A study involving a key member of the IDEA-FAST [1] consortium presents new benchmarks to support the continued development of systems that enable healthcare practitioners to better manage patients with sleep disorders. The findings, which highlight the value of digital measures correlated from multimodal sensor data, add impetus to IDEA-FAST’s aim to generate digital measures of fatigue and sleep disturbances for clinical validation.

The research [2], which was partially funded by the IDEA-FAST project, analysed wearable movement and cardiac sensor data across different sleep stage classifications. Effective algorithms were identified by comparing the performance of measures from a) a single sensor type, and b) a combined set of sensors, and synchronising these with gold-standard polysomnography sleep measures. The algorithms can be applied to more in-depth sleep studies involving larger populations and diseases, with subjects participating from the comfort of their own homes rather than in a clinical environment.

For the IDEA-FAST project, which uses a variety of digital health technologies to measure fatigue and sleep disturbances, the data from multiple sensors may provide an even greater insight to the severity of fatigue and sleep disturbance symptoms experienced by people with chronic conditions [3].

Automated sleep stage classification algorithms using multimodal sensor data will add great value to IDEA-FAST’s analysis of the features of fatigue and sleep disturbances.

Dr. Yu Guan, co-applicant of the IDEA-FAST project and senior author of the latest research publication

As new technologies develop, more accurate data can be captured as patients go about their normal daily routine. This can be analysed and evaluated to develop more specific clinical measures.

We are in the early stages of the first part of our study, where we will identify the digital measures of fatigue and sleep disturbances that best correlate with patient-reported and clinical outcome measures. These will then be tested in a larger clinical validation study. The results will increase clinical trial efficiency and help advance the development of new treatments for the chronic diseases we are focusing on in IDEA-FAST.

Professor Wan-Fai Ng, IDEA-FAST project co-ordinator

References:

[1] Identifying Digital Endpoints to Assess FAtigue, Sleep and acTivities in daily living in Neurodegenerative disorders and Immune-mediated inflammatory diseases. https://idea-fast.eu

[2] Bing Zhai, Ignacio Perez-Pozuelo, Emma A.D. Clifton, Joao Palotti, and Yu Guan. 2020. Making Sense of Sleep: Multimodal Sleep Stage Classification in a Large, Diverse Population Using Movement and Cardiac Sensing. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 4, 2, Article 67 (June 2020), 33 pages. https://doi.org/10.1145/3397325

[3] Parkinson’s disease, Huntington’s disease, Rheumatoid arthritis, systemic lupus erythematosus, primary Sjögren’s syndrome, and inflammatory bowel disease