Quantum-Inspired Evolutionary Algorithms for Biomedical Decision Support Systems

Abstract

Such decision support systems in the biomedical sphere are more important for health improvement, as they provide data-driven insights for making decisions about diagnostics, prognosis, and treatment plans. However, with regard to high dimensions, biomedical data is challenging because it makes existing computing methods difficult to execute. A new strategy of decision-making strategies in BDSS is proposed using quantum-inspired evolutionary algorithms. It introduces an approach bridging the gap in terms of the convergence speed and quality of solutions of traditional algorithms along with scalability by introducing concepts from quantum superposition and entanglement into evolutionary strategies. This approach has been extensively tested using publicly available biomedical datasets. QIEAs can achieve better performance than conventional algorithms concerning faster convergence, higher accuracy, and better multiobjective optimization. This work opens up the integration of quantum-inspired computational intelligence to real biomedical applications, like personalized medicine and predictive analytics.