Quantum Neural Networks for Propensity Score Estimation and Survival Analysis in Observational Biomedical Studies

2025-06-24

AI Summary

Causal inference comparing laparoscopic versus open surgery survival in colorectal cancer patients is confounded by selection bias in observational studies. Method: We propose a noise-aware quantum neural network (QNN) framework for propensity score estimation, incorporating ZFeatureMap encoding, SummedPaulis output operators, gradient-free CMA-ES optimization with variance regularization to enhance robustness on small-sample, high-dimensional clinical data; covariate balance is achieved via integrated genetic matching and matching weights. Results: Under simulated noise, the model achieves AUC = 0.750 and standardized mean differences < 0.087. Post-adjustment survival analysis reveals no statistically significant difference between surgical approaches (p = 0.287–0.851), confirming that unadjusted analyses suffer from confounding bias. This work pioneers the application of noise-resilient QNNs to clinical causal inference, delivering an interpretable, stable, quantum-enhanced solution for small-sample observational studies.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Causality

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

This study investigates the application of quantum neural networks (QNNs) for propensity score estimation to address selection bias in comparing survival outcomes between laparoscopic and open surgical techniques in a cohort of 1177 colorectal carcinoma patients treated at University Hospital Ostrava (2001-2009). Using a dataset with 77 variables, including patient demographics and tumor characteristics, we developed QNN-based propensity score models focusing on four key covariates (Age, Sex, Stage, BMI). The QNN architecture employed a linear ZFeatureMap for data encoding, a SummedPaulis operator for predictions, and the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for robust, gradient-free optimization in noisy quantum environments. Variance regularization was integrated to mitigate quantum measurement noise, with simulations conducted under exact, sampling (1024 shots), and noisy hardware (FakeManhattanV2) conditions. QNNs, particularly with simulated hardware noise, outperformed classical logistic regression and gradient boosted machines in small samples (AUC up to 0.750 for n=100), with noise modeling enhancing predictive stability. Propensity score matching and weighting, optimized via genetic matching and matching weights, achieved covariate balance with standardized mean differences of 0.0849 and 0.0869, respectively. Survival analyses using Kaplan-Meier estimation, Cox proportional hazards, and Aalen additive regression revealed no significant survival differences post-adjustment (p-values 0.287-0.851), indicating confounding bias in unadjusted outcomes. These results highlight QNNs' potential, enhanced by CMA-ES and noise-aware strategies, to improve causal inference in biomedical research, particularly for small-sample, high-dimensional datasets.

Problem

• Using quantum neural networks to reduce selection bias in survival analysis
• Comparing laparoscopic vs open surgery outcomes in colorectal cancer patients
• Improving propensity score estimation for small high-dimensional biomedical datasets

Innovation

• Quantum neural networks for propensity score estimation
• CMA-ES for robust quantum optimization
• Noise-aware strategies enhance predictive stability