Neural Network Developed at HSE Campus in Perm Will Determine Root Cause of Stroke in Patients
Specialists at HSE Campus in Perm and clinicians at Perm City Clinical Hospital No. 4, have been collaborating to develop a neural network capable of determining the root cause of a stroke. This marks the world's first attempt to create such a system, the developers note.
According to Sofya Kulikova, Senior Research Fellow at the Centre for Cognitive Neuroscience, HSE Campus in Perm, specialists at her centre have been collaborating with their colleagues at City Hospital No. 4 since 2019. During this period, they have co-authored multiple papers and hosted two workshops on employing various tools for data analysis in neurology.
They began collaborative efforts to develop a new AI tool for identifying the cause of strokes about a year ago, after winning a competition for Research and Study Groups.
Identifying the cause of a stroke is a crucial task for preventing any reoccurrences, which tend to be even more severe than primary strokes, according to Kulikova. A substantial amount of data is required for designing neural network-based tools capable of handling such a task.
'Therefore, colleagues from the clinic have been actively collecting and marking up data, while also involving their peers from other regions in the study. Simultaneously, our group has been developing and testing a tool designed to automatically identify not only the location of the lesion but also the potential underlying cause of the stroke using an MRI image.'
Data for the project is submitted by physicians from various Russian clinics, and over 1,000 images have so far been uploaded to the database. These images are used to train the neural network to identify the most probable cause of a stroke in each instance, the Perm Region Ministry of Health told TASS.
A stroke is an acute interruption of blood supply to the brain, which can be either ischemic or haemorrhagic. In an ischemic stroke, blood vessel blockage by a thrombus or atherosclerotic plaque impedes blood flow to the brain, resulting in oxygen deprivation and subsequent neuronal death. In a haemorrhagic stroke, a cerebral vessel ruptures, causing bleeding into surrounding tissues, which also results in neuronal death. Ischemic strokes are more likely to cause severe forms of disability, such as impaired speech, memory, coordination, and motor functions, while haemorrhagic strokes often result in death. Additionally, there are transient ischemic attacks, often referred to as micro-strokes. They occur when blood flow in the cerebral arteries is briefly interrupted, leading to focal brain lesions, but the symptoms typically dissipate quickly. As a result, patients often disregard the symptoms until the condition becomes critical. According to the World Health Organization (WHO), stroke ranks among the top ten leading causes of death worldwide. Furthermore, half of stroke patients experience recurrent strokes, with up to 15% experiencing them up to four times.
According to the WHO, 75% of strokes are avoidable through timely prevention measures combined with medical supervision. That is why identifying the underlying cause of the condition is so crucial. To achieve this, each patient hospitalised with an ischemic stroke undergoes a comprehensive set of studies, including CT or MRI of the brain, visualisation of cerebral vessels, ultrasound of the vessels in the neck, heart, arteries, and veins of the lower extremities, as well as electrocardiography and Holter ECG monitoring.
However, according to Professor Alexey Kulesh, Head of the Neurology Department at Clinical Hospital No. 4, in 40% of cases, these studies do not provide a clear understanding of the underlying cause of the disease. The percentage of recurrent strokes does not decrease, indicating that the underlying cause of the acute pathology has not been determined, resulting in ineffective preventative therapy being prescribed.
Until now, there hasn't been a systematic analysis, recognised by medical practitioners worldwide, correlating the shape of the lesion with the cause of stroke. This inspired the idea of creating a database of stroke lesion images and using AI to group them according to common characteristics.
Alexey Kulesh
'Certain patterns are evident, and artificial intelligence can already provide insights with a high degree of probability regarding the cause of a particular stroke. Certainly, the standard examination of a patient with an ischemic stroke will be conducted by default. However, with the assistance of a neural network, we will be able to place a diagnostic emphasis in the most probable area, enabling us to do so more efficiently. During a single hospital stay, the patient will receive treatment, rehabilitation, and recommendations for preventing recurrent strokes.'
Currently, there is an experimental version of the tool that has been tested by Kulikova and her colleagues 'on open data related to another brain disease, with very promising results.' Some of these results were presented at the Sixth International Cognitive Neuroscience Forum in Yekaterinburg. Experts are hopeful that after completing data collection and testing the tool on its own database, it will prove valuable for a wide range of medical practitioners.
