Machine learning using libraries Qiskit and squlearn

The bachelor thesis deals with the use and comparison of quantum and classical machine learning techniques, specifically focusing on classification tasks for the diagnosis of Parkinson’s disease. Using current frameworks such as qiskit and squlearn for quantum machine learning and scikit-learn for classical approaches. The study assesses how these technologies handle and analyze datasets. The aim is to perform a detailed review and comparison of quantum algorithms versus classical methods, focusing on their performance in classification tasks, specifically with respect to evaluation metrics such as precision, recall and F1-score. The work is structured in different stages, starting with a theoretical introduction to quantum machine learning, followed by data preprocessing and feature selection using mutual information, and the implementation and evaluation of both the support vector machine classifier and its quantum equivalent, the QSVC algorithm. These models are tested on two datasets and the results are compared with previous research. The paper concludes with a discussion of the comparative results, a control test using the Oxford Parkinson’s disease detection dataset, and an examination of the important attributes and their effect on the predictive performance of the models.