Machine learning (ML) is revolutionizing health sciences, specifically in medical imaging, drug discovery, and personalized care. This shift toward data-driven medicine utilizes computational models to derive clinical insights from complex health data. However, the domain faces significant hurdles, including strict privacy regulations, data heterogeneity, and extreme variance in dataset scales - from small clinical trials to massive omics repositories.To address these challenges, we propose a methodology centered on specialized data processing and encoding to ensure security and optimize data for varying sizes. By integrating quantum computing, our approach tackles complex medical datasets that remain intractable for classical ML. A case study on a heart disease dataset validates the proposed framework, demonstrating the efficacy of hybrid classical-quantum techniques in overcoming the limitations of modern data-driven medicine.

A Recipe for Data-driven Medicine: Data Encoding, Machine Learning, and Quantum Computing

Distefano, Salvatore
;
Ziiatdinov, Mansur
2026-01-01

Abstract

Machine learning (ML) is revolutionizing health sciences, specifically in medical imaging, drug discovery, and personalized care. This shift toward data-driven medicine utilizes computational models to derive clinical insights from complex health data. However, the domain faces significant hurdles, including strict privacy regulations, data heterogeneity, and extreme variance in dataset scales - from small clinical trials to massive omics repositories.To address these challenges, we propose a methodology centered on specialized data processing and encoding to ensure security and optimize data for varying sizes. By integrating quantum computing, our approach tackles complex medical datasets that remain intractable for classical ML. A case study on a heart disease dataset validates the proposed framework, demonstrating the efficacy of hybrid classical-quantum techniques in overcoming the limitations of modern data-driven medicine.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
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/11570/3365410
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact