Let’s start at the beginning. You trained as a computer engineer. Did you always know that’s what you wanted to do?

As a child, I was very good at languages and philosophy; they came easily to me, but I was more interested in understanding things that posed a personal challenge, such as mechanics and mathematics. On the other hand, my older brother had a computer when I was still in school, and I drove him crazy installing programs, playing, and later connecting to the internet to chat with the neighbors. So when it came time to choose my high school path, I already leaned toward computer engineering.

How did you arrive at IDIAPJGol and what was your first contact with SIDIAP?

I was working at UPC when a colleague told me there was an IT position at the Institute. I became interested, and since I really liked databases, when they explained what SIDIAP was, I thought it could be a good fit. And so it was: I started working as a Data Manager and learning what Primary Care is, guided by Dr. Elorza.

How has SIDIAP evolved since you started working there?

When I arrived, SIDIAP was very young; there were manual processes and it was not yet well known internationally. In Spain, and in Europe more broadly, research with real-world data (Real World Data) was just beginning.

Now, the number of research projects with Catalan participation, as well as their level and impact, has increased enormously. Thanks to this, the team behind it has grown, we’ve improved the documentation we provide to researchers, and the technology we use. For example, the data update time has been cut in half — now semi-annual — quality indicators have improved, the available data sources for research have expanded, and the number of international Common Data Models (CDM) we participate in has increased.

And what do you think your personal contribution has been?

Over the years, I’ve become a good translator between research teams and their needs, and the technical teams. Personally, I’ve worked extensively on the automation and optimization of SIDIAP’s technological processes, on raising the national and international visibility of the platform and the team’s work — which is much more than just providing data — and on driving technological projects from within.

Would you highlight any specific study in which SIDIAP has been key in making major advances?

SIDIAP data have been used in many studies on different pathologies that have achieved great impact.

I especially remember the race-against-time projects carried out at the start and during the COVID-19 pandemic, when we were all confined: first characterizing patients, then the waves and resulting complications, and later assessing whether there were adverse effects from the vaccines.

Even so, before and after the pandemic, high-impact studies have been conducted, such as REGIPREV — the first project using SIDIAP data in 2011 — APRES, which showed that the use of antibiotics in some cases can be counterproductive in terms of resistance, and the 4E study evaluating the effectiveness of statins in older populations.

All publications using SIDIAP can be found at: https://www.sidiap.org/index.php/ca/activitat.

Are you already applying Artificial Intelligence (AI) in SIDIAP?

Yes, we currently collaborate with researchers to apply AI algorithms to research projects in Primary Care. We work with free-text processing (NLP), make predictions, and are developing Deep Learning algorithms on the databases to ensure pseudo-anonymisation.

What challenges do you think AI will allow SIDIAP to overcome?

I believe that with AI, and with explainability techniques (XAI), we’ll be able to find relationships that are not yet preconceived, which makes it very exciting. SIDIAP data will be used to validate risk prediction models and thus work toward their implementation in the health system.

Thanks to AI, it will also be much easier to guarantee that data requested for research present no risks, and thus simplify access to them.