| The name of the base system (platform): | Artificial intelligence (AI, Artificial intelligence, AI) |
| Developers: | Sberbank |
| Date of the premiere of the system: | 2022/11/25 |
| Branches: | Pharmaceuticals, Medicine, Healthcare |
| Technology: | Speech technology |
The main articles are:
- Artificial Intelligence in Medicine
- Speech Recognition (Technology, Market)
- Speech technology: On the path from recognition to understanding
- Physician speech recognition
2022: MedBench Platform Introduction
Sberbank scientists presented an open Russian-language platform for solving problems in the field of artificial intelligence (AI) in medicine. Sberbank announced this on November 25, 2022. Taking into account the specifics of the subject area and the shortage of such data, this is an important project in the interests of the Russian-speaking community of researchers.
On the MedBench platform website, anyone can download marked-up datasets for building AI models. To objectively assess the quality of a model or method, the platform also allows you to check the resulting solutions on a closed (test) part of the data.
Three tasks for automatic natural language processing are already available on the platform: logic and knowledge, question-response modeling and understanding the meaning of the medical text. For each task, together with the Siberian State Medical University, the answers of assessors were prepared and the quality of such a solution was assessed. The platform website supports a public leaderboard (from the English leaderboard - leaderboard) reflecting the rating of the best proposed solutions. Before publishing, the solution code is checked for reproducibility.
{{quote 'author = said Maxim Eremenko, Vice President - Director of the Department for the Development of Artificial Intelligence and Machine Learning Technologies of Sberbank. | For many years, Sberbank has been involved in the implementation of AI in various fields. And I can say that in medicine, artificial intelligence has very promising prospects. Neural networks are already analyzing medical images faster and helping specialists assess the likelihood of possible diagnoses. But we understand that the race for artificial intelligence is in full swing, and therefore presented a specialized free platform for stimulating research and accelerated testing of AI solutions in medicine. I think the platform will be able to make important contributions to both science and practical healthcare,}}
Links
| The site content is translated by machine translation software powered by PROMT. The machine-translated articles are not always perfect and may contain errors in vocabulary, syntax or grammar. Read original article If you find inaccuracies or errors in the results of machine translation, please write to editor@tadviser.ru. We will make every effort to correct them as soon as possible. |