DISTRA, a tool developed by Vicomtech that uses Artificial Intelligence to predict future diseases based on current pathology

A group of researchers from Vicomtech has developed, in collaboration with the Asuncion Klinika hospital in Toulouse, a tool called DISTRA which, through the use of artificial intelligence, is capable of identifying risk patterns or predicting future diseases that a person will suffer depending on their current pathology. A system has been developed to display information using graphs and statistical analysis in order to understand how different trajectories affect the group selected for the study. The graphs summarise all the information in a visual way, allowing health professionals to study the cohort, i.e. the group that is part of the study and is observed for the duration of the study, so that the tool is able to classify it according to its impact and interact with the interactive graph to achieve a more in-depth analysis.

For this purpose, the database of electronic records of Asuncion Klinika has been used, which has allowed the Vicomtech team to access 526,597 diagnostic records coded with ICD9 and ICD10, covering a large part of the population of Tolosaldea. Specifically, the medical records of 71,846 patients have been used, completely anonymously. Thus, Datua has taken the tool developed by Vicomtech into production, designing the interface of the platform to be used by the clinic.  

Vicomtech has contributed mathematical expertise to the project, using data mining techniques to assess the impact of the trajectories identified in the data. In particular, artificial intelligence has been applied to predict future ailments based on the patient's current pathology. In addition, Vicomtech has been able to create visual analysis interfaces to facilitate access to information for both clinicians and patients.

Studies have shown that estimating disease progression based on the patient's current condition is key to precision medicine. However, the number of tools for this analysis using artificial intelligence is limited or non-existent.

This project has an ambitious projection for the future, as it will seek to expand the data network thanks to new records made in other populations. With this growth, the team of researchers will be able to obtain comparative data from the different populations recorded. Thanks to DISTRA and the tool developed, artificial intelligence could be used to train predictive models focused on single patients rather than general populations.

By focusing on the individual characteristics of each patient, predictive models can be tailored more precisely to their specific needs, resulting in more accurate diagnoses and more effective treatments. This allows for more personalised medical care, improving the quality of patient follow-up and maximising the potential to improve the health and quality of life of each individual. In addition, by having the ability to access data such as complete medical history, potential disease risks can be proactively identified and addressed, leading to more effective preventative care and more favourable long-term health outcomes. 

English subtitles available. Activate them in the player

Watch video on Youtube