A multidisciplinary team from the University of Coimbra is developing a computer analysis system to predict the probability that an induced birth will occur vaginally, it was announced this Monday.
So far, researchers involved in the project analyzed data from 2,600 women followed at the Coimbra Hospital and University Center (CHUC), “which point to promising results,” the higher education institution reported.
“The next step is to analyze the ultrasounds collected and, subsequently, create a tool with all this data and test it on real people,” said the Faculty of Science and Technology of the University of Coimbra (FCTUC) in a statement sent to Lusa. agency.
Researchers from the Department of Computer Engineering (DEI) of FCTUC) and the Faculty of Medicine (FMUC) participate in the work, who “are committed to developing a system that aims to predict, through computational analysis, the possibility of a birth vaginal”. after his induction.”
“Labor inductions are being performed more and more frequently, but they do not always result in a vaginal delivery,” he said.
This was the “starting point” of the research “Prediction of vaginal birth after induction of labor with machine learning”, by the author Iolanda Ferreira, doctoral student in Health Sciences, under the scientific direction of Ana Luísa Areia, professor at FMUC, with the support of João Nuno Correia, professor at the same faculty.
“All inductions have between a 30 and 35% chance of ending in a cesarean section, so we know in advance that 70% of women will have a vaginal birth. However, if of that 30% we could specify that in reality will end in a cesarean section, we were able to provide adequate and proactive advice on the need to induce labor, an arduous process for the mother and the fetus and which, in fact, can increase the emotional and economic burden associated with this procedure,” explained Iolanda Ferreira. .
Since it is “such a common procedure, which generates so much data, we thought that perhaps we could use a technique that analyzes it to help doctors understand if it is worth it – or when it is worth investing in an induction” . to achieve a vaginal birth,” he stated.
Quoted in the note, the doctoral student highlighted that, “at this time, obstetricians invest in inducing labor in all women, knowing from the beginning, due to certain characteristics, what may or may not occur vaginally.”
For João Nuno Correia, “the idea is to devise something that, through the fusion of data (tables and images), forms a support module that provides personalized information about each pregnant woman, about the high probability of vaginal birth after induction”. .
“If this is high, the induction will be performed with greater confidence. If not, that is, there is a very high probability of cesarean section, the pregnant woman can be advised otherwise,” he added.
In this research, the innovation consists of “predicting the type of birth also using ultrasound image data.”
“The clinician is based on the person’s clinical history and their characteristics after that pregnancy, (…) we want to see if the system, when analyzing that combination of clinical data and images, perceives it in a way that later helps or not draw conclusions,” the researchers stressed.
This collaboration between DEI and FMUC “is essential, because in the future it will support doctors’ decisions before delivery and, consequently, improve both neonatal outcomes and women’s experience during childbirth,” they concluded.
Source: TSF
