Quantum Reservoir Computing with Neutral Atoms on a Small, Complex, Medical Dataset

TL;DR

This study explores quantum reservoir computing using neutral atoms on a small medical dataset, demonstrating improved robustness and accuracy with hardware execution compared to noiseless emulation, suggesting a regularising effect.

Contribution

It provides the first comparison of quantum reservoir computing performance between hardware and emulation on a complex medical dataset, highlighting the regularising benefits of hardware execution.

Findings

Hardware execution improves model robustness and accuracy.

Quantum features exhibit structured, time-dependent transformations.

Hardware induces compression and reduces mutual information in features.

Abstract

Biomarker-based prediction of clinical outcomes is challenging due to nonlinear relationships, correlated features, and the limited size of many medical datasets. Classical machine-learning methods can struggle under these conditions, motivating the search for alternatives. In this work, we investigate quantum reservoir computing (QRC), using both noiseless emulation and hardware execution on the neutral-atom Rydberg processor \textit{Aquila}. We evaluate performance with six classical machine-learning models and use SHAP to generate feature subsets. We find that models trained on emulated quantum features achieve mean test accuracies comparable to those trained on classical features, but have higher training accuracies and greater variability over data splits, consistent with overfitting. When comparing hardware execution of QRC to noiseless emulation, the models are more robust over different data splits and often exhibit statistically significant improvements in mean test accuracy. This combination of improved accuracy and increased stability is suggestive of a regularising effect induced by hardware execution. To investigate the origin of this behaviour, we examine the statistical differences between hardware and emulated quantum feature distributions. We find that hardware execution applies a structured, time-dependent transformation characterised by compression toward the mean and a progressive reduction in mutual information relative to emulation.