See also:
Neural Network Maps as a Method for Constructing Mathematical Models
Scientists from HSE University–Nizhny Novgorod and the Institute of Physics Belgrade, Serbia, are jointly exploring the application of machine learning techniques and neural networks to the study of nonlinear dynamics. Natalya Stankevich, Leading Research Fellow at the Laboratory of Topological Methods in Dynamics of the Faculty of Informatics, Mathematics, and Computer Science at HSE University–Nizhny Novgorod, spoke to the HSE News Service about this international project.
HSE Scientists Develop Method to Compress Large Language Models Without Losing Quality
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a new compression method for large language models such as GPT and LLaMA that reduces their size by 25–36% without additional training or significant loss of accuracy. This is the first approach to use mathematical transformations—specifically, rotations of model weights—to make models more amenable to compression with structured matrices. The study results have been published in ACL Findings 2025. The code is available on GitHub.
HSE Scientists Train Neural Network to 'Hear' Faults in Electric Motors
Researchers at the AI and Digital Science Institute of the HSE Faculty of Computer Science have developed a new method—the Signature-Guided Data Augmentation (SGDA) framework—that achieves 99% accuracy in motor fault detection and 86% accuracy in fault classification. The application of this approach can reduce industrial equipment repair costs, minimise downtime, and improve production safety. The study results have been published in Engineering Applications of Artificial Intelligence.
HSE Graduate’s AI Project Wins at TECH & AI Awards
Daria Davydova, graduate of the HSE Graduate School of Business and Head of the AI Implementation Unit at the Artificial Intelligence Department of Alfa-Bank, received a prize at the TECH & AI Awards. She was awarded for the best AI solution for optimising business processes. The winners were determined as part of the VII Russian Summit and Awards on Digital Transformation (CDO/CDTO Summit & Awards).
New Neural Network for Science and Innovation Being Developed at HSE University
HSE researchers are training large language models (LLMs) to understand Russian-language scientific terminology while improving their energy efficiency. The adapted model runs 2.7 times faster and requires 73% less memory than the original open model, allowing it to operate on more affordable hardware. The programme has passed state registration.
HSE FCS Researchers Showcase AI and Bioinformatics Breakthroughs at ICLR 2026
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science, along with students from the AI360: Artificial Intelligence Engineering track of the Applied Mathematics and Information Science bachelor’s programme, took part in ICLR, one of the world’s most prestigious international conferences on machine learning and representation learning. This year’s event was held in Rio de Janeiro, Brazil.
The Future of Cardiogenetics Lies in Artificial Intelligence
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a program capable of analysing regions of the human genome that were previously inaccessible for accurate interpretation in genetic testing. The program adapts large generative AI (GenAI) models for cardiogenetics to predict how specific mutations affect the function of individual genes.
Teaching a Machine to Read the Past: HSE Develops Neural Network to Decipher Manuscripts
Diaries and letters are an invaluable resource for humanities scholars. But what can be done when the text is impossible to read? At the HSE Faculty of Humanities, this challenge has been translated into the language of mathematics: a team of philologists, historians, and machine learning specialists has created an information system that not only recognises illegible handwriting but also helps analyse archival content.
HSE and Yandex Propose Method to Speed Up Neural Networks for Image Generation
A team of scientists at HSE FCS and Yandex Research has proposed a method that reduces computational costs and accelerates text-to-image generation in diffusion models without compromising quality. These models currently set the standard for text-to-image generation, but their use is limited by high computational loads, the company said in a statement.
A Trap for the Advanced Student: How to Break the Habit of Blindly Trusting Neural Networks
Andrei Ternikov, Associate Professor at the St Petersburg School of Economics and Management at HSE University–St Petersburg, has developed a method for conducting online exams that significantly limits students’ ability to use ChatGPT and other AI models to obtain correct answers. Andrei Ternikov spoke to the HSE News Service about his approach—which won the HSE University Autumn Educational Innovation Competition, received an Alfa Future grant, and was presented at an international conference in Japan.