Prediction of future pathologies through Artificial Intelligence and Big Data

One of the most basic aspects of clinical care in hospitals is an understanding of risk factors for disease and mortality , especially for rare but preventable diseases or outcomes. Although the elaboration of relationships between diseases has a long history, the recent advent of digitized medical records and disease registries has improved the ability to organize and analyze health data. The availability of these data allows retrieval of known temporal correlations of diseases using non-longitudinal data, exploration of unordered pairs of diseases, and allows network analyzes of disease relationships to be performed on a national scale. However, while big data analytics have aided the ability to visualize, search, and organize health data, success in identifying and validating new temporal relationships between diseases that could significantly change clinical care has been limited.

Main goal:

The objective of this project, subsidized by the Hazitek program to support Business R&D promoted by the Spri, together with the Department of Economic Development, Sustainability and the Environment of the Basque Government , is to implement tools based on artificial intelligence for the development of algorithms that define different trajectories of temporary pathologies to be able to predict future diseases , as well as the development of innovative visual analytics tools that help health professionals in decision-making.


Technological objectives:

  • Research in technologies that allow a better understanding of the data from its origin, and allowing its subsequent exploitation by a knowledge management system

  • Research into technologies that allow these data to be converted into knowledge and to obtain efficient use of them in a health field through the application of predictive models and decision support systems for both medical professionals and health managers.

  • Research in technologies that promote prevention, with special emphasis on that population that is vulnerable to a potential risk of developing multiple diseases

Participating entities:

Funded by:

Fila de la tabla