The partnership aims to create a real-time sleep coaching assistant integrating machine learning and CBT-I.

Summary: SleepCogni, a UK-based insomnia device maker, partnered with the University of Sheffield to enhance AI and machine learning for personalized sleep solutions. Professor George Panoutsos was appointed AI science advisor. The partnership aims to develop a personalized sleep coaching assistant leveraging machine learning, cognitive behavioral therapy standards, and device data. This assistant will offer real-time, multilingual support through a bedside device. The collaboration includes Joseph Hawkins, who enhanced SleepCogni’s machine-learning capabilities. Panoutsos’ team is also developing a digital twin to ensure effective biofeedback loops for personalized therapy.

Key Takeaways:

  • SleepCogni collaborates with the University of Sheffield to advance AI technology for personalized sleep health solutions.
  • The partnership aims to create a real-time, multilingual sleep coaching assistant integrating machine learning and cognitive behavioral therapy for insomnia.
  • Panoutsos’ team is developing a digital twin of the SleepCogni device to ensure personalized and effective biofeedback loops for insomnia therapy.

United Kingdom-based SleepCogni, a maker of handheld devices that help people self-manage insomnia, has partnered with the University of Sheffield’s School of Electrical and Electronic Engineering to advance artificial intelligence (AI) and machine learning technology in sleep health.

Professor George Panoutsos, PhD, a leader in computational intelligence and head of the School of Electrical and Electronic Engineering at Sheffield, was selected as AI science advisor. Over the past eight years, SleepCogni has cultivated a strong relationship with Panoutsos, working closely with him and his research group, according to a release from SleepCogni. 

Via the partnership, SleepCogni aims to develop a personalized sleep coaching assistant that leverages machine learning research for sleep optimization and decision-making. This assistant will integrate large language models based on cognitive behavioral therapy for insomnia standards, proprietary device data, and input from a sleep medical advisory team. Delivered through a bedside device, it will offer real-time, 24-hour support and advice in 50 languages, perceiving users’ emotional cues and providing personalized, empathetic audio responses.

This partnership includes contributions from Joseph Hawkins, SleepCogni’s head of operations, who enhanced SleepCogni’s machine-learning capabilities as an undergraduate student.

Advancing Sleep Health Technology

“The physiological, behavioral, and environmental data collected by the SleepCogni device is significant and provides a great opportunity to advance sleep health technology. Not only can SleepCogni generate immediate impact in sleep health, they can also use the same framework to set the future research agenda in digital health for sleep, such as personalized advisory systems, and autonomous sleep health optimization. With SleepCogni we are exploring state of the art machine learning models to apply and evaluate their potential towards full feedback systems that would improve sleep health,” says Panoutsos in a release. 

According to Panoutsos, initial analyses have uncovered potential correlations in the data that could be used to forecast sleep efficiency. “The alignment of SleepCogni’s feedback algorithm with a class of models known as discrete event systems is excellent, as it opens opportunities to use a plethora of system analysis tools to demonstrate system robustness,” he says in a release.

Panoutsos and his team are now developing a new simulation model, a digital twin of the SleepCogni device, that would interact with the feedback algorithm in real time to test millions of algorithm variations, ensuring safe and effective biofeedback loops. This will allow therapy sessions to be personalized based on the severity of insomnia. 

Future Prospects and Innovations

“We are thrilled to welcome professor Panoutsos to our team. His leadership in AI and machine learning will help us develop a clear and strategic path forward, leveraging the best knowledge and expertise available globally,” says Richard Mills, CEO of SleepCogni, in a release. “The University of Sheffield’s leading computational resources, combined with the AI expertise of professor Panoutsos, his colleagues, and students, make this partnership a significant asset for our business, which we expect to grow.”

Mills adds that the company is also excited about the developments in large language models, such as the GPT-4o’s voice capabilities, which have “the potential to be a game changer for SleepCogni and its users.”

Photo 315631434 © Uladzimir Zuyeu |