Window into the Body: Scientists Develop Neural Network to Detect Risk of 15 Diseases from Retinal Images
Russian universities, with the participation of HSE University, Sber, and Z-union, have developed a neural network that can simultaneously assess the risk of 15 types of pathology from retinal photographs, including not only eye diseases but also cardiovascular conditions. The AI system can help clinicians detect potentially concerning changes at an early stage, identify signs reflecting the condition of retinal blood vessels, and determine whether a patient may need further examination. The paper has been published in Frontiers in Medicine.
The retina is sometimes described as a window into the body. It allows clinicians to observe blood vessels and nerve tissue without surgery and detect not only vision problems but also signs of cardiovascular disease, diabetes, hypertension, atherosclerosis, and other conditions. In recent years, artificial intelligence systems have increasingly been used to diagnose a wide range of diseases, helping clinicians analyse retinal images more quickly and accurately and identify signs of various pathologies.
Most existing medical neural networks are trained to detect signs of a single disease or a small group of related conditions. For example, one algorithm may assess the risk of diabetic retinopathy based on changes in retinal blood vessels, while another may detect signs of glaucoma by analysing the condition of the optic nerve. To screen for multiple diseases, clinicians typically need to use several specialised models. The new solution developed by Russian scientists takes a different approach: it analyses a single retinal image and simultaneously assesses the likelihood of 15 different pathologies.
To develop the system, Russian scientists used deep learning methods. The algorithm was trained on more than 20,000 specially collected fundus images (20,351 in total), learning to detect even subtle changes in blood vessels, the optic nerve, and other retinal structures. One of the main challenges was recognising rare diseases, for which only a limited number of medical images are available.
The researchers addressed this problem by deliberately presenting the neural network with images of rare pathologies more frequently during training, slightly modifying each image, for example by changing its brightness or rotating it. In addition, the learning algorithm was configured to assign greater weight to errors in detecting rare diseases than to errors involving common conditions. As a result, the neural network learned to detect not only common but also rare pathologies.
On the test data, the system demonstrated high accuracy, with the model performance metric (ROC AUC) ranging from 0.95 to 0.99 across different diseases. However, real-world medical practice is far more diverse than the data used to train the neural network; therefore, as expected, its performance was significantly lower when the system was first tested on real clinical cases.
Andrey Savchenko
‘We trained the neural network to recognise a wide range of pathologies. Our goal is to help prevent early signs of disease from being overlooked, when treatment is often most effective. Although the model’s performance has improved significantly for several rare pathologies, detecting rare diseases remains the most challenging task and requires collecting more data. While our neural network detects signs in retinal images that may indicate an increased risk of disease, it does not make a diagnosis. The final decision is always made by a medical professional,’ says co-author Andrey Savchenko, Leading Research Fellow at the Laboratory for Theoretical Foundations of AI Models of the AI and Digital Science Institute at HSE FCS and Scientific Director at Sber AI Lab
For now, the neural network remains a research project. The next stage will involve large-scale clinical trials with patients at different clinics. If these trials confirm the system’s effectiveness, artificial intelligence could become a reliable tool for clinicians, helping them detect a wide range of diseases at an early stage.
The study was supported by a grant for research centres in the field of AI provided by the Ministry of Economic Development of the Russian Federation and implemented at HSE University.
See also:
Road Injuries Leading Cause of Death Among Men Aged 10 to 39
Worldwide, road injuries are the leading cause of death among males aged 10–39. An international team of researchers reached this conclusion as part of the Global Burden of Disease Study 2023, analysing data from 204 countries between 1990 and 2023. Their findings have been published in The Lancet Public Health, with HSE University Professor Vasily Vlassov listed among the collaborators.
Sustainable Management and Business Value: HSE Economists Examine the Relationship in the Russian Market
In the Russian market, sustainable development increases business value primarily when it becomes part of a company’s corporate strategy. This is the conclusion reached by researchers from HSE University and their international colleagues after analysing the management practices of 152 publicly listed Russian companies. The study has been published in the journal Business Strategy and the Environment.
HSE Researchers Find That Doctors’ Ratings Are More Persuasive to Patients Than Experience
HSE University researchers have investigated how doctors’ professional experience and patient ratings affect patients’ trust in medical information. They found that people are more likely to be persuaded by the opinions of highly rated doctors, while paying less attention to their years of experience. The findings have been published in the journal Frontiers in Human Neuroscience.
Users Lose Out from Restrictions on Personal Data Collection and Processing
An economist at HSE University used a microeconomic model to show that excessively strict restrictions on the collection and processing of personal data can do users more harm than good. The article has been published in Voprosy Ekonomiki.
HSE Researchers Show How Congenital Motor Disorders Affect Brain Development
Researchers from HSE University’s Institute for Cognitive Neuroscience have synthesised the findings of their previous studies on brain development in children with obstetric brachial plexus palsy and arthrogryposis. Their analysis shows that impaired motor function in early childhood not only limits children’s motor experience but also affects memory, categorical thinking, and information processing. The study has been published in Frontiers in Psychology.
AI Users Earn Up to 41.8% More Than Non-Users
Research conducted by economists at HSE University has revealed a significant correlation between the regular use of GenAI in the workplace and higher pay among Russian employees. The study found that individuals who frequently use GenAI in their professional activities earn notably more than those who reject these new tools or resort to them occasionally. The salary premium for highly qualified specialists reaches 41.8%. The article was published in the Voprosy Ekonomiki journal.
Personal Interest in Doctoral Thesis Topic Most Important for Confidence in Successful Defence
A researcher at HSE University analysed data on 1,539 doctoral students from 161 Russian universities to identify which features of a thesis topic are associated with academic success and engagement. The most important factor was found to be personal interest in the research topic, which was associated with almost all key aspects of doctoral programme experience—from engaging with the academic supervisor to research activity and confidence about successfully defending the thesis. The findings have been published in Higher Education.
Researchers Develop Methodology to Assess the Quality of Legal Representation in Criminal Proceedings
Having a good defence attorney in criminal proceedings can largely determine whether a defendant retains their freedom, health and good name. Researchers at HSE University propose a method for predicting an attorney’s performance based on the outcomes of their previous cases. The methodology takes into account the severity of the charges, the complexity of the cases, and the most likely outcome, drawing on judicial statistics.
When Pictures Hinder Understanding: Illustrations May Impede Learning of Abstract Ideas
Illustrations can help remember specific actions but do not always make abstract ideas easier to learn. Researchers from HSE University and Humboldt University compared how people learn from texts with different levels of abstractness. They found that participants remembered illustrations better and performed better on related tasks after reading a multimedia text about yoga asanas than after reading an abstract text about the Nash equilibrium. The findings could help improve the selection of illustrations for educational and informational materials. The study has been published in Learning and Instruction.
HSE Researchers Present Study on Neural Network Robustness in Video Analysis at ChinaMM 2026
Researchers from HSE University presented a study at the international ChinaMM 2026 conference on how video transmission distortions affect the performance of neural networks. The authors proposed a new approach to testing the robustness of such models under conditions that closely resemble the real-world use of video services.