Vladimir Kokh

Petr Philonenko, Vladimir Kokh, Pavel Blinov

Conventional medical cancer screening methods are costly, labor-intensive, and extremely difficult to scale. Although AI can improve cancer detection, most systems rely on complex or specialized medical data, making them impractical for large-scale screening. We introduce Can-SAVE, a lightweight AI system that ranks population-wide cancer risks solely based on medical history events. By integrating survival model outputs into a gradient-boosting framework, our approach detects subtle, long-term patient risk patterns - often well before clinical symptoms manifest. Can-SAVE was rigorously evaluated on a real-world dataset of 2.5 million adults spanning five Russian regions, marking the study as one of the largest and most comprehensive deployments of AI-driven cancer risk assessment. In a retrospective oncologist-supervised study over 1.9M patients, Can-SAVE achieves a 4-10x higher detection rate at identical screening volumes and an Average Precision (AP) of 0.228 vs. 0.193 for the best baseline (LoRA-tuned Qwen3-Embeddings via DeepSeek-R1 summarization). In a year-long prospective pilot (426K patients), our method almost doubled the cancer detection rate (+91%) and increased population coverage by 36% over the national screening protocol. The system demonstrates practical scalability: a city-wide population of 1 million patients can be processed in under three hours using standard hardware, enabling seamless clinical integration. This work proves that Can-SAVE achieves nationally significant cancer detection improvements while adhering to real-world public healthcare constraints, offering immediate clinical utility and a replicable framework for population-wide screening. Code for training and feature engineering is available at https://github.com/sb-ai-lab/Can-SAVE.

Aleksandr Nesterov, Bulat Ibragimov, Dmitriy Umerenkov et al.

The symptom checking systems inquire users for their symptoms and perform a rapid and affordable medical assessment of their condition. The basic symptom checking systems based on Bayesian methods, decision trees, or information gain methods are easy to train and do not require significant computational resources. However, their drawbacks are low relevance of proposed symptoms and insufficient quality of diagnostics. The best results on these tasks are achieved by reinforcement learning models. Their weaknesses are the difficulty of developing and training such systems and limited applicability to cases with large and sparse decision spaces. We propose a new approach based on the supervised learning of neural models with logic regularization that combines the advantages of the different methods. Our experiments on real and synthetic data show that the proposed approach outperforms the best existing methods in the accuracy of diagnosis when the number of diagnoses and symptoms is large.

Alexander Yalunin, Dmitriy Umerenkov, Vladimir Kokh

In this paper we present a novel approach to abstractive summarization of patient hospitalisation histories. We applied an encoder-decoder framework with Longformer neural network as an encoder and BERT as a decoder. Our experiments show improved quality on some summarization tasks compared with pointer-generator networks. We also conducted a study with experienced physicians evaluating the results of our model in comparison with PGN baseline and human-generated abstracts, which showed the effectiveness of our model.

Ivan Kruzhilov, Stepan Kudin, Luka Vetoshkin et al.

This paper evaluates the performance of supervised and unsupervised deep learning models for denoising positron emission tomography (PET) images in the presence of reduced acquisition times. Our experiments consider 212 studies (56908 images), and evaluate the models using 2D (RMSE, SSIM) and 3D (SUVpeak and SUVmax error for the regions of interest) metrics. It was shown that, in contrast to previous studies, supervised models (ResNet, Unet, SwinIR) outperform unsupervised models (pix2pix GAN and CycleGAN with ResNet backbone and various auxiliary losses) in the reconstruction of 2D PET images. Moreover, a hybrid approach of supervised CycleGAN shows the best results in SUVmax estimation for denoised images, and the SUVmax estimation error for denoised images is comparable with the PET reproducibility error.

Alexander Ponomarchuk, Ilya Burenko, Elian Malkin et al.

