IEEE International Conference on Smart Information Systems and Technologies (SIST)
Hybrid Quantum-Classical Neural Network Framework for Sleep Efficiency Classification
Mirwais Mohebi, Aiman Bekturganova, Sarsenbek Zhussupbekov, Jandos Amankulov, Assiya Boltaboyeva, Nurdaulet Tasmurzayev
Abstract
Sleep insufficiency now ranks among the leading modifiable risk factors for cardiovascular disease, metabolic disorders, and cognitive decline, affecting hundreds of millions of people worldwide. Yet assessing sleep quality objectively and at scale remains a significant challenge. This paper presents a hybrid quantum-classical neural network that classifies sleep efficiency into good or poor categories using demographic, physiological, and behavioral data from 452 adult participants. The proposed model integrates classical fully connected layers with a six-qubit variational quantum circuit, trained end-to-end via the PennyLane and PyTorch interface. Its performance is evaluated against six established classifiers, namely SVM, Random Forest, XGBoost, MLP, CNN, and LSTM, under a unified stratified five-fold cross-validation protocol. Among all models tested, the proposed network achieves the highest accuracy (0.923) and ROC-AUC (0.962), while using approximately six times fewer trainable parameters than the MLP. A post-hoc SHAP analysis reveals that the model's predictions are driven by physiologically meaningful features, most notably light sleep percentage, deep sleep percentage, and REM sleep percentage. These results suggest that hybrid quantum-classical architectures offer a promising and practical direction for automated sleep health screening.