Quantum simulation scenarios and disease classification behaviour on diabetes data

Abstract

In quantum mechanics, the state of a particle can be fully characterised for all future periods based on the beginning conditions and knowledge of the potential occupied by the particle. This paper presents an overview of the integration of statistical machine learning and quantum mechanics. Furthermore, we provide simulation scenarios, classification behaviour, and empirical observations on healthcare data through the utilisation of Feynman diagrams (Feynman et al., 2010) and QLattice (Abzu, 2022). The experimental simulation is carried out in the following instances: 1) changing the number of updating loops; 2) calling the qgraph.fit function multiple times before updating the QLattice; 3) fitting and selecting graphs according to different loss functions; 4) setting the graphs max depth to comparatively higher or smaller values. The paper concludes by summarising the observations made throughout the study and discussing the potential for future work in this field.