Exploration of LLMs, EEG, and behavioral data to measure and support attention and sleep

TL;DR

This paper investigates how large language models can analyze EEG and behavioral data to assess attention and sleep, offering personalized suggestions but highlighting the need for more data for certain detections.

Contribution

It demonstrates the potential of LLMs to estimate sleep quality and generate personalized interventions from multimodal data, advancing sleep and attention monitoring methods.

Findings

LLMs can estimate sleep quality from behavioral features.

Personalized sleep improvement suggestions are feasible.

Detection of attention and sleep stages needs more data.

Abstract

We explore the application of large language models (LLMs), pre-trained models with massive textual data for detecting and improving these altered states. We investigate the use of LLMs to estimate attention states, sleep stages, and sleep quality and generate sleep improvement suggestions and adaptive guided imagery scripts based on electroencephalogram (EEG) and physical activity data (e.g. waveforms, power spectrogram images, numerical features). Our results show that LLMs can estimate sleep quality based on human textual behavioral features and provide personalized sleep improvement suggestions and guided imagery scripts; however detecting attention, sleep stages, and sleep quality based on EEG and activity data requires further training data and domain-specific knowledge.