The application retrieve information on patients' previous pathologies, results and tests in order to design customised treatments.
Vicent Soler and Carolina Pascual, together with Amparo Navarro, attend the presentation of this project, financed by donations from the public
Alicante. Tuesday, 13 July 2021
The Government of Valencian and the University of Alicante have promoted a project using big data and artificial intelligence to improve care for patients suffering from COVID-19, after analysing the previous pathologies they have suffered, the treatments they have undergone, the results obtained and the evolution of the disease. Based on the cross-referencing of these data, the algorithms suggest the most successful treatment for each patient.
The project has been developed by the University of Alicante Lucentia research group and several hospitals in the region of Valencia are collaborating, such as the Hospital la Fe in Valencia, with the participation of researchers María Eugenia Gas López, José Luis Vallés Pardo and Alba Loras, and Bernardo Baldivieso, director of the Planning Area, as well as the Hospital de Elda, with the collaboration of medical doctors Reyes Pascual Pérez, Head of the Internal Medicine and Infectious Diseases section and UMH senior lecturer at the Department of Medicine; and Eleuterio Llorca Martínez, Head of the Pneumology section and President of the scientific committee of the Valencian Society of Pneumology.
Regional Minister for Finance and Economic Model Vicent Soler, and the Regional Minister for Innovation, Carolina Pascual, together with University of Alicante President Amparo Navarro have presented today the initiative that has been financed thanks to donations made by citizens, through the line set up by the Valencia government. In particular, this project received funding of €100,000.
Vicent Soler stressed that this is an example of the collaboration between the Valencian government, the university world and civil society. This crisis has been a challenge at all levels and has forced us to give the best of ourselves as a government and as individuals. They decided to allocate the donations made by anonymous citizens, groups and companies in their entirety to research projects of excellence against the virus, and now we are seeing the results.
Increasingly, the university is being recognised as a top-level research centre. That is why it is so important to continue making progress in the transformation of our economic model towards one based on knowledge, R&D&I and sustainability.
In this sense, the UA president recalled that more than 70% of the research carried out in Spain is developed within the universities, for which she thanked the Valencian government for its economic support and urged them to consolidate new lines of funding for scientific progress and the positioning of research in our region
Along the same lines, Carolina Pascual pointed out that it is fundamental to adapt technological training to the needs of the productive fabric. The Valencian Region has an excellent network of research institutes which, in collaboration with universities and companies, can play a fundamental role in raising our level of research and offering cutting-edge solutions to the challenges we are facing.
For this reason, she indicated that this is one of the projects chosen by the Regional Ministry of Innovation to allocate part of the 1.2 million received from COVID-19 donations. "Aware that sustained investment in the field of science allows us to get out of the crisis faster and better, they have seen clearly the areas that need to be given preference. The commitment to science will grow by 70% in the 2021 budget.
The event was also attended by Regional Secretary for Universities and Research Carmen Beviá and Director of the Lucentia research team and professor in the Department of Computer Languages and Systems (DLSI) at the University of Alicante, Juan Carlos Trujillo Mondéjar, who explained the details of the development of the project.
The proposal and construction of this model is based on the previous experience of the Lucentia research group at the University of Alicante. The project has enabled the development of a platform that accesses patients' medical records to retrieve information on previous pathologies, treatments received and tests performed to detect COVID-19.
Based on this data, artificial intelligence models are designed and trained so that each time a new patient is admitted, the system classifies them into one of the three groups. In addition, based on data on the evolution of all patients to the measures and treatments received, the algorithms will suggest the most successful treatment for each one of them.
Advantages of the system
The use of this system has revealed several advantages, including the fact that it allows data to be extracted transparently from medical records and other data sources, without requiring additional work on the part of the clinicians. This is essential in the face of possible overloading of the health system.
It also provides a classification of the patient through an intelligence system, indicating the degree of confidence based on the available data, so as to shorten care times and contribute to optimising the system.
In this first phase, the model has been trained with variables provided by the Instituto de Investigación Sanitaria La Fe de Valencia, having developed a model that obtains 90% accuracy, and obtaining results comparable to other models published by the international community. At present, the current state of the model developed within the framework of this project has an accuracy comparable to other similar models, improving the level of detail of the morbidities considered.
Furthermore, based on the different meetings with the experts of the clinical informatics committee, more models have been proposed to be built in order to predict whether a patient, depending on his severity and condition, should be monitored by one of the hospital units (hospital home unit, hospital, ICU) on the basis of the data provided. Given the special features of medical resources in this disease, such as the possible saturation of units and services, a prediction model will also be built to indicate the days that the patient will be admitted to the intensive care unit (ICU).
So far, over 3,000 variables from 6,000 patients have been included in the algorithm and analysed. This application can not only be integrated with hospitals in the Valencian region, but also easily exportable to all hospitals in Spain. If we correctly hybridise information technologies with the knowledge of experts and medical doctors, we can collaborate together to achieve the goal of a more personalised medicine, more focused on the patient and not standard diagnoses, as explained by Juan Carlos Trujillo, the director of the Lucentia research group.
Download link of the application presentation video
Carretera San Vicente del Raspeig s/n - 03690 San Vicente del Raspeig - Alicante - Tel. 96 590 3400 - Fax 96 590 3464