Accurate and reliable diagnosis of diseases is crucial in enabling timely medical treatment and enhancing patient survival rates. In recent years, Machine Learning has revolutionized diagnostic practices by creating classification models capable of identifying diseases. However, these classification problems often suffer from significant class imbalances, which can inhibit the effectiveness of traditional models. Therefore, the interest in Quantum models has arisen, driven by the captivating promise of overcoming the limitations of the classical counterpart thanks to their ability to express complex patterns by mapping data in a higher-dimensional computational space. This work proposes a novel approach for enhancing the classification performance of Quantum Neural Networks (QNN) consisting of multiple Variational Quantum Circuits (VQCs) arranged sequentially. This strategy increases the nonlinearity of the model by exploiting the measurement operation and improving its ability to capture complex patterns. In this analysis, the proposed method is compared against classical models while varying its degrees of freedom, specifically the number of involved VQCs, on three well-known healthcare datasets - Prostate Cancer, Heart Failure, and Diabetes. The results prove the potential of the quantum model and demonstrate the validity of the proposed approach, showing that its advantage increases with the complexity of the classification.

Multi-VQC: A Novel QML Approach for Enhancing Healthcare Classification / Tudisco, Antonio; Volpe, Deborah; Turvani, Giovanna. - (2025), pp. 28-34. (Intervento presentato al convegno 2025 IEEE International Conference on Quantum Software tenutosi a Helsinki (Fin) nel 7-2 July 2025) [10.1109/qsw67625.2025.00013].

Multi-VQC: A Novel QML Approach for Enhancing Healthcare Classification

Tudisco, Antonio;Volpe, Deborah;Turvani, Giovanna
2025

Abstract

Accurate and reliable diagnosis of diseases is crucial in enabling timely medical treatment and enhancing patient survival rates. In recent years, Machine Learning has revolutionized diagnostic practices by creating classification models capable of identifying diseases. However, these classification problems often suffer from significant class imbalances, which can inhibit the effectiveness of traditional models. Therefore, the interest in Quantum models has arisen, driven by the captivating promise of overcoming the limitations of the classical counterpart thanks to their ability to express complex patterns by mapping data in a higher-dimensional computational space. This work proposes a novel approach for enhancing the classification performance of Quantum Neural Networks (QNN) consisting of multiple Variational Quantum Circuits (VQCs) arranged sequentially. This strategy increases the nonlinearity of the model by exploiting the measurement operation and improving its ability to capture complex patterns. In this analysis, the proposed method is compared against classical models while varying its degrees of freedom, specifically the number of involved VQCs, on three well-known healthcare datasets - Prostate Cancer, Heart Failure, and Diabetes. The results prove the potential of the quantum model and demonstrate the validity of the proposed approach, showing that its advantage increases with the complexity of the classification.
2025
979-8-3315-6720-0
File in questo prodotto:
File Dimensione Formato  
MultiVQC.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 338.72 kB
Formato Adobe PDF
338.72 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
QSW_QML_Healtcare.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 777.3 kB
Formato Adobe PDF
777.3 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/3002732