Sleep Brain and Cardiac Activity Predict Cognitive Flexibility and Conceptual Reasoning Using Deep Learning

TL;DR

This study introduces CogPSGFormer, a deep learning model that predicts cognitive flexibility and reasoning abilities from sleep-related physiological signals, demonstrating high accuracy and advancing understanding of sleep-cognition links.

Contribution

We developed a novel multi-scale convolutional-transformer model that integrates multi-modal sleep data to predict cognitive performance, a first in leveraging sleep microstructure for this purpose.

Findings

Achieved 80.3% accuracy in classifying cognitive performance groups.

Demonstrated the effectiveness of multi-modal sleep data in cognitive prediction.

Provided a reproducible framework with publicly available code.

Abstract

Despite extensive research on the relationship between sleep and cognition, the connection between sleep microstructure and human performance across specific cognitive domains remains underexplored. This study investigates whether deep learning models can predict executive functions, particularly cognitive adaptability and conceptual reasoning from physiological processes during a night's sleep. To address this, we introduce CogPSGFormer, a multi-scale convolutional-transformer model designed to process multi-modal polysomnographic data. This model integrates one-channel ECG and EEG signals along with extracted features, including EEG power bands and heart rate variability parameters, to capture complementary information across modalities. A thorough evaluation of the CogPSGFormer architecture was conducted to optimize the processing of extended sleep signals and identify the most effective configuration. The proposed framework was evaluated on 817 individuals from the STAGES dataset using cross-validation. The model achieved 80.3\% accuracy in classifying individuals into low vs. high cognitive performance groups on unseen data based on Penn Conditional Exclusion Test (PCET) scores. These findings highlight the effectiveness of our multi-scale feature extraction and multi-modal learning approach in leveraging sleep-derived signals for cognitive performance prediction. To facilitate reproducibility, our code is publicly accessible (https://github.com/boshrakh95/CogPSGFormer.git).