Analysing Genetic Information Can Help Prevent Complications after Myocardial Infarction
Researchers at HSE University have developed a machine learning (ML) model capable of predicting the risk of complications—major adverse cardiac events—in patients following a myocardial infarction. For the first time, the model incorporates genetic data, enabling a more accurate assessment of the risk of long-term complications. The study has been published in Frontiers in Medicine.
Coronary artery disease (CAD), or ischaemic heart disease (IHD), is a condition characterised by insufficient blood and oxygen supply to the heart from narrowing or blockage of the coronary arteries. It is typically caused by plaques composed of fats and cholesterol that build up on the walls of blood vessels. Coronary heart disease may present as angina (chest pain), myocardial infarction (heart attack), or other problems.
According to WHO, ischaemic heart disease is the world’s biggest killer, responsible for 13% of the total deaths. Therefore, it is crucial to prescribe appropriate treatment to minimise the risks of complications and recurrences. Researchers at HSE University developed a model capable of predicting the probability of major adverse cardiac events following a myocardial infarction.
The scientists analysed data from patients admitted with myocardial infarction to the Surgut District Centre for Diagnostics and Cardiovascular Surgery between 2015 and 2024. Upon admission to the emergency department, medical researchers (cardiologists) explained the main points of the study protocol to the patients and obtained their informed consent to participate. The cardiologists then assessed the condition of the coronary arteries supplying the heart and based on their evaluation, either balloon angioplasty with stenting or coronary artery bypass grafting were performed. All patients received guideline-based therapy, including RAAS-blockers, beta-blockers, statins, and dual antiplatelet therapy. The information was documented in the patients' hospital medical records. For each patient, standard clinical measurements were taken, including blood pressure, body mass index, and cholesterol and glucose levels.
During the laboratory stage, DNA was isolated from the leukocyte rings in the collected blood samples and then frozen at −80°C for future genetic testing. The genotypes were determined based on a specific genetic variation (polymorphism) in the VEGFR-2 gene. The genetic marker VEGFR-2 is a component of the body's signalling system that regulates the growth of new blood vessels. There are three variations of the genotype—C/C, C/T, and T/T—differing in the variation of the DNA nucleotides cytosine (C) or thymine (T) in this region of the gene. Although the marker has been known for a long time, this was the first study to examine its impact on the prognosis of complications following myocardial infarction.
The authors evaluated the impact of 39 factors on the prognosis of risks such as cardiac death, recurrent acute coronary syndrome, stroke, and the need for repeat revascularisation, a procedure that helps restore blood flow in the arteries. To select the best model, the researchers trained and tested several machine learning algorithms: Gradient Boosting (CatBoost and LightGBM), Random Forest, Logistic Regression, and an AutoML approach.
The CatBoost model, a gradient boosting algorithm optimised for working with categorical data rather than numeric values, demonstrated the best performance. It makes predictions by sequentially building and training 'weak' decision trees, where each new tree corrects the errors of the previous ones. When building trees, the algorithm splits the data into two parts: the model is trained on one portion, while errors are calculated on the other. This reduces the risk of overfitting, where the model simply memorises the correct answers, and helps it identify general patterns for making predictions in new, unseen cases.
The influence of features on the model's accuracy was evaluated using the method of sequential feature addition, which assesses their contribution at each stage. The researchers selected the 9 most significant features: gender, body mass index, Charlson comorbidity index (which accounts for the presence of serious concomitant diseases), condition of the lateral wall of the left ventricle, degree of damage to the left coronary artery trunk, number of affected arteries, variant of the VEGFR-2 gene, choice between percutaneous coronary intervention or coronary artery bypass grafting, and statin dosage.
The results showed that the dose of statins, medications used to lower cholesterol levels in the blood, is the most important factor influencing the risk of complications. High doses of statins reduce this risk, particularly in patients with an unfavourable genotype. The VEGFR-2 polymorphism, specifically the presence of the T allele, was ranked fourth in terms of importance.
'Previously, genetic factors were not included in ML models, primarily because sequencing or even genotyping of individual nucleotides is not routinely performed in hospitals. In addition to standard measurements, we had access to data on polymorphism in the VEGFR-2 gene. This allowed us to compare this indicator with others and determine that the risk allele of the VEGFR-2 variant is one of the five most important factors for predicting long-term outcomes in patients with myocardial infarction,' explains Maria Poptsova, Head of the HSE International Laboratory of Bioinformatics and co-author of the paper.
The researchers emphasise that analysing genetic data contributes to creating more accurate and personalised models for predicting the risk of major adverse cardiovascular events in patients following a myocardial infarction.
'Cardiovascular diseases require resources for diagnosis, treatment, rehabilitation, and prevention, and therefore place a significant burden on the healthcare system. The introduction of such models into clinical practice could reduce mortality and the frequency of recurrent infarctions, optimise treatment, and ease the burden on healthcare professionals,' according to Alexander Kirdeev, Research Assistant at the International Laboratory of Bioinformatics and lead author of the paper.
