Quantum kernels for real-world predictions based on electronic health records

TL;DR

This paper empirically investigates whether quantum kernels can outperform classical models in healthcare data, specifically electronic health records, by systematically testing various configurations on an IBM quantum computer.

Contribution

It introduces the first systematic framework for empirical quantum advantage in healthcare, analyzing quantum versus classical models across multiple data configurations.

Findings

Quantum kernels show advantage in specific data regimes.

Proposed a terrain ruggedness index to predict model performance.

Conducted one of the largest quantum machine learning experiments to date.

Abstract

In recent years, research on near-term quantum machine learning has explored how classical machine learning algorithms endowed with access to quantum kernels (similarity measures) can outperform their purely classical counterparts. Although theoretical work has shown provable advantage on synthetic data sets, no work done to date has studied empirically whether quantum advantage is attainable and with what kind of data set. In this paper, we report the first systematic investigation of empirical quantum advantage (EQA) in healthcare and life sciences and propose an end-to-end framework to study EQA. We selected electronic health records (EHRs) data subsets and created a configuration space of 5-20 features and 200-300 training samples. For each configuration coordinate, we trained classical support vector machine (SVM) models based on radial basis function (RBF) kernels and quantum models with custom kernels using an IBM quantum computer, making this one of the largest quantum machine learning experiments to date. We empirically identified regimes where quantum kernels could provide advantage on a particular data set and introduced a terrain ruggedness index, a metric to help quantitatively estimate how the accuracy of a given model will perform as a function of the number of features and sample size. The generalizable framework introduced here represents a key step towards a priori identification of data sets where quantum advantage could exist.