Deep learning with wearable based heart rate variability for prediction of mental and general health

Coutts, Louise V.; Plans, David; Brown, Alan W.; Collomosse, John

doi:10.1016/j.jbi.2020.103610

Cited by 71 publications

(51 citation statements)

References 13 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, driver profile, age, gender, and other factors included in input data might improve the classification accuracy achieved from machine-learning models. It has been reported that setting up the parameters of preprocessing algorithms based on the driver profile, age, and gender could result in higher classification accuracy ( 18 ). Therefore, personalized algorithms and individually normalized features should be explored to improve model performance.…”

Section: Discussionmentioning

confidence: 99%

Data-Driven Detection and Assessment for Urban Railway Transit Driver Fatigue in Real Work Conditions

Jiao

Chen

Sun

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Fatigue among urban railway transit (URT) drivers affects their performance and is a contributing factor in many railway accidents and incidents. This paper attempts to develop a robust fatigue detection system for URT drivers. An experimental study was conducted in actual work conditions, involving 198 professional URT drivers, to provide authentic and representative data. Fatigue scores based on the Karolinska Sleepiness Scale were used as the ground truth, and heart rate variability (HRV) data were collected using wearable photoplethysmography (PPG) sensors under actual working conditions. An extensive statistical analysis found that continuous working hours were a major factor in driver fatigue. HRV features were able to differentiate various fatigue levels. Four classifiers (k-nearest neighbors, Naive Bayes, support vector machines, and random forests) were trained to detect fatigue in real time for binary and three-class fatigue classifications, respectively. For the binary classification, the best performance was achieved by the random forest classifier using the corrected feature set as input with an accuracy of 92.5%. However, the accuracy dropped by 8 to 27 percentage points for the three-class classification. Moreover, the research found that the corrected feature set circumventing inter-individual variability in HRV could improve the performance of fatigue classifiers. The findings from this research could contribute to developing a robust and real-time URT driver fatigue detection system and improve current URT operational safety regulations.

show abstract

Section: Discussionmentioning

confidence: 99%

Data-Driven Detection and Assessment for Urban Railway Transit Driver Fatigue in Real Work Conditions

Jiao

Chen

Sun

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Coutts et al acquire HRV with a wearable device worn on the wrist and estimate mental health states such as depressed, positive, and anxious moods, which are binarized into two groups, namely, high and low. (17) The results of deep learning-based estimation showed that they could classify with high accuracy. However, this experiment was conducted on students only and cannot estimate the stress of physicians assumed in this study.…”

Section: Related Workmentioning

confidence: 99%

A Method for Estimating Physician Stress Using Wearable Sensor Devices

Imura¹,

Gotoh²,

Sakai³

et al. 2022

Sensors and Materials

View full text Add to dashboard Cite

The idea of Society 5.0 initiative has been proposed to solve various social problems by connecting virtual cyberspace and real physical space through information technology. When applying the idea to improve the work-life balance of physicians in the medical field, we must consider the increased stress owing to their long continuous working hours. Estimating the stress of physicians in their daily lives by the questionnaires is insufficient, because of the difficulty of accurate their activity recalling. By using bio-metric information such as heart rate, physical activity, and sleeping information, it was expected that the daily stress state of physicians with high accuracy. In this paper, we propose a method for estimating physician stress by analyzing bio-metric information acquired by wearing a wearable sensor device. The proposed method estimates the state of stress during daily activities by acquiring data on heart rate variability (HRV) during wakefulness as well as sleep depth during rapid eye movement (REM) and non-REM sleep. Up to seven physicians wore the wearable sensor device for the maximum of eight weeks and the sleep depth and low-/high-frequency (LF/HF) components of HRV were obtained. Our observation showed that physicians' root mean square of successive differences (rMSSDs) were constantly high in their healthy state. Therefore, the decreasing of this index can be used as an indicator of fatigue and stress. In addition, by combining LF/HF components to the rMSSDs, we may estimate the stress state of physicians and find personal stressors.

show abstract

“…The experimental results showed that for mental health measures and classification, the proposed models achieved accuracies of 73% and 83% with two- and five-minute HRV data streams, respectively. 39 Another study by Bashivan et al employed DL and other machine learning methods to recognize the mental state via a wearable electroencephalogram. In that work, electroencephalogram data were used, supported by machine learning, to differentiate between ‘emotional’ versus ‘logical’.…”

Section: Introductionmentioning

confidence: 99%

Decision support system for the differentiation of schizophrenia and mood disorders using multiple deep learning models on wearable devices data

Nguyen

Chan

et al. 2022

Health Informatics J

View full text Add to dashboard Cite

In the modern world, with so much inherent stress, mental health disorders (MHDs) are becoming more common in every country around the globe, causing a significant burden on society and patients’ families. MHDs come in many forms with various severities of symptoms and differing periods of suffering, and as a result it is difficult to differentiate between them and simple to confuse them with each other. Therefore, we propose a support system that employs deep learning (DL) with wearable device data to provide physicians with an objective reference resource by which to make differential diagnoses and plan treatment. We conducted experiments on open datasets containing activity motion signal data from wearable devices to identify schizophrenia and mood disorders (bipolar and unipolar), the datasets being named Psykose and Depresjon. The results showed that, in both workflow approaches, the proposed framework performed well in comparison with the traditional machine learning (ML) and DL methods. We concluded that applying DL models using activity motion signal data from wearable devices represents a prospective objective support system for MHD differentiation with a good performance.

show abstract

Deep learning with wearable based heart rate variability for prediction of mental and general health

Cited by 71 publications

References 13 publications

Data-Driven Detection and Assessment for Urban Railway Transit Driver Fatigue in Real Work Conditions

Data-Driven Detection and Assessment for Urban Railway Transit Driver Fatigue in Real Work Conditions

A Method for Estimating Physician Stress Using Wearable Sensor Devices

Decision support system for the differentiation of schizophrenia and mood disorders using multiple deep learning models on wearable devices data

Contact Info

Product

Resources

About