Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Quantum Machine Learning in Healthcare: Evaluating QNN and QSVM Models

Antonio Tudisco, Deborah Volpe, Giovanna Turvani

TL;DR

This study compares quantum classifiers (QNN and QSVM) with classical models for healthcare diagnosis across three imbalanced datasets (Heart Failure, Diabetes, Prostate Cancer). Using PCA preprocessing to fit NISQ constraints, QSVM consistently shows robustness to imbalance and often superior recall, while QNN can overfit and vary with hyperparameters. The results indicate quantum approaches hold promise, particularly for imbalanced medical data, though classical models remain strong on more balanced datasets. The work advocates further exploration of hybrid quantum-classical methods and advanced quantum kernels to advance clinical applicability.

Abstract

Effective and accurate diagnosis of diseases such as cancer, diabetes, and heart failure is crucial for timely medical intervention and improving patient survival rates. Machine learning has revolutionized diagnostic methods in recent years by developing classification models that detect diseases based on selected features. However, these classification tasks are often highly imbalanced, limiting the performance of classical models. Quantum models offer a promising alternative, exploiting their ability to express complex patterns by operating in a higher-dimensional computational space through superposition and entanglement. These unique properties make quantum models potentially more effective in addressing the challenges of imbalanced datasets. This work evaluates the potential of quantum classifiers in healthcare, focusing on Quantum Neural Networks (QNNs) and Quantum Support Vector Machines (QSVMs), comparing them with popular classical models. The study is based on three well-known healthcare datasets -- Prostate Cancer, Heart Failure, and Diabetes. The results indicate that QSVMs outperform QNNs across all datasets due to their susceptibility to overfitting. Furthermore, quantum models prove the ability to overcome classical models in scenarios with high dataset imbalance. Although preliminary, these findings highlight the potential of quantum models in healthcare classification tasks and lead the way for further research in this domain.

Quantum Machine Learning in Healthcare: Evaluating QNN and QSVM Models

TL;DR

This study compares quantum classifiers (QNN and QSVM) with classical models for healthcare diagnosis across three imbalanced datasets (Heart Failure, Diabetes, Prostate Cancer). Using PCA preprocessing to fit NISQ constraints, QSVM consistently shows robustness to imbalance and often superior recall, while QNN can overfit and vary with hyperparameters. The results indicate quantum approaches hold promise, particularly for imbalanced medical data, though classical models remain strong on more balanced datasets. The work advocates further exploration of hybrid quantum-classical methods and advanced quantum kernels to advance clinical applicability.

Abstract

Effective and accurate diagnosis of diseases such as cancer, diabetes, and heart failure is crucial for timely medical intervention and improving patient survival rates. Machine learning has revolutionized diagnostic methods in recent years by developing classification models that detect diseases based on selected features. However, these classification tasks are often highly imbalanced, limiting the performance of classical models. Quantum models offer a promising alternative, exploiting their ability to express complex patterns by operating in a higher-dimensional computational space through superposition and entanglement. These unique properties make quantum models potentially more effective in addressing the challenges of imbalanced datasets. This work evaluates the potential of quantum classifiers in healthcare, focusing on Quantum Neural Networks (QNNs) and Quantum Support Vector Machines (QSVMs), comparing them with popular classical models. The study is based on three well-known healthcare datasets -- Prostate Cancer, Heart Failure, and Diabetes. The results indicate that QSVMs outperform QNNs across all datasets due to their susceptibility to overfitting. Furthermore, quantum models prove the ability to overcome classical models in scenarios with high dataset imbalance. Although preliminary, these findings highlight the potential of quantum models in healthcare classification tasks and lead the way for further research in this domain.

Paper Structure

This paper contains 12 sections, 3 equations, 17 figures, 12 tables.

Table of Contents

  1. Introduction
  2. Motivation and General Idea
  3. Implementation
  4. Results
  5. Figures of Merit
  6. Datasets Analysis
  7. Performed Tests
  8. Heart-Failure
  9. Diabetes
  10. Prostate Cancer
  11. Discussion
  12. Conclusions

Figures (17)

  • Figure 1: Quantum Neural Network (QNN).
  • Figure 2: Representation of a general angle encoding circuit, where R can be any rotational gate. A combination of multiple rotational gates can also be employed.
  • Figure 3: Example of Basic Entangling Layer circuit.
  • Figure 4: Example of a Strongly Entangling Layer circuit.
  • Figure 5: Quantum Support Vector Machine (QSVM).
  • ...and 12 more figures