Researchers at Florida Atlantic University’s College of Engineering and Computer Science have studied the use of quantum computing alongside machine learning to improve early detection of chronic kidney disease (CKD). The research team, led by Arslan Munir, Ph.D., associate professor in the Department of Electrical Engineering and Computer Science, worked with colleagues from Bangladesh to develop and compare two automated systems for diagnosing CKD: the Classical Support Vector Machine (CSVM) and the Quantum Support Vector Machine (QSVM).
CKD is a progressive condition that damages kidneys over time and can lead to kidney failure if not treated. It often develops gradually with few symptoms in its early stages, making timely diagnosis difficult. Worldwide, around 850 million people live with some form of kidney disease, with about 10 million requiring dialysis or transplantation.
Artificial intelligence and machine learning are increasingly being used to build tools that can detect CKD more efficiently. These algorithms can find subtle patterns in complex medical data that may be missed by clinicians.
In this study, researchers prepared a CKD dataset using comprehensive preprocessing methods. They applied Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) for data optimization before analyzing each dataset with both CSVM and QSVM algorithms.
Results published in Informatics and Health showed that CSVM outperformed QSVM under current hardware conditions. With PCA optimization, CSVM achieved 98.75% accuracy compared to QSVM’s 87.5%. Using SVD, CSVM reached 96.25%, while QSVM managed 60%. Additionally, CSVM was up to 42 times faster than QSVM in some experiments.
Despite these findings, Munir noted that “QSVM’s underperformance is primarily a reflection of today’s computational limitations rather than the potential of quantum algorithms themselves.” He added that even within classical hardware constraints, QSVM’s accuracy surpassed several existing classical SVM methods from previous studies.
Munir stated: “What makes our work unique is that we didn’t just apply classical machine learning to detect chronic kidney disease – we also tested a quantum version under the same conditions. By directly comparing classical and quantum models, and using two different optimization methods, we gained valuable insight into where the technology stands today and how quantum computing could help shape the future of health care analytics.”
The team plans to continue their research by exploring additional quantum machine learning algorithms beyond QSVM and testing their approach on larger datasets. They also aim to optimize feature selection techniques for broader diagnostic applications.
Stella Batalama, Ph.D., dean of the College of Engineering and Computer Science at FAU said: “This research is an important leap toward bringing quantum computing into health care – an emerging field with the power to transform how we detect and treat complex diseases. By combining machine learning with next-generation quantum technologies, this work offers real hope for earlier, faster and more accurate diagnosis of chronic kidney disease, ultimately improving outcomes and saving lives.”
