Hyperdimensional computing in biomedical sciences: a brief review
Open Access
- 13 May 2025
- journal article
- Published by PeerJ in PeerJ Computer Science
- Vol. 11, e2885
Abstract
Hyperdimensional computing (HDC, also known as vector-symbolic architectures—VSA) is an emerging computational paradigm that relies on dealing with vectors in a high-dimensional space to represent and combine every kind of information. It finds applications in a wide array of fields including bioinformatics, natural language processing, machine learning, artificial intelligence, and many other scientific disciplines. Here we introduced the basic foundations of the HDC, focusing on its application to biomedical sciences, with a particular emphasis to bioinformatics, cheminformatics, and medical informatics, providing a critical and comprehensive review of the current HDC landscape, highlighting pros and cons of applying this computational paradigm in these specific scientific domains. In this study, we first selected around forty scientific articles on hyperdimensional computing applied to biomedical data existing in the literature, and then analyzed key aspects of their studies, such as vector construction, data encoding, programming language employed, and other features. We also counted how many of these scientific articles are open access, how many have public software code available, how many groups of authors, journals, and conferences are most present among them. Finally, we discussed the advantages and limitations of the HDC approach, outlining potential future directions and open challenges for the adoption of HDC in biomedical sciences. To the best of our knowledge, our review is the first open brief survey on this topic among the biomedical sciences, and therefore we believe it can be of interest and useful for the readership.Keywords
Funding Information
- Digital Intervention in Psychiatric and Psychologist Services (F/310240/01-04/X56)
- Ministero dell’Università e della Ricerca of Italy (“Dipartimenti di Eccellenza 2023-2027”)
This publication has 87 references indexed in Scilit:
- Classification using hyperdimensional computing: a review with comparative analysisArtificial Intelligence Review, 2025
- Multi-Class Classification of Abnormal Heartbeat Detection using Hyperdimensional ComputingJournal of Signal Processing Systems, 2024
- Determining the Number of Clusters in Clinical Response of TMS Treatment using Hyperdimensional ComputingJournal of Signal Processing Systems, 2024
- Energy efficiency in cloud computing data centers: a survey on software technologiesCluster Computing, 2022
- A comparison of vector symbolic architecturesArtificial Intelligence Review, 2021
- Preprints Involving Medical Research—Do the Benefits Outweigh the Challenges?JAMA, 2020
- How many preprints have actually been printed and why: a case study of computer science preprints on arXivScientometrics, 2020
- Hyperdimensional Computing for Blind and One-Shot Classification of EEG Error-Related PotentialsMobile Networks and Applications, 2017
- Conference proceedings as a source of scientific information: A bibliometric analysisJournal of the American Society for Information Science and Technology, 2008
- Data Integration — Problems, Approaches, and Perspectives2007