Electrical and Computer Engineering Publications

Document Type

Conference Proceeding

Publication Date


First Page


URL with Digital Object Identifier


Last Page



Increasingly we are faced with complex health data, thus researchers are limited in their capacity to mine data in a way that accounts for the complex inter-relationships between health variables of interest. This research tackles the challenge of producing accurate health prediction models in order to overcome the limitations of simple multivariate regression techniques and the assumption of linear association, also known as algorithmic models, by combining it with a soft computing approach. Predictive models develop methods to enable healthcare researchers and professionals to predict the likelihood of an individual's proclivity to a disease and the likely effectiveness of possible treatments. Personalized approaches focus on the individual - relying on the individual's existing health data across the healthcare system with treatment targeted at the individual.


Full conference program available at: https://link.springer.com/content/pdf/10.1007%2F978-3-030-15996-2.pdf

Citation of this paper:

Capretz L.F., HPC for Predictive Models in Healthcare, 13th International Conference on High-Performance Computing (HPC) for Computational Science (VECPAR 2018), Sao Pedro, Sao Paulo, Brazil, Lecture Notes in Computer Science (LNCS11333), pp. 257-258, DOI: 10.1007/978-3-030-15996-2, Springer Nature Switzerland, 2019.

Find in your library