Sber’s neural network model GigaChat MAX successfully passed the tests and solved the situational issues of primary accreditation in the specialty “General Medicine” on the basis of the accreditation center of the First Moscow State Medical University named after IM Sechenov from the Ministry of Health of Russia (Sechenov University). reported the press service of Sber.
Commenting on the test results of the model, Sergei Zhdanov, director of the Sber Health Industry Center, noted that this is an important step towards the practical use of artificial intelligence in healthcare.
“GigaChat MAX continues to learn and get smarter to bring value to people. “We will develop GigaChat MAX in individual specialties,” he said.
The testing consisted of two stages. The neural network model answered 80 questions in the first one and solved situational problems in the second one.
According to the test results, GigaChat MAX successfully answered 83% of the questions (70% pass rate) and provided 20 correct answers to situational problems (at least 17 questions pass rate).
According to Andrei Svistunov, the first vice-rector of Sechenov University, such tools will increase the accuracy of the doctor’s decisions.
“GigaChat MAX will save time and reduce routine workload by helping the doctor make decisions,” he said.
Let us recall that in February 2024, the GigaChat neural network model was one of the first in the world to pass the final exam for sixth-form students required to obtain the general practitioner qualification. Every medical school graduate must also undergo accreditation, which tests more in-depth knowledge. To achieve this, GigaChat MAX has also been trained by hundreds of doctors using a significant amount of medical training material.
What are you thinking?
Source: Gazeta
Jackson Ruhl is a tech and sci-fi expert, who writes for “Social Bites”. He brings his readers the latest news and developments from the world of technology and science fiction.