Quantum neural networks detect sleep apnea with fewer parameters than classical systems

Researchers at Universidade da Coruña and CESGA have demonstrated a quantum recurrent neural network capable of classifying sleep-disordered breathing events with performance comparable to classical systems, despite using a significantly reduced number of parameters. The work, which tested the model on multiple real-world datasets, revealed the quantum approach outperformed classical models on the smallest dataset, while showing good generalization capabilities. These results suggest variational quantum recurrent models offer a promising alternative for time-series classification as quantum computing technologies mature, even with current limitations. The variational classical-quantum architecture successfully classified segments of time-series data, a key step toward automated sleep apnea detection, while minimizing the computational resources typically…