A new project that uses the help of Artificial Intelligence, coordinated by Tullio Ghi, full professor of Gynecology and Obstetrics at the Catholic University of Rome, is about to cross the doors of the delivery room giving life to an innovative software.

Artificial Intelligence-Based Software will be incorporated into an ultrasound machine and guide the delivery, providing real-time information on the position of the baby's head and suggesting, with a traffic light, to the operators whether to proceed with the natural descent into the birth canal, whether to use the ventouse or intervene with an emergency cesarean section.

Mother with newborn baby son lying in bed

How the project was born

The tool, which could arrive in the delivery room starting from 2028, was developed within the framework of a work published in 'The European Journal of Obstetrics & Gynecology and Reproductive Biology' and coordinated by Tullio Ghi, professor of Gynecology and Obstetrics at the Catholic University and director of the Complex Operating Unit of Obstetrics of the Agostino Gemelli Irccs University Hospital with the technical support ofInstitute of Clinical Physiology of the CNR of Lecce and the Obstetric Clinic of the University of Parma.

The study, carried out within the framework of the Islands international group (International Study Group on Labor and Delivery Sonography) founded by Professor Ghi, will now proceed to a search selected by the Ministry of Health among the projects of national interest (Prin) and financed with a fund of approximately 200 thousand euros.

Where the software comes into play

The journey fetal path in the birth canal may encounter different obstacles and risks. When the occiput of the fetus is oriented towards the sacrum and not towards the mother's pubis, a prolongation or arrest of the progression of labor may occur.

Sometimes the position of the head during descent requires the use of a suction cup to facilitate the exit or an emergency cesarean section for a safe birth for the mother and the baby.

It is for these reasons that it is essential to evaluate how the head is positioned. If the evaluation is done with the fingers, errors can occur in one case out of five, errors that can for example determine the application of the suction cup in the incorrect point of the head with consequent failure of the extraction of the fetus, prolong the birth and, in the worst cases, delay the birth of a child causing suffering.

Thanks to this innovative software, based on artificial intelligence, the doctor will be able to check the ultrasound images on the spot and have precise answers in real time, displaying the 'verdict' like a traffic light: red if it is not the case to proceed with the suction cup and if it is necessary to undertake the choice of an emergency caesarean, green if it is possible to proceed with the suction cup, yellow if the situation is uncertain.

In the published multicenter study, The software has been validated so far on the basis of 2.154 ultrasound images from 16 centers around the world.. The overall performance of the model for fetal head position classification was excellent, with a overall accuracy of 94,5% and a sensitivity of 95,6%.

Artificial intelligence applied to ultrasound can immediately assess the position of the fetal head during delivery, with maximum accuracy. Future studies will test it on a large number of patients before it is introduced into routine clinical practice, but experts are confident and certain that the software will be able to enter delivery rooms within, at most, 4 years.

Artificial Intelligence arrives in the delivery room. A traffic light will help doctors decide last edit: 2024-11-23T07:00:00+01:00 da laracalogiuri

Post comments