Scientists from three centers in Gdańsk are working on a solution that can radically increase the chances of detecting a brain aneurysm before it ruptures and hemorrhages. Artificial intelligence analyzing clinical data plays a key role here, said the spokesman of the Gdańsk University of Technology.
Patryk Rosiński announced in a press release that the aim of the project conducted by scientists from the Gdańsk University of Technology, the Medical University of Gdańsk and the University Clinical Center in Gdańsk is to create a tool that – based on laboratory data, medical interview and descriptions from medical records – it will allow you to estimate the risk of the presence of an aneurysm and its rupture.
– This is a groundbreaking approach. Until now, it was believed that such an assessment was only possible on the basis of imaging tests, such as tomography or angiography – said the spokesman.
The researchers plan to carry out three stages of work: predicting the risk of aneurysm rupture, assessing the probability of a patient belonging to a risk group, and creating a clinical calculator and application for doctors to support decisions regarding the treatment of at-risk patients.
The team's models analyze routine laboratory test results and text-based medical records. Data from over 60,000 people was used to create them. patients treated at the University Clinical Center in Gdańsk in the years 2006–2024.
The university's spokesman announced that the first models achieved promising results – over 77%. effectiveness and about 80 percent sensitivitywhich indicates great clinical potential.
In the first stage, 26 laboratory test results and predictors from medical records were taken into account, including: glucose levels, platelets, creatinine, sodium, MCH, MPV, lymphocytes, potassium, as well as risk factors such as smoking, diabetes and hypertension.
– At this stage, statistically significant differences were demonstrated between patients with a ruptured and unruptured aneurysm. In the case of patients with a ruptured aneurysm, tests were always conducted on the basis of data from before its rupture, the spokesman said.
Dr. Patryk Jasik, team leader from the Gdańsk University of Technology, emphasized that the data had been carefully prepared for analysis and modeling, taking into account protection against leaks.
– We used modern predictive models, including: TabNet, and multi-criteria validation, which allowed to avoid overestimating the results. The accuracy of the models exceeds 80 percent, and in some analyzes it reaches over 90 percent. – explained the scientist.
According to Dr. Justyna Fercho, team leader from the Medical University of Gdańsk and UCK, the use of such methods is currently highly appreciated by doctors.
– We can consciously use the knowledge on the basis of which the model assesses the risk of aneurysm to diagnose patients more effectively – emphasized the researcher.
The university spokesman reminded that up to 1 in 50 adults may have an unruptured aneurysm, which in Poland means hundreds of thousands of people potentially at risk.
Currently, two main methods of securing aneurysms are used: surgical clipping, an invasive method requiring the opening of the skull (cost approximately PLN 30,000), and the less invasive endovascular embolization, which involves the introduction of materials closing the aneurysm through a thin catheter, most often platinum coils (coiling).. In the case of wide-necked or complex aneurysms, stents or flow diverters are additionally used. The cost of the procedure is 25-40 thousand. PLN depending on the material used.
In the event of an aneurysm rupture, treatment costs increase dramatically, and patients often require many years of rehabilitation and disability benefits because they cannot return to work.
– Early detection of an aneurysm based on risk assessment not only saves health and life, but also real savings for the health care system – emphasized Dr. Patryk Jasik.
The “AI-Powered Medical Software for Predicting the Likelihood of Intracranial Aneurysm” project has been qualified for the international I3HIES acceleration program, which supports the most promising innovations in the field of health care and helps develop them to the investment and commercialization stage. (PAP)
pm/bar/
