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:
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.
HSE Researchers Train Neural Network to Predict Protein–Protein Interactions More Accurately
Scientists at the AI and Digital Science Institute of the HSE Faculty of Computer Science have developed a model capable of predicting protein–protein interactions with 95% accuracy. GSMFormer-PPI integrates three types of protein data (including information about protein surface properties) to analyse relationships between proteins, rather than simply combining datasets as in previous models. The solution could accelerate the discovery of disease molecular mechanisms, biomarkers, and potential therapeutic targets. The paper has been published in Scientific Reports.
How Neural Networks Detect and Interpret Wordplay: New Insights from HSE Researchers
An international team including researchers from the HSE Faculty of Computer Science has presented KoWit-24, an annotated dataset of 2,700 Russian-language Kommersant news headlines containing wordplay. The dataset enables an assessment of how artificial intelligence detects and interprets wordplay. Experiments with five large language models show that even advanced systems still make mistakes, and that interpreting wordplay is more challenging for them than detecting it. The results were presented at the RANLP conference; the paper is available on Arxiv.org, and the dataset and the code for reproducing the experiments are available on GitHub.
Human Intuition Proves Stronger than Algorithms: Game Theory Tournament Held at HSE University in Perm
Researchers from the International Laboratory of Intangible-driven Economy (Perm) and the HSE Laboratory of Sports Studies, together with mathematician and science populariser Alexey Savvateev, organised a game theory tournament entitled ‘The Election Race.’ Participants competed both against one another and against artificial intelligence. For now, humans have managed to gain the upper hand and propose more effective strategies.
Educational Programmes on Robotics and Neural Network Technologies Launch at HSE University’s Faculty of Computer Science
Every year, in response to IT industry demands, the Higher School of Economics Faculty of Computer Science launches new educational programmes while updating existing ones. In 2026, the faculty introduced Bachelor’s and Master’s degree programmes in robotics for the first time.
‘Policymakers Should Prioritise Investing in AI for Climate Adaptation’
Michael Appiah, from Ghana, is a Postdoctoral Fellow at the International Laboratory of Intangible-Driven Economy (IDLab) at HSE University–Perm. He recently spoke at the seminar ‘Artificial Intelligence, Digitalization, and Climate Vulnerability: Evidence from Heterogeneous Panel Models’ about his research on ‘the interplay between artificial intelligence, digitalisation, and climate vulnerability.’ Michael told the HSE News Service about the academic journey that led him to HSE University, his early impressions of Perm, and how AI can be utilised to combat climate change.
AI Overestimates How Smart People Are, According to HSE Economists
Scientists at HSE University have found that current AI models, including ChatGPT and Claude, tend to overestimate the rationality of their human opponents—whether first-year undergraduate students or experienced scientists—in strategic thinking games, such as the Keynesian beauty contest. While these models attempt to predict human behaviour, they often end up playing 'too smart' and losing because they assume a higher level of logic in people than is actually present. The study has been published in the Journal of Economic Behavior & Organization.