The accuracy of the voice input service in the radiation diagnostics departments in Moscow reached 98%

2022: The accuracy of the voice input service in the radiation diagnostics departments in Moscow reached 98%

The accuracy of the voice input service in the radiation diagnostics departments in Moscow reached 98%. This was announced on July 8, 2022 by the director of the Center for Diagnostics and Telemedicine of the Moscow Department of Health (DZM) Yuri Vasiliev.

To fill in documents by voice artificial intelligence in the digital healthcare platform, a voice assistant created by the CST group of companies is used. By Voice2Med July 2022, Voice2Med works in medical institutions in 65 regions of the country and is available for doctors of eight specialties, the general director said. CST Dmitry Dyrmovsky

According to Yuri Vasiliev, radiation diagnostics departments in Moscow use a voice input system to create conclusions. During the work with the help of this service, more than 160 thousand medical documents were filled out (by July 8, 2022). On average, about 10 thousand such documents are filled out monthly.

For the first half of 2022, Moscow radiologists using voice input filled out 8% more protocols than a year earlier. Thanks to the technology, the time to fill out the protocol is reduced by more than 20%, and specialists can focus on an even more thorough study of the research results, Vasiliev noted.

When examining patients or conducting a study, the doctor uses a headset to dictate information that is decrypted and automatically transferred to the open protocol of the medical information system

The first large-scale introduction of a stationary version of the voice assistant Voice2Med was implemented in Moscow, which became possible thanks to a single digital healthcare platform developed by the Moscow City Social Development Complex and the Department of Information Technologies.^[1]

2020: Automation of filling out medical records in Moscow

The group of companies CST (part of the ecosystem) Sberbank optimizes the work of medical institutions, the work of radiation diagnostics doctors using intelligent ones. speech technologies This was announced on June 19, 2020 by Sberbank.

The solution is based on Voice2med, an artificial intelligence-based product created by the CST group from scratch. Voice2med allows you to dictate information for maps, protocols and other documents through a special microphone. The system recognizes all medical terms and expressions, and the quality of speech recognition is 97-98%. During the study, the doctor dictates the text, which is recognized in real time and automatically transferred to the completed protocol in the medical information system. The solution allows you to save medical workers from routine, focus on research.

The pilot project for the introduction of voice input of conclusions was carried out in close cooperation with the Department of Information Technologies of the city of Moscow, the infrastructure was studied, the optimal deployment of the system was determined. The Moscow Department of Health carried out serious methodological work, which made it possible to provide a full-fledged cycle of training for medical personnel in specialized classrooms. According to the results of a large-scale pilot project, the CST Group took into account the accumulated experience, finalized the solution, as a result, the quality of speech recognition reached the highest value.

Sergei Morozov, Chief Specialist in Radiation and Instrumental Diagnostics of the Department, health care Moscow Director of the Center for Diagnostics and: telemedicine

{{quote 'This technology can begin to be included in the training of current resident doctors, so that from the very beginning they get used to the fact that you can simply take and dictate the text of the conclusion protocol. Preparation for this from the very basics of the profession is one of the criteria that the tool will be in demand, it will be used. Accordingly, then it will begin to scale. I think this will further contribute to what has already begun to happen: standardization of medical documentation, exemption of the doctor and time for a more detailed study of diagnostic images, optimization of the doctor's work, reduction of the time for preparing research protocols. Specialists will have more time to analyze diagnostic images and medical documents of patients. }}

Dmitry Dyrmovsky, CEO of Speech Technology Center Group:

When medicine is under enormous pressure, modern technologies and products based on artificial intelligence come to the rescue, and Voice2med is one of them. The solution allows you to save medical workers from routine, save more than 20% of the time on filling out protocols, improve their quality, and most importantly - focus on research. The peculiarity of the project is close interaction with the Information Technology Department, during which it was possible to qualitatively test and integrate the solution on a developed IT infrastructure and with the help of a ready-made centralized complex. In addition, the Moscow Department of Health provided invaluable methodological support in the project, ensuring high-quality training of medical personnel. We hope to develop our projects in order to ensure a high level of quality of service and adequate technological support for medicine, one of the key industries.

The greatest efficiency in using voice input is achieved when describing studies of computer, magnetic resonance imaging and digital radiography. This is because short patterns of fluorography and mammography protocols fill up faster with a few mouse clicks. The Center for Diagnostics and Telemedicine Technologies notes that the introduction of a voice filling system for medical protocols can become an effective tool not only for radiologists, but also for surgeons, endoscopists and forensic doctors, and in the future - also for therapists and neuropathologists.