Students from the Landau Phystech School of Physics and Research and the Department of Innovative Pharmaceutics, Medical Engineering, and Biotechnology (BFK) at MIPT have developed an innovative neural network called MeMo (Meeting Moments), designed to automate the filling of medical documentation. This system helps doctors in real-time to recognize voice, record patient appointments, as well as fill out medical records, referrals to specialists, and write prescriptions.
MIPT claims that the use of MeMo reduces the time doctors spend on non-core tasks by more than a third. Automating these processes can increase the number of patients a doctor can see per day by 20%. According to the project's author, Maria Protopopova, up to 40% of a doctor's time is spent on reporting and filling out documents. The new approach helps specialists focus on interacting with patients, leaving the work with medical records to algorithms.
The MeMo project also focuses on data security: all information is processed on the clinic's servers and does not leave its boundaries, which ensures compliance with legislation on the protection of personal data and medical confidentiality.
The project won the MIPT accelerator "Phystech.Idea" and received grant support from the Foundation for Assistance to Innovations in the amount of 1.2 million rubles. The team plans to complete work on the local version of the application by the end of August and conduct pilot testing in one of the clinics.
Read materials on the topic:
To help doctors: Sber is creating a medical assistant GigaPevt
In Russia, they came up with how to find a hospital anywhere in the world through an application
