The Hospital Clínic and the Barcelona Supercomputing Center use AI to predict the evolution of Covid-19 patients

Technology News

The Hospital Clínic de Barcelona and the Barcelona Supercomputing Center –Centro Nacional de Supercomputación (BSC) are working on a new model based on artificial intelligence (AI) that helps doctors predict the evolution of Covid-19 patients and those responsible centers to plan their internal organization in the event of a new wave of cases . The project is part of the Plan to Promote Language Technologies of the Secretary of State for Digitalization and Artificial Intelligence and is open to collaboration with more hospitals.

To develop these tools, its research teams will use as a basis the information contained in the clinical reports of 3,051 Covid-19 episodes (corresponding to 2,440 patients) that the hospital treated during the acute phase of the pandemic and those that may arise in the future.

With the information on the diagnosis , treatment and evolution of these cases (duly anonymized), a model based on artificial intelligence will be trained, specifically deep learning neural networks, which will look for common patterns and generate predictions on the evolution of new patients.

For models based on neural networks to be effective, they must be trained with large amounts of data , such as those that Hospital Clínic can provide. In addition, they also require great calculation capacity (such as that of the MareNostrum 4 supercomputer, from the Barcelona Supercomputing Center), since the training sessions need to be repeated thousands of times for the system to learn to distinguish between what is important and what is superfluous . as well as to establish correlations between events.

The elaboration of prediction models based on clinical reports has the added complexity that, before training the artificial intelligence models, it is necessary to automatically extract all the relevant information contained in the various hospital documents referring to the same case: laboratory reports, radiology, diagnoses, clinical courses, etc.

To achieve this, natural language processing technologies (another branch of AI) are used, which analyze the texts written by healthcare personnel and turn them into “events” that the system must take into account (relevant diagnostic results, symptoms, treatments, evolution, etc.).

These “events” are used to train neural networks, which will search for common patterns and, based on them, will make evolution predictions for new cases.

Institutional collaboration
“The pandemic Covid-19 has offered the opportunity to realize the necessary collaboration between institutions in order for advanced research have a return for the benefit of the patient as substantive assistance to the physician in making decisions , ” says Xavier Pastor , head of Medical Informatics at the Hospital Clínic de Barcelona.

With this collaboration, he emphasizes, “it will be possible to obtain an added value from the great effort of health professionals who, under exceptional conditions, have used, without interruption, the computerized medical history as a real-time documentary record of the situation of each patient , of the actions that have been carried out and the results obtained ”.

“The clinical reports of Covid-19 cases contain essential information to analyze the evolution of the disease, the response to treatment and the previous conditions of the patients that may have been risk factors”, adds Alfonso Valencia , director of the Department of Sciences of the Life of the Barcelona Supercomputing Center.

This agreement enables collaboration between BSC experts in data mining and natural language processing with experts in clinical information management in hospitals and is essential to answer critical clinical questions about the origin and evolution of the disease.

For Valencia, the ultimate objective of the collaboration is to provide the health systems, and in particular the hospitals with which it collaborates, with computer systems that can contribute to improving the treatment of patients in both this and future epidemics.

Leave a Reply

Your email address will not be published. Required fields are marked *