Our next presenter will talk about Artificial Intelligence. IOMED combines electronic health record databases with machine learning to get accurate results, improve research outcomes and reduce the time to market by streamlining clinical trials.
I am here to talk about data and artificial intelligence. And when we speak about data in clinical research, one of the main chapters is real-world data. Real-world data represents everything in the medical practice between the patient and doctor collected in electronic health record (EHR) systems.
The problem with this information is that it is mainly unstructured. Furthermore, the bulk of this information is collected as text, as we cannot automatically analyze or collect information. Instead, we need to manually transform it, manually collect it, read through the medical records, and so on. This takes a huge amount of time and represents a big problem when we discuss clinical research.
As you all very well know, clinical research is one of the key points in developing our healthcare system. And the problem is when we use clinical data or real-world data for this kind of research, we spend a huge amount of time collecting, treating, and cleaning that data.
What we intend to do is capture all of this and change data at the source. We want to change the data in the hospital. And that is what we do using natural language processing. Natural language processing is a variant of artificial intelligence that allows us to read the clinical text and find everything clinically relevant there. It is not about finding words; it is about finding context and understanding the text as a whole. Understanding all of the language and transforming it into something usable. In this case, into structured data. That we can then collect and use for different purposes.
When we use this technology, we can massively reduce the time of data collection. Previously this sample took around 320 hours, completed in 60 hours for the data collection. We are massively reducing a critical part of clinical research. We are changing everything related to data collection, the recruitment of patients, and so on. We can reduce time and increase the number of patients we recruit, collect data, and everything we extract from that information. We can completely overturn this process.
This is something we are already doing. Something that is being implemented in several hospitals in our environment. We are present in over 15 hospitals in pain. We are currently expanding in the UK; we are looking to expand into Portugal. Currently, we are offering access to a database of 12 million directly from the EHR systems. This is one of the largest healthcare research databases available in the market.
To access this, we offer two very different products. On the one hand, Compass is a product that is an interface that allows you to perform queries on your own and access an aggregated version of the data instantly. And then, we have what we call automatic data collection, which is a service that allows you to access patient-level data for particular uses like clinical research, clinical trials on a case-by-case basis.