most as top features for predicting mental fatigue compared to physical ones. These results support the idea that fatigue is a highly multimodal concept. Analysis of clusters from sensor data highlighted a digital phenotype indicating the presence of fatigue (95% of observations) characterized by a high intensity of physical activity. Mental fatigue followed similar trends but was less predictable. Potential future directions could focus on anomaly detection assuming longer individual monitoring periods.

Conclusion

Taken together, these results are the first demonstration that multimodal digital data can be used to inform, quantify, and augment subjectively captured non-pathological fatigue measures.

SUBMITTER: Luo H

PROVIDER: S-EPMC7768149 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The use of wearable sensors allows continuous recordings of physical activity from participants in free-living or at-home clinical studies. The large amount of data collected demands automatic analysis pipelines to extract gait parameters that can be used as clinical endpoints. We introduce a deep learning-based automatic pipeline for wearables that processes tri-axial accelerometry data and extracts gait events-bout segmentation, initial contact (IC), and final contact (FC)-from a single sensor located at either the lower back (near L5), shin or wrist. The gait events detected are posteriorly used for gait parameter estimation, such as step time, length, and symmetry. We report results from a leave-one-subject-out (LOSO) validation on a pilot study dataset of five participants clinically diagnosed with Parkinson's disease (PD) and six healthy controls (HC). Participants wore sensors at three body locations and walked on a pressure-sensing walkway to obtain reference gait data. Mean absolute errors (MAE) for the IC events ranged from 22.82 to 33.09 milliseconds (msecs) for the lower back sensor while for the shin and wrist sensors, MAE ranges were 28.56-64.66 and 40.19-72.50 msecs, respectively. For the FC-event detection, MAE ranges were 29.06-48.42, 40.19-72.70 and 36.06-60.18 msecs for the lumbar, wrist and shin sensors, respectively. Intraclass correlation coefficients, ICC(2,k), between the estimated parameters and the reference data resulted in good-to-excellent agreement (ICC ≥ 0.84) for the lumbar and shin sensors, excluding the double support time (ICC = 0.37 lumbar and 0.38 shin) and swing time (ICC = 0.55 lumbar and 0.59 shin). The wrist sensor also showed good agreements, but the ICCs were lower overall than for the other two sensors. Our proposed analysis pipeline has the potential to extract up to 100 gait-related parameters, and we expect our contribution will further support developments in the fields of wearable sensors, digital health, and remote monitoring in clinical trials.

Project description:Background: Studies aiming to objectively quantify movement disorders during upper limb tasks using wearable sensors have recently increased, but there is a wide variety in described measurement and analyzing methods, hampering standardization of methods in research and clinics. Therefore, the primary objective of this review was to provide an overview of sensor set-up and type, included tasks, sensor features and methods used to quantify movement disorders during upper limb tasks in multiple pathological populations. The secondary objective was to identify the most sensitive sensor features for the detection and quantification of movement disorders on the one hand and to describe the clinical application of the proposed methods on the other hand. Methods: A literature search using Scopus, Web of Science, and PubMed was performed. Articles needed to meet following criteria: 1) participants were adults/children with a neurological disease, 2) (at least) one sensor was placed on the upper limb for evaluation of movement disorders during upper limb tasks, 3) comparisons between: groups with/without movement disorders, sensor features before/after intervention, or sensor features with a clinical scale for assessment of the movement disorder. 4) Outcome measures included sensor features from acceleration/angular velocity signals. Results: A total of 101 articles were included, of which 56 researched Parkinson's Disease. Wrist(s), hand(s) and index finger(s) were the most popular sensor locations. Most frequent tasks were: finger tapping, wrist pro/supination, keeping the arms extended in front of the body and finger-to-nose. Most frequently calculated sensor features were mean, standard deviation, root-mean-square, ranges, skewness, kurtosis/entropy of acceleration and/or angular velocity, in combination with dominant frequencies/power of acceleration signals. Examples of clinical applications were automatization of a clinical scale or discrimination between a patient/control group or different patient groups. Conclusion: Current overview can support clinicians and researchers in selecting the most sensitive pathology-dependent sensor features and methodologies for detection and quantification of upper limb movement disorders and objective evaluations of treatment effects. Insights from Parkinson's Disease studies can accelerate the development of wearable sensors protocols in the remaining pathologies, provided that there is sufficient attention for the standardisation of protocols, tasks, feasibility and data analysis methods.

Project description:BackgroundContinuous vital sign monitoring may identify changes sooner than current standard monitoring.ObjectiveTo investigate if the use of real-time digital alerts sent to healthcare staff can improve the time taken to identify unwell patients and those with sepsis.DesignA prospective cohort study design.SettingWest Middlesex University Hospital, UK.ParticipantsFifty acutely unwell surgical patients admitted to hospital.InterventionPatients wore a lightweight wearable sensor measuring heart rate (HR), respiratory rate (RR) and temperature every 2 min whilst standard intermittent ward monitoring of vital signs was performed by nurses. Digital alerts were sent to healthcare staff from the sensor to a smartphone device. All alerts were reviewed for recruited patients to identify the exact time on the sensor in which deterioration occurred. The time to acknowledgement was then reviewed for each action and an average time to acknowledgement calculated.ResultsThere were 50 patients recruited in the pilot study, of which there were vital sign alerts in 18 patients (36%). The total number of vital sign alerts generated in these 18 patients was 51. Of these 51 alerts, there were 7 alerts for high HR (13.7%), 33 for RR (64.7%) and 11 for temperature (21.6%). Out of the 27 acknowledged alerts, there were 2 alerts for HR, 17 for RR and 8 for temperature. The average time to staff acknowledgement of the notification for all alerts was 154 min (2.6 h). There were some patients which had shown signs of deterioration in the cohort. The frequency of routine observation monitoring was increased in 2 cases, 3 patients were referred to a senior clinician and 2 patients were initiated on the sepsis pathway.ConclusionThis study demonstrates the evaluation of digital alerts to nurses in real time. Although not all alerts were acknowledged, deterioration on the ward observations was detected and actions were taken accordingly. Patients were started on the sepsis pathway and escalation to senior clinicians occurred. Further research is required to review why only some alerts were acknowledged and the effects of digital alerting on patient outcomes.Trial registrationClinicalTrials.gov, NCT04638738.