Artificial intelligence in the Moscow region has checked over a million medical prescriptions.
The Moscow region continues to actively implement artificial intelligence technologies in the healthcare system. Since February 2026, an AI-based digital assistant has been helping local doctors, and during this time it has already checked over one million medication prescriptions. This is a significant step in automating routine processes that directly affects the quality of medical care.
How the verification system works
The developed algorithm operates in automatic mode and analyzes each prescription against 15 key criteria. Among them are drug compatibility, patient age and gender, as well as potential risks of overdose or exceeding recommended treatment durations. Notably, the system is active both during in-person appointments and during telemedicine consultations where a prescription needs to be extended or adjusted.
The technology adds an additional layer of accuracy when choosing a treatment plan. However, as emphasized by the regional Ministry of Health, the final decision always remains with the doctor. AI acts as a reliable assistant that signals potential risks before the patient receives the medication, but does not replace the specialist's clinical thinking.
AI in Russian medicine: a large-scale trend
The Moscow region is far from the only region where neural networks are being integrated 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, for example, 200 medical AI services were tested over six years, of which 67 are already operating in hospitals. More than 2,000 clinics from 75 regions have connected to the city platform "MosMedAI," including radiology diagnostic algorithms.
Major technology players are also entering the market. At the end of July, Yandex registered LLC "Yandex Med" to develop medical software. Their digital assistant transcribes conversations between doctors and patients, searches the knowledge base, and prepares a brief summary of the medical history. The use of neural networks extends beyond clinics — recently, they were used for the first time to assemble complete bacteriophage genomes, of which 16 samples proved viable in the laboratory.
My view: The implementation of AI in medicine is not just a trend, but a necessity for reducing the burden on doctors and minimizing human errors. However, the key challenge remains the same: ensuring algorithm transparency and maintaining patient trust. Technology should remain a tool, not a replacement for professional judgment.