QUANTUM MECHANICS AND MEDICAL DIAGNOSIS

Ingemar T. Ernberg, Göran Johansson, Tomas Lindblad +2 more

Gamzepelin Aksoy, Zeynep Özpolat

Quantum-assisted machine learning approaches have become a significant area of research in the healthcare domain by offering alternative solutions to classical methods, particularly when dealing with high-dimensional and complex datasets. This study presents a comparative evaluation of the classification performance of classical Support Vector Machines (SVM) and quantum-based algorithms Quantum Support Vector Machine (QSVM) and Pegasos-QSVM on healthcare data. Experimental analyses were conducted using three distinct medical datasets related to liver disease, breast cancer, and heart failure. The results demonstrate that the QSVM model consistently achieved the highest and most stable classification accuracy. Although the Pegasos-QSVM model achieved comparable accuracy rates in certain configurations, its performance was generally more variable. Nevertheless, thanks to its lower computational cost and faster processing time, Pegasos-QSVM emerges as a promising alternative, particularly in resource-constrained environments. The findings suggest that quantum-assisted models can deliver performance levels competitive with classical approaches, particularly highlighting the effectiveness of QSVM on small- to medium-sized datasets.

Alexander V. Chalyi

Upasna Tiwari, Sahil Panwar, Rijul Sharma

Medical image diagnosis has become an integral part of the medical field, which helps the doctor diagnose the disease using various medical image techniques like X-ray, computed tomography, and magnetic resonance imaging. The recent advancements in artificial intelligence and deep learning techniques have improved the efficiency of the medical image diagnosis using artificial intelligence and machine learning techniques. However, the large-scale requirement of the data has raised many issues related to the privacy and security of the data in the medical field. In this regard, the concept of privacy-preserving artificial intelligence has been introduced to ensure the security of the data in the artificial intelligence system. Classical machine learning techniques are limited in handling the complexity of the data and the efficiency of the system. In this regard, the concept of quantum computing has been introduced, which helps the system process the data using the superposition property of the system. The proposed approach also integrates principles of data science and cyber security to ensure efficient data handling and robust protection against emerging digital threats