Posted in | News | Medical Sensor | Biosensors

Comfortable Sleep Monitoring with Smart Pajamas

Researchers from the University of Cambridge have developed machine-washable smart garments designed to monitor sleep disorders such as sleep apnea in a home setting. The system eliminates the need for adhesive patches, bulky equipment, or visits to a sleep clinic. The study was published in Proceedings of the National Academy of Sciences (PNAS).

Illustration and photograph of 'smart pajamas'. Image Credit: Luigi Occhipinti

The research team developed printed fabric sensors capable of detecting subtle skin movements to monitor breathing, even when the pajamas are worn loosely around the neck and chest.

A lightweight AI algorithm was used to train the integrated sensors, enabling the smart pajamas to identify six distinct sleep states with 98.6 % accuracy while filtering out routine movements such as turning and tossing. The energy-efficient sensors require only a few examples of sleep patterns to differentiate between normal and disordered sleep.

According to the researchers, the smart pajamas could assist individuals with sleep disorders in monitoring their sleep patterns and assessing the effects of lifestyle modifications.

Sleep is essential for overall health, yet more than 60 % of adults experience poor sleep quality, leading to a loss of 44–54 working days annually and an estimated 1 % decline in global GDP. Common causes of sleep disturbances include mouth breathing, sleep apnea, and snoring, which are also associated with chronic conditions such as depression, diabetes, and cardiovascular disease.

Poor sleep has huge effects on our physical and mental health, which is why proper sleep monitoring is vital. However, the current gold standard for sleep monitoring, polysomnography, or PSG, is expensive, complicated, and isn’t suitable for long-term use at home.

Luigi Occhipinti, Professor and Study Lead, Cambridge Graphene Centre, University of Cambridge

Home sleep monitoring devices that are simpler than polysomnography (PSG) typically focus on a single condition and are often large or uncomfortable. While smartwatches and other wearable technologies offer greater comfort, they have limited accuracy in detecting sleep disorders and primarily estimate sleep quality rather than directly measuring it.

We need something that is comfortable and easy to use every night but is accurate enough to provide meaningful information about sleep quality.

Luigi Occhipinti, Professor and Study Lead, Cambridge Graphene Centre, University of Cambridge

Occhipinti and colleagues expanded on their previous work on a smart choker designed for individuals with speech impairments to develop the smart pajamas. The team redesigned the graphene-based sensors to improve sensitivity for breath analysis during sleep.

Thanks to the design changes we made, the sensors are able to detect different sleep states, while ignoring regular tossing and turning. The improved sensitivity also means that the smart garment does not need to be worn tightly around the neck, which many people would find uncomfortable. As long as the sensors are in contact with the skin, they provide highly accurate readings,” said Occhinpinti.

The researchers developed a machine learning model called SleepNet, which classifies various sleep states, including obstructive sleep apnea (OSA), central sleep apnea (CSA), snoring, teeth grinding, nasal breathing, and mouth breathing, based on signals recorded by the sensors. SleepNet is a lightweight artificial intelligence network designed to operate on portable devices without requiring a connection to a computer or server, reducing computational complexity.

We pruned the AI model to the point where we could get the lowest computational cost with the highest degree of accuracy. This way, we are able to embed the main data processors in the sensors directly,” said Occhinpinti.

When tested on both healthy individuals and patients with sleep apnea, the smart pajamas demonstrated 98.6 % accuracy in identifying various sleep states. The researchers improved sensor durability by incorporating a specialized starching step, allowing the smart pajamas to withstand machine washing.

The latest version of the smart pajamas includes wireless data transfer capabilities, enabling sleep data to be securely transmitted to a computer or smartphone.

Sleep is so important to health, and reliable sleep monitoring can be key in preventative care. Since this garment can be used at home, rather than in a hospital or clinic, it can alert users to changes in their sleep that they can then discuss with their doctor. Sleep behaviors such as nasal versus mouth breathing are not typically picked up in an NHS sleep analysis, but it can be an indicator of disordered sleep,” said Occhipinti.

The researchers have engaged with patient groups and aim to adapt the sensors for additional medical conditions and domestic applications, such as baby monitoring. Efforts are also underway to enhance sensor longevity for extended use.

The study received partial funding from Haleon, the EU Graphene Flagship, and the Engineering and Physical Sciences Research Council (EPSRC), a division of UK Research and Innovation (UKRI).

Journal Reference:

Tamg, C., et al. (2025) A deep learning–enabled smart garment for accurate and versatile monitoring of sleep conditions in daily life. PNAS. doi.org/10.1073/pnas.2420498122

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.