AI assistant in Moscow region polyclinics: over a million prescriptions checked by neural network in six months
An AI-powered digital assistant integrated into the healthcare system of the Moscow region has proven its effectiveness: in the first six months of operation, the algorithm checked over one million medical prescriptions. This is a significant step toward automating the quality control of medical care in the region.
The system was launched in February 2026 and has since been actively used both in in-person appointments and within telemedicine consultations. The main task of the AI is to verify the correctness of prescriptions at the moment they are issued, especially when an existing prescription needs to be extended or adjusted.
How the verification algorithm works
In automatic mode, the neural network evaluates each prescription against 15 key criteria. These include drug compatibility, compliance with the patient's age and gender, as well as potential risks of overdose or exceeding recommended treatment durations. This approach allows errors to be identified at an early stage, before the patient even receives the medication.
It is important to emphasize that the technology does not replace the doctor, but rather adds an additional layer of accuracy when choosing a treatment plan. The final decision always remains with the specialist. According to Lyudmila Bolataeva, Deputy Governor of the Moscow Region, the tool helps select the optimal therapy option, working both in an in-person format and during remote consultations.
AI in Russian medicine: the trend is gaining momentum
The Moscow region is not the only area where neural networks are being introduced into healthcare. Similar projects are being launched at the federal level and in individual regions, where AI takes on routine checks and data processing. In Moscow, 200 medical AI services have been tested over six years, 67 of which are already operating in hospitals. More than 2,000 clinics from 75 regions have connected to the city platform "MosMedAI," which provides access to radiology diagnostic algorithms based on imaging.
Yandex is also eyeing this market. At the end of July, the company registered LLC "Yandex Med" to develop medical software. The digital assistant transcribes conversations between doctors and patients, searches for relevant data in the knowledge base, and prepares a brief summary from the medical history. The use of neural networks extends beyond clinics as well — for the first time, they were used to assemble complete genomes of bacteriophages, viruses that infect bacteria. 16 of these samples proved viable in the laboratory.
My view: The integration of AI into the drug prescription process is not just a passing trend, but a systemic solution that reduces the burden on doctors and minimizes the human factor. Given the scale of checking a million prescriptions, we can speak of a high level of trust in algorithms from the medical community. However, the key challenge remains the same — ensuring transparency in AI operations and keeping responsibility for the final decision with humans. The market is clearly moving toward a hybrid "doctor + algorithm" model, and the Moscow region is emerging as one of the flagships in this regard.