Quantum-Inspired Ensemble Learning for Robust Healthcare Risk Prediction
Abstract
Predicting risks for clinical decision support in healthcare is crucial as it helps to detect diseases early and effectively manage patients. While single machine learning models have managed to demonstrate good prediction accuracy, there remain some limitations that hamper their performance due to factors such as the presence of class imbalance, noisy clinical data and differences in patients’ characteristics. Therefore, in this study, a quantum-inspired ensemble learning algorithm has been developed in order to overcome these problems by implementing an adaptive decision level aggregation approach to increase prediction robustness. This quantum-inspired ensemble learning model works entirely within the classical machine learning setup and applies a confidence-based probability weighting strategy based on the quantum concept to combine classifier predictions. The framework is tested on the publicly available Pima Indians Diabetes Dataset with stratified 10-fold cross-validation. Performance metrics used to assess the proposed framework include Accuracy, Precision, Recall, F1 Score, ROC-AUC, Matthews Correlation Coefficient, and Log Loss. Experimental results show that the method significantly outperforms the traditional ensemble methods such as majority vote, average probability, static weighted vote, stacking in terms of classification accuracy and balancing of prediction performance. The proposed framework offers a viable and scalable solution for healthcare risk…
Read the paper
Related studies
- In silico toxicology protocols
- QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
- Quantum Informed Machine-Learning Potentials for Molecular Dynamics Simulations of CO2's Chemisorption and Diffusion in Mg-MOF-74
- In-silico strategies in nano-drug design: Bridging nanomaterials and pharmacological applications
- mRNA codon optimization with quantum computers
- The computational power of the human brain
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.