Sleep Biomarkers: New Approaches to Sleep Monitoring at Home

Objectives: A comprehensive review of modern wearable electroencephalography (EEG) systems for home sleep monitoring was conducted, integrating technological and behavioral aspects. Based on an analysis of form factors, materials, and classification algorithms—long short-term memory (LSTM) networks, Random Forest, and convolutional neural networks (CNNs)—the main advances in rigid and flexible headbands, tattoo patches, and in-ear devices were identified. Concurrently, the evolution of consumer perceptions of wellness services was examined, shifting from aesthetics to data-driven resilience. The concept of “emotional ergonomics” was proposed to personalize interfaces, ensure algorithmic transparency, and enhance user emotional comfort. Methods: The methodology for conducting a systematic review and triangulating literature and user data was substantiated. Scientific gaps in the standardization of wearable EEG device validation were highlighted, and prospects for integrating multisensory platforms and AI-driven analytics to improve monitoring accuracy and user acceptance were outlined. Findings:The findings are expected to interest researchers in somnology and translational medicine who seek to integrate molecular and physiological indicators with artificial intelligence algorithms to enhance the accuracy of sleep disorder diagnosis and prognosis. Moreover, these insights will be valuable to developers of wearable biometric sensors and digital health platforms, as well as to regulatory experts shaping safety and efficacy standards for remote monitoring technologies. The scientific novelty consists in the introduction, for the first time, of a combined concept of “emotional ergonomics” for sleep devices, integrating the hardware and software characteristics of wearable EEG sensors with contemporary consumers’ demands for transparency in validation, personalization, and a comfortable user experience in the post-pandemic period.