The Russian clinic implemented a neuronet of the domestic developer for the description of x-rays

In the Russian private clinic "Meditsina" the neuronet for the description of x-rays developed by Care Mentor AI company is implemented. It is the unique project for the Russian medicine: instead of 20 minutes which are spent by the doctor for the description of the x-ray the artificial intelligence performs this work in only 3 seconds. So by the time of when the patient puts on after the conducted research, the description of the picture and the preliminary diagnosis will be already ready.

The neuronet is developed for the description of x-rays

As the neuronet will recognize aberrations whether it is possible to trust it what probability of an error and what it gives except saving of time the academician Grigory Roytberg, the president of Meditsina clinic explained:

The artificial intelligence which we began to use in clinic for the description of the picture has the strike accuracy of 85-90 percent. It is better, than the average doctor! I think, by 2020 at us in clinic not the person, and the computer will be engaged in diagnostics considerably. It will give the chance to reduce rates of radiologists and to considerably reduce research cost. Our task to save the doctor from routine work he more than forces and time could spend for what the machine cannot do.

Before giving start to test use of the program, more than 200,000 x-rays were analyzed and this work is continued. The complexity is that each picture described by the program carefully is rechecked by radiologists. Specialists of Meditsina company take part in the project. In the near future it is going to implement the description artificial intelligence of KT and MRT-researches.

Except the description of pictures, in Medicine even more than 100 integrated information systems including the program for control of prescription of medicines of "Smart Assistant" are implemented. The software allows to control compatibility of the drugs appointed to the patient by different specialists. It is known that identical compound components can enter different medicines, the program does not allow to exceed the recommended doses of such components. Moreover, the program considers age of the patient, a floor, medicine which he took in the last three months whether transaction and a lot more factors which the doctor can not provide are necessary to the patient in the near future. In case of identification of some deviations, the program displays warning to which the doctor will be able to react, and in case of critical errors work in the program will be blocked.

Software it is developed by Digital Worlds company and already showed good results - errors of medicinal therapy decreased practically to zero.