2023-11-24 07:45:28
Many aspects of COVID-19 remain unknown, especially because the infection itself and the characteristics of each of its variants are variable. The disappearance of the disease is not expected in the short or medium term, so it is necessary to continually analyze the associated characteristics and factors related to poor evolution in order to quickly adapt treatments and, where appropriate, reorganize the health system. Therefore, it is essential for healthcare services to develop predictive models that provide more information about the health status of patients and predict the risk of worsening or having to be admitted to the ICU.
Researchers from the Department of Mathematics of the University of the Basque Country (UPV/EHU), together with medical and research staff from the Galdakao-Usansolo Hospital, have used the data of 380,081 patients infected with SARS-CoV-2 in the CAPV between 1 March 2020 and January 9, 2022 to achieve a predictive model.
UPV/EHU professor Irantzu Barrio explains that “we have identified factors related to hospital admissions of people with this infection, poor outcomes (having to be treated in the ICU or dying) and mortality. “We have seen which factors in the general population of the Basque Country can predict one of the three aforementioned situations and, based on the developed model, we have created a series of scales to measure the severity of the patients.”
The model was developed by the team led by Janire Portuondo-Jiménez, from the Biocruces-Bizkaia Health Research Institute in the Basque Country, before the Omicron variant appeared, so it has been validated with data from infections contracted with this variant also. The members of the research are satisfied with the good results obtained: “We have achieved a good model, which can also be used with new variants.” On the other hand, the researcher has pointed out that this is a study carried out at the population level, that is, “we have used a large number of data, and in statistics, the more data that is used to create models, the better and more rigorous the models are. results obtained”.
In this way, they propose a series of risk scales based on basic information, very easy to calculate and with great predictive capacity. “We have not used many variables, only baseline variables: other diseases of the patients, treatments, age, sex… In fact, collecting data at a population level makes the database very complex,” says Barrio. . These scales can be of great help to primary care, emergency department, and hospital care professionals. “Not so much to make medical decisions, but to know what degree of risk a patient infected by SARS-CoV-2 has, based on their characteristics and other ailments, of developing poorly in the short term,” explains the professor.
Irantzu Barrio (Photo: Laura López / UPV/EHU)
A journey of many years
The Mathmode research group of the UPV/EHU, to which Irantzu Barrio belongs, is an expert in the development, validation and subsequent preparation of predictive models through computer tools for use by professionals. This has not been the first time they have worked together with the Galdakao-Usansolo Hospital. In fact, they have been collaborating for many years in statistical research on different diseases: “We have investigated the evolution of people who have had some type of cancer, chronic obstructive pulmonary disease, heart failure or the quality of life of cancer patients, etc. ». Barrio highlights the importance of teamwork: «It is very important that professionals from different areas collaborate and complement each other. “They set objectives and we have to be able to see which alternatives are the most methodologically appropriate to investigate them.” Currently they continue working with the database created for this research, analyzing other aspects.
The study is entitled “Clinical prediction rules for adverse evolution in patients with COVID-19 by the Omicron variant”. And it has been published in the academic journal International Journal of Medical Informatics. (Source: UPV/EHU)
#Predict #poor #clinical #outcome #patients #COVID19