Yandex B2B Tech, together with the Yandex School of Data Analysis and St. Petersburg State Pediatric Medical University, has developed the world’s first AI solution for assessing brain development in infants under 12 months of age. The neural network automates MRI analysis, cutting processing time from several days to just minutes.

MediCircle spoke to Yulia Busygina, Healthcare Project Manager, Yandex B2B Tech, an MD and a MedTech innovator, to get an in-depth understanding of this innovation and what it means to the healthcare community.

Yandex developed its open-source AI tool to address one of healthcare's most pressing challenges — early detection of neurological disorders in infants. The system analyses MRI scans to identify early markers of cerebral palsy with over 90% accuracy, offering clinicians faster and more objective assessments of brain development. The motivation stemmed from our broader mission to apply AI expertise to socially significant problems — leveraging technology to deliver solutions with tangible, real-world impact. We aim to create tools that are not just for individual projects but can be adapted and scaled to different areas like healthcare, pharmaceuticals, insurance, and other industries.

Yandex partners with diverse organizations, including public institutions, to help them address the specific challenges they face. This case was no exception: in collaboration with St. Petersburg State Pediatric Medical University, we tackled a key problem — lengthy MRI analysis for infants caused by the difficulty of identifying gray and white matter in developing brains. But now our AI solution provides doctors with an assistive tool that speeds up diagnosis, reduces uncertainty, and helps them make better-informed decisions.

By open-sourcing the model, Yandex aims to empower global researchers and hospitals to validate, adapt, and improve the system for their own populations while also enabling them to contribute to its ongoing development and technological refinement.

AI isn't just automating tasks in healthcare — it's reshaping how care is defined, delivered, and scaled. Yandex envisions AI moving from augmentation to transformation: systems that detect subtle disease markers earlier, personalise treatment pathways, and democratise access across geographies. The recent open-source infant brain development tool is a case in point.

In India's context, this means AI can help bridge gaps between urban centres and remote or underserved regions where specialist diagnostics are scarce. Yandex's strategy emphasises open platforms, data-sharing, and cloud-based deployment — enabling hospitals, researchers, and public health agencies to adapt solutions locally. Looking ahead, the industry sees the potential for AI to contribute to areas like continuous monitoring (via imaging or multimodal sensors), real-time decision-support, and personalised intervention plans—making healthcare more proactive, efficient, and equitable.

The Yandex open-source AI tool for detecting early signs of cerebral palsy in infants demonstrates over 90% accuracy, verified through extensive validation on MRI scans from the internal evaluation data of St. Petersburg State Pediatric Medical University. The model was trained on diverse neuroimaging data to ensure consistent performance across different imaging equipment, protocols, and patient demographics.

Because it is open-source, clinicians and researchers can retrain or fine-tune the model using local datasets, making it adaptable to different healthcare systems — including emerging markets such as India where MRI standards and population diversity can vary.

This collaboration marks a major leap in AI-driven pediatric diagnostics. By combining the computational infrastructure and AI expertise of Yandex B2B Tech, the research depth of Yandex School of Data Analysis, and the clinical expertise of St. Petersburg State Pediatric Medical University, the team has created the world's first AI tool capable of assessing infant brain development via MRI scans with 90% precision.

Traditionally, analyzing such scans could take a radiologist several days. The new neural network reduces that process to just minutes, enabling early detection of potential neurodevelopmental issues such as cerebral palsy. (Yandex Press Release, 2025)

The partnership demonstrates how alliances of academics, clinicians, and technology companies can close the diagnosis gap and make advanced neuroimaging accessible globally. In countries like India, where pediatric neurologists are often stretched thin, such AI-powered tools can support earlier interventions, reduce diagnostic backlogs, and improve long-term developmental outcomes for infants.

Yandex envisions a future where AI acts as a continuous partner in healthcare — not just a diagnostic tool but a decision-support ecosystem spanning prevention, detection, and personalized care. Future work focuses on multimodal learning, generative AI, and AI agents. 

Building on successes like its open-source infant brain analysis model, Yandex aims to expand AI applications across imaging, digital pathology, and clinical data interpretation, ensuring faster, more equitable access to quality healthcare. The company sees significant potential for AI in high-impact fields such as oncology diagnostics and treatment, as well as in safeguarding the health of expectant mothers and infants.

Moving forward, potential collaborations with academic and healthcare partners globally, including in markets like India, could pave the way for co-developing scalable, locally validated solutions.

Ultimately, Yandex's mission is to democratize medical AI — making powerful, transparent, and ethically designed tools freely available to healthcare ecosystems worldwide.

More information available on https://yandex.cloud/en/social-tech