At Sechenov University they learned to assess the risks of seven types of cancer… » Medvestnik


Sechenov University has developed a cancer diagnostic system using neural networks. Artificial intelligence calculates risks based on the results of an analysis of 14 tumor markers.

Scientists at the Institute of Personalized Oncology at PMGMU named after. THEM. Sechenov have developed a medical decision support system (MDS) OncoPro – it is capable of assessing the risks of developing seven oncological diseases using one blood sample, the university press service reported on October 4. The system is based on a neural network that analyzes the results of the analysis for 14 tumor markers.

OncoPro uses neural networks trained on data from more than 1 thousand patients with various types of cancer. Based on the results of an analysis of 14 tumor markers, the system calculates the patient’s likelihood of having cancer of the lung, intestine, bladder, breast, kidney, ovary or prostate (depending on gender), said the director of the Institute of Personalized Oncology Marina Sekacheva.

OncoPro can be accessed through a cloud platform. The doctor needs to enter the results of tumor marker tests, and then the system calculates the risks for each type of cancer. Based on these data, the specialist makes a decision on further examination.

OncoPro is suitable for use in medical examinations – the medical university believes that in the future the neural network can be integrated into a medical information system, and the results will be included in the card from the laboratory.

Earlier it became known that in Moscow a neural network was trained to detect 10 pathologies at once on one CT image. The algorithms mark areas of possible pathologies with color clues on the medical image. A neural network can detect pathologies at an early stage, when they may be invisible to the doctor.

Despite the fact that half of Russians believe that artificial intelligence can be used in diagnosis and treatment, only one in six is ​​ready to entrust their own health to a neural network. At the same time, three-quarters of the population would not want such technologies to replace the doctor, MV wrote. At the same time, the authorities set a course for the robotization of medicine: at the beginning of 2023, the Ministry of Health instructed the regions to urgently implement at least one AI-based solution in medical organizations. Last fall, the President demanded that special attention be paid to the introduction of such technologies in the healthcare sector, especially in primary care. Vladimir Putin.



Source link