Multi-Sensor Sleep Tracking for Nightshift Work

(SENSE Trial)

Overseen By Philip Cheng, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Henry Ford Health System

Disqualifiers: Neurological disorders, Alcohol use disorder, Pregnancy, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 3

100 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to improve sleep tracking for nightshift workers by testing a new method that uses multiple sensors and smart technology. The goal is to more accurately detect daytime sleep, often misreported with current methods. Participants will have their sleep monitored either in a lab using both single-sensor and multi-sensor methods or at home with the multi-sensor approach. The trial seeks individuals who work fixed night shifts at least three times a week and have done so for at least six months. As an unphased trial, it offers participants the opportunity to contribute to innovative research that could enhance sleep health for nightshift workers.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this multi-sensor sleep tracking method is safe for nightshift workers?

Research has shown that using multiple sensors to track sleep is safe for nightshift workers. Studies have found that this method improves the detection of daytime sleep by 43.4%, a significant improvement over using just one sensor. No reports of harmful side effects from using multiple sensors have emerged, indicating it is well-tolerated.

The single-sensor method has been used for a long time and is generally considered safe. Although it may not be as accurate for tracking sleep in nightshift workers, it has not been linked to any major safety issues. Both methods appear safe and have been used without reports of serious risks. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it explores innovative ways to track sleep quality using multiple sensors, which could be a game-changer for people working night shifts. Unlike traditional methods that rely solely on a single sensor, like a wrist-worn actigraphy device, this trial uses a combination of sensors from smart devices, including watches and phones. By harnessing advanced machine learning algorithms, the multi-sensor approach aims to provide a more comprehensive and accurate analysis of sleep patterns. This could lead to better understanding and management of sleep for those who work irregular hours, potentially improving their overall health and well-being.

What evidence suggests that this trial's methods could be effective for improving sleep tracking in nightshift workers?

This trial will compare single-sensor and multi-sensor sleep tracking methods for nightshift workers. Studies have shown that using multiple sensors with machine learning greatly improves the accuracy of sleep tracking for nightshift workers. Traditional methods, which use just one sensor, often miss much of the actual daytime sleep, accurately capturing it only about half the time. The multi-sensor approach, which participants in this trial may experience, combines data from various devices, such as watches and phones, to provide a more accurate picture. This method is particularly beneficial for nightshift workers, whose sleep patterns differ from the norm. Research indicates that this advanced system better detects when someone is truly asleep during the day, leading to more reliable results. ^{1 2 4 6 7}

Are You a Good Fit for This Trial?

This trial is for nightshift workers who struggle with sleep due to their inverted schedules. It's designed to test new methods of tracking sleep more accurately during the day, which traditional actigraphy fails to do.

Inclusion Criteria

Participants must have worked the nightshift for at least six months

Must plan to maintain the nightshift schedule for the duration of the study

I work at least three night shifts a week, starting between 6 PM and 2 AM, for 8-12 hours and will continue to do so.

Exclusion Criteria

Illicit drug use via self-report and urine drug screen

Alcohol use disorder

Termination of nightshift schedule or planned travel during the study period

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

In-Lab Validation

Participants undergo in-lab validation using polysomnography to test the multi-sensor ML approach against legacy algorithms

1 day

1 visit (in-person)

At-Home Implementation

Participants use the multi-sensor approach for sleep tracking at home for four weeks

4 weeks

1 visit (in-person) for setup, daily virtual check-ins

Follow-up

Participants are monitored for data quality and user experience feedback after the at-home implementation

2 weeks

1 visit (virtual)

What Are the Treatments Tested in This Trial?

Interventions

• Multi-Sensor Sleep Tracking
• Single-Sensor Tracking

Trial Overview

The study is comparing three ways of monitoring sleep: using multiple sensors at home, a single sensor in a lab setting, and multiple sensors in a lab. The goal is to improve accuracy with machine learning algorithms.

How Is the Trial Designed?