The study was carried out in the framework of HSE University's 'Mirror Laboratories' project.
Alexander Kirdeev
See also:
Scientists Present New Solution to Imbalanced Learning Problem
Specialists at the HSE Faculty of Computer Science and Sber AI Lab have developed a geometric oversampling technique known as Simplicial SMOTE. Tests on various datasets have shown that it significantly improves classification performance. This technique is particularly valuable in scenarios where rare cases are crucial, such as fraud detection or the diagnosis of rare diseases. The study's results are available on ArXiv.org, an open-access archive, and will be presented at the International Conference on Knowledge Discovery and Data Mining (KDD) in summer 2025 in Toronto, Canada.
Hi-Tech Grief: HSE Researchers Explore the Pros and Cons of Digital Commemoration
Researchers at HSE University in Nizhny Novgorod have explored how technological advancements are transforming the ways in which people preserve the memory of the deceased and significant events. Digital technologies enable the creation of virtual memorials, the preservation of personal stories and belongings of the deceased, interaction with their digital footprint, and even the development of interactive avatars based on their online activity. However, these technologies not only evoke nostalgia and provide a sense of relief but can also heighten anxiety and fear, and delay the process of accepting loss. The study has been published in Chelovek (The Human Being).
Scientists Find Out Why Aphasia Patients Lose the Ability to Talk about the Past and Future
An international team of researchers, including scientists from the HSE Centre for Language and Brain, has identified the causes of impairments in expressing grammatical tense in people with aphasia. They discovered that individuals with speech disorders struggle with both forming the concept of time and selecting the correct verb tense. However, which of these processes proves more challenging depends on the speaker's language. The findings have been published in the journal Aphasiology.
Implementation of Principles of Sustainable Development Attracts More Investments
Economists from HSE and RUDN University have analysed issues related to corporate digital transformation processes. The introduction of digital solutions into corporate operations reduces the number of patents in the field of green technologies by 4% and creates additional financial difficulties. However, if a company focuses on sustainable development and increases its rating in environmental, social, and governance performance (ESG), the negative effects decrease. Moreover, when the ESG rating is high, digitalisation can even increase the number of patents by 2%. The article was published in Sustainability.
Russian Scientists Develop New Compound for Treating Aggressive Tumours
A team of Russian researchers has synthesised a novel compound for boron neutron capture therapy (BNCT), a treatment for advanced cancer that uses the boron-10 isotope. The compound exhibits low toxicity, excellent water solubility, and eliminates the need for administering large volumes. Most importantly, the active substance reaches the tumour with minimal impact on healthy tissues. The study was published in the International Journal of Molecular Sciences shortly before World Cancer Day, observed annually on February 4.
Scientists Discover Link Between Brain's Structural Features and Autistic Traits in Children
Scientists have discovered significant structural differences in the brain's pathways, tracts, and thalamus between children with autism and their neurotypical peers, despite finding no functional differences. The most significant alterations were found in the pathways connecting the thalamus—the brain's sensory information processing centre—to the temporal lobe. Moreover, the severity of these alterations positively correlated with the intensity of the child's autistic traits. The study findings have been published in Behavioural Brain Research.
Earnings Inequality Declining in Russia
Earnings inequality in Russia has nearly halved over the past 25 years. The primary factors driving this trend are rising minimum wages, regional economic convergence, and shifts in the returns on education. Since 2019, a new phase of this process has been observed, with inequality continuing to decline but driven by entirely different mechanisms. These are the findings made by Anna Lukyanova, Assistant Professor at the HSE Faculty of Economic Sciences, in her new study. The results have been published in the Journal of the New Economic Association.
Russian Physicists Discover Method to Increase Number of Atoms in Quantum Sensors
Physicists from the Institute of Spectroscopy of the Russian Academy of Sciences and HSE University have successfully trapped rubidium-87 atoms for over four seconds. Their method can help improve the accuracy of quantum sensors, where both the number of trapped atoms and the trapping time are crucial. Such quantum systems are used to study dark matter, refine navigation systems, and aid in mineral exploration. The study findings have been published in the Journal of Experimental and Theoretical Physics Letters.
HSE Scientists Develop Application for Diagnosing Aphasia
Specialists at the HSE Centre for Language and Brain have developed an application for diagnosing language disorders (aphasia), which can result from head injuries, strokes, or other neurological conditions. AutoRAT is the first standardised digital tool in Russia for assessing the presence and severity of language disorders. The application is available on RuStore and can be used on mobile and tablet devices running the Android operating system.
HSE Researchers Discover Simple and Reliable Way to Understand How People Perceive Taste
A team of scientists from the HSE Centre for Cognition & Decision Making has studied how food flavours affect brain activity, facial muscles, and emotions. Using near-infrared spectroscopy (fNIRS), they demonstrated that pleasant food activates brain areas associated with positive emotions, while neutral food stimulates regions linked to negative emotions and avoidance. This approach offers a simpler way to predict the market success of products and study eating disorders. The study was published in the journal Food Quality and Preference.