RESUMEN
The discovery of quantum algorithms offering provable advantages over the best known classical alternatives, together with the parallel ongoing revolution brought about by classical artificial intelligence, motivates a search for applications of quantum information processing methods to machine learning. Among several proposals in this domain, quantum kernel methods have emerged as particularly promising candidates. However, while some rigorous speedups on certain highly specific problems have been formally proven, only empirical proof-of-principle results have been reported so far for real-world datasets. Moreover, no systematic procedure is known, in general, to fine tune and optimize the performances of kernel-based quantum classification algorithms. At the same time, certain limitations such as kernel concentration effects-hindering the trainability of quantum classifiers-have also been recently pointed out. In this work, we propose several general-purpose optimization methods and best practices designed to enhance the practical usefulness of fidelity-based quantum classification algorithms. Specifically, we first describe a data pre-processing strategy that, by preserving the relevant relationships between data points when processed through quantum feature maps, substantially alleviates the effect of kernel concentration on structured datasets. We also introduce a classical post-processing method that, based on standard fidelity measures estimated on a quantum processor, yields non-linear decision boundaries in the feature Hilbert space, thus achieving the quantum counterpart of the radial basis functions technique that is widely employed in classical kernel methods. Finally, we apply the so-called quantum metric learning protocol to engineer and adjust trainable quantum embeddings, demonstrating substantial performance improvements on several paradigmatic real-world classification tasks.
RESUMEN
BACKGROUND: The rapid course of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic calls for fast implementation of clinical trials to assess the effects of new treatment and prophylactic interventions. Building trial platforms embedded in existing data infrastructures is an ideal way to address such questions within well-defined subpopulations. METHODS: We developed a trial platform building on the infrastructure of two established national cohort studies: the Swiss human immunodeficiency virus (HIV) Cohort Study (SHCS) and Swiss Transplant Cohort Study (STCS). In a pilot trial, termed Corona VaccinE tRiAL pLatform (COVERALL), we assessed the vaccine efficacy of the first two licensed SARS-CoV-2 vaccines in Switzerland and the functionality of the trial platform. RESULTS: Using Research Electronic Data Capture (REDCap), we developed a trial platform integrating the infrastructure of the SHCS and STCS. An algorithm identifying eligible patients, as well as baseline data transfer ensured a fast inclusion procedure for eligible patients. We implemented convenient re-directions between the different data entry systems to ensure intuitive data entry for the participating study personnel. The trial platform, including a randomization algorithm ensuring balance among different subgroups, was continuously adapted to changing guidelines concerning vaccination policies. We were able to randomize and vaccinate the first trial participant the same day we received ethics approval. Time to enroll and randomize our target sample size of 380 patients was 22 days. CONCLUSION: Taking the best of each system, we were able to flag eligible patients, transfer patient information automatically, randomize and enroll the patients in an easy workflow, decreasing the administrative burden usually associated with a trial of this size.