Group I: Single vs Multi-Sensor Sleep Tracking In-Lab Experimental Treatment 2 Interventions

In Part 1 of the study, all participants' data will undergo two separate methods for analyzing sleep. The legacy actigraphy algorithm methods will use only raw accelerometer data from a single sensor collected and processed using legacy actigraphy algorithms. The legacy algorithm is comprised first of reducing accelerometer data into activity counts per epoch, which will then be categorized into sleep or wake in accordance with the Cole-Kripke algorithm. The multi-sensor machine learning (ML) method will use raw accelerometer data in addition to data from additional sensors from the watch, phone, and other smart sensors in the sleeping environment. These data will be processed using a machine learning algorithm.

Group II: Multi-Sensor Sleep Tracking At-Home Experimental Treatment 1 Intervention

This condition includes 4 weeks of at-home sleep tracking using the multi-sensor approach. Daily sleep diaries will also be collected to enable data quality check. Once collected, all data will be processed with the same machine learning algorithm used in the in-lab experimental condition.

Who Is Running the Clinical Trial?

Henry Ford Health System

Lead Sponsor

Trials

334

Recruited

2,197,000+

Michigan State University

Collaborator

Trials

202

Recruited

687,000+

Published Research Related to This Trial

Shift workers who align their sleep-wake patterns with their circadian rhythm experience less daytime sleepiness, even if their total sleep time is shorter, indicating the importance of circadian alignment over just sleep duration.

A new computational package can help individuals optimize their sleep-wake patterns in real-time, potentially reducing daytime sleepiness by adjusting sleep durations based on varying bedtimes, which could be integrated with wearable technology.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Personalized sleep-wake patterns aligned with circadian rhythm relieve daytime sleepiness. Hong, J., Choi, SJ., Park, SH., et al.[2021]

Commercially available sleep tracking technology, such as wearables and smartphone apps, is becoming increasingly popular for monitoring sleep patterns, which are essential for health and well-being.

The systematic review included 842 studies, focusing on those that provided sleep data for at least 4 nights, highlighting the growing interest and research into the effectiveness and limitations of these sleep trackers.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Sleep tracking: A systematic review of the research using commercially available technology. Robbins, R., Seixas, A., Masters, LW., et al.[2022]

Citations

1.

trialx.com

trialx.com/clinical-trials/listings/315717/the-use-of-multiple-sensors-to-track-sleep-in-nightshift-workers/

The Use of Multiple Sensors to Track Sleep in Nightshift ...

The first aim of this study is to establish an open-source machine learning algorithm for sleep tracking that outperforms legacy actigraphy ...

2.

pmc.ncbi.nlm.nih.gov

pmc.ncbi.nlm.nih.gov/articles/PMC12137229/

Detailed assessment of night shift work aspects and ...

Night shift work has been associated with adverse health outcomes, but inconsistencies in epidemiological findings reveal gaps in understanding ...

3.

nature.com

nature.com/articles/s41598-021-87029-w

A multimodal analysis of physical activity, sleep, and work ...

This paper uses commercial wearable sensors to explore correlates and differences in the level of physical activity, sleep, and circadian misalignment ...

4.

academic.oup.com

academic.oup.com/joh/article/67/1/uiaf053/8258640

Sleep and well-being before and after a shift schedule change ...

This study aimed to assess the impact of transitioning from an 8-hour to a 12-hour shift schedule on sleep outcomes using wearable sensors among ICU nurses ...

5.

arxiv.org

arxiv.org/html/2507.03520v1

TILES-2018 Sleep Benchmark Dataset: A Longitudinal ...

Recent advances in wearable sensing technology have enabled continuous, noninvasive, and cost-effective monitoring of sleep patterns in real- ...

6.

govtribe.com

govtribe.com/award/federal-grant-award/project-grant-r01hl177767

Project Grant R01HL177767

THE OBJECTIVE OF THIS PROPOSAL IS TO VALIDATE A MULTI-SENSOR ML APPROACH TO TRACK SLEEP IN NIGHTSHIFT WORKERS, AND TO IDENTIFY FACILITATORS AND ...

7.

academic.oup.com

academic.oup.com/sleep/article/48/Supplement_1/A192/8134889

Using a Multi-Device Machine Learning Approach Improves ...

Preliminary results show our multi-device ML approach increases detection of daytime sleep by 43.4% in night shift workers. In nighttime ...