Quantum Multi-Attribute Search in Healthcare Databases A Hybrid Grover QML Framework for Patient Record Retrieval
R. Keerthana, A. Rajivkannan, K. R. Natarajan +3 more
This study proposed to improve the execution time and accuracy of patient record retrieval in healthcare databases by using a hybrid model that combines Grover's quantum search with Quantum Machine Learning (QML). Two methods were used in this study, where Group 1 refers to classical and standard Grover search methods, and Group 2 refers to the proposed hybrid Grover-QML framework on the same dataset of 1,000 patient records using three attributes: age, symptoms, and disease. The proposed hybrid Grover-QML framework improve an execution time of 0.48 s, an accuracy of 95.2%, and a search efficiency of 94.4%, which are better than the classical method and the standard Grover method, which recorded 0.73 s execution time, 92.3% accuracy, and 83.9% search efficiency. These results show that using Grover's quantum search together with Quantum Machine Learning makes the search faster and more reliable. The proposed method is suitable for efficient multi-attribute patient record retrieval in large healthcare databases.
IEEE Global Symposium on Emerging and Communication Technologies (GSEACT)•Jun 1, 2026•0 citations