RSS
Логотип
Баннер в шапке 1
Баннер в шапке 2
2022/08/02 17:15:17

GOST R Artificial intelligence systems in clinical medicine. Part 1. Clinical evaluation

The main articles are:

2022: Approval of the national standard developed by Moscow radiologists

Moscow doctors - employees of the Center for Diagnostics and Telemedicine of the Department of Health - have developed a standard regulating the conduct of clinical trials of artificial intelligence systems. Previously, such a document did not exist for these systems. On August 2, 2022, Zdrav.Expert was informed about this by representatives of the Center for Diagnostics and Telemedicine (NPCC DiT DZM).

Московские radiologists developed GOST for testing AI in clinical medicine
Illustration: medvestnik.ru

National Standard (GOST R) "Artificial Intelligence Systems in Clinical Medicine. Part 1. Clinical Evaluation "approved and effective September 1, 2022. This was announced by the Deputy Mayor of Moscow for Social Development Anastasia Rakova.

File:Aquote1.png
"We have gained vast experience in the field of artificial intelligence in healthcare. In March 2022, the development of our doctors in this industry formed the basis of uniform national standards for the use of advanced technologies in medicine. We are moving on - Moscow specialists have developed GOST for testing artificial intelligence systems. It has already been approved and will enter into force on September 1 of this year, "the deputy mayor said.
File:Aquote2.png

According to Anastasia Rakova, the document regulates the requirements for clinical trials of neural networks. According to the proposed system, specialists will receive an accurate assessment of whether the product meets the declared characteristics of accuracy, effectiveness, and most importantly, whether it carries risks to the patient's health. Doctors from all over Russia will be guided by this standard and introduce only the best developments into practice. Thus, now almost the entire cycle of the introduction of artificial intelligence into medicine will be regulated by uniform standards developed on the basis of the experience of Moscow doctors.

The adopted GOST defines the methodology and procedure for conducting clinical trials of artificial intelligence systems, contains terms and definitions, includes indicators of the effectiveness of such systems within the framework of clinical validation and the recommended form of a report on the clinical component of trials, describes quality control of the clinical trial procedure.

Clinical evaluation involves three stages. First, analytical validation confirms the ability of artificial intelligence systems to accurately, reproducibly, and reliably process data. The evaluation of the clinical link then shows the conformity of the output of such systems to the stated functional purpose. And finally, within the framework of clinical validation, the effectiveness of the system is confirmed - the ability to produce clinically significant results. Earlier, national standards were adopted and entered into force for the introduction of artificial intelligence systems in clinical medicine - they were also developed by Moscow radiologists.