Hybrid Quantum Neural Network for Multivariate Clinical Time Series Forecasting

2026-03-09

AI Summary

This work addresses the challenge of multistep time series forecasting for clinical multivariate physiological signals by proposing a quantum-classical hybrid architecture. The approach employs a GRU encoder to extract historical temporal features and maps these features to the parameters of a variational quantum circuit (VQC), which models nonlinear interactions among variables through a quantum layer. This enables joint prediction of heart rate, blood oxygen saturation, pulse rate, and respiratory rate. Notably, this study is the first to integrate a VQC into a recurrent neural network, introducing the quantum layer as a learnable nonlinear feature mixer to enhance inductive bias under limited clinical data. Evaluated on the BIDMC dataset, the method achieves prediction accuracy comparable to classical and deep learning baselines while demonstrating superior robustness to noise and missing inputs.

Technology Category

• Machine Learning: Quantum Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Forecasting physiological signals can support proactive monitoring and timely clinical intervention by anticipating critical changes in patient status. In this work, we address multivariate multi-horizon forecasting of physiological time series by jointly predicting heart rate, oxygen saturation, pulse rate, and respiratory rate at forecasting horizons of 15, 30, and 60 seconds. We propose a hybrid quantum-classical architecture that integrates a Variational Quantum Circuit (VQC) within a recurrent neural backbone. A GRU encoder summarizes the historical observation window into a latent representation, which is then projected into quantum angles used to parameterize the VQC. The quantum layer acts as a learnable non-linear feature mixer, modeling cross-variable interactions before the final prediction stage. We evaluate the proposed approach on the BIDMC PPG and Respiration dataset under a Leave-One-Patient-Out protocol. The results show competitive accuracy compared with classical and deep learning baselines, together with greater robustness to noise and missing inputs. These findings suggest that hybrid quantum layers can provide useful inductive biases for physiological time series forecasting in small-cohort clinical settings.

Problem

• multivariate time series forecasting
• physiological signals
• clinical monitoring
• multi-horizon prediction
• patient status anticipation

Innovation

• Hybrid Quantum-Classical Architecture
• Variational Quantum Circuit (VQC)
• Multivariate Time Series Forecasting
• Physiological Signal Modeling
• Quantum Feature Mixer