The COVID-19 pandemic created a significant interest and demand for infection detection and monitoring solutions. In this paper we propose a machine learning method to quickly triage COVID-19 using recordings made on consumer devices. The approach combines signal processing methods with fine-tuned deep learning networks and provides methods for signal denoising, cough detection and classification. We have also developed and deployed a mobile application that uses symptoms checker together with voice, breath and cough signals to detect COVID-19 infection. The application showed robust performance on both open sourced datasets and on the noisy data collected during beta testing by the end users.

Alexey Krylov, Iskander Vagizov, Dmitrii Korzh et al.

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation techniques often rely on manual engineering or rudimentary obfuscation, producing low-quality or incoherent text that is easily flagged by perplexity-based filters. We present an automated red-teaming framework that evolves semantically meaningful and stealthy jailbreak prompts for aligned compact LLMs. The approach employs a multi-stage evolutionary search, where candidate prompts are iteratively refined using a population-based strategy augmented with temperature-controlled variability to balance exploration and coherence preservation. This enables the systematic discovery of prompts capable of bypassing alignment safeguards while maintaining natural language fluency. We evaluate our method on benchmarks in English (In-The-Wild Jailbreak Prompts on LLMs), and a newly curated Arabic one derived from In-The-Wild Jailbreak Prompts on LLMs and annotated by native Arabic linguists, enabling multilingual assessment.

Dmitriy Umerenkov, Oleg Cherkashin, Alexander Nesterov et al.

In this paper we present a novel approach to risk assessment for patients hospitalized with pneumonia or COVID-19 based on their admission reports. We applied a Longformer neural network to admission reports and other textual data available shortly after admission to compute risk scores for the patients. We used patient data of multiple European hospitals to demonstrate that our approach outperforms the Transformer baselines. Our experiments show that the proposed model generalises across institutions and diagnoses. Also, our method has several other advantages described in the paper.

Pavel Blinov, Arina Reshetnikova, Aleksandr Nesterov et al.

The paper describes the open Russian medical language understanding benchmark covering several task types (classification, question answering, natural language inference, named entity recognition) on a number of novel text sets. Given the sensitive nature of the data in healthcare, such a benchmark partially closes the problem of Russian medical dataset absence. We prepare the unified format labeling, data split, and evaluation metrics for new tasks. The remaining tasks are from existing datasets with a few modifications. A single-number metric expresses a model's ability to cope with the benchmark. Moreover, we implement several baseline models, from simple ones to neural networks with transformer architecture, and release the code. Expectedly, the more advanced models yield better performance, but even a simple model is enough for a decent result in some tasks. Furthermore, for all tasks, we provide a human evaluation. Interestingly the models outperform humans in the large-scale classification tasks. However, the advantage of natural intelligence remains in the tasks requiring more knowledge and reasoning.

Pavel Blinov, Vladimir Kokh

The paper researches the problem of representation learning for electronic health records. We present the patient histories as temporal sequences of diseases for which embeddings are learned in an unsupervised setup with a transformer-based neural network model. Additionally the embedding space includes demographic parameters which allow the creation of generalized patient profiles and successful transfer of medical knowledge to other domains. The training of such a medical profile model has been performed on a dataset of more than one million patients. Detailed model analysis and its comparison with the state-of-the-art method show its clear advantage in the diagnosis prediction task. Further, we show two applications based on the developed profile model. First, a novel Harbinger Disease Discovery method allowing to reveal disease associated hypotheses and potentially are beneficial in the design of epidemiological studies. Second, the patient embeddings extracted from the profile model applied to the insurance scoring task allow significant improvement in the performance metrics.

Manvel Avetisian, Ilya Burenko, Konstantin Egorov et al.

Analysis of chest CT scans can be used in detecting parts of lungs that are affected by infectious diseases such as COVID-19.Determining the volume of lungs affected by lesions is essential for formulating treatment recommendations and prioritizingpatients by severity of the disease. In this paper we adopted an approach based on using an ensemble of deep convolutionalneural networks for segmentation of slices of lung CT scans. Using our models we are able to segment the lesions, evaluatepatients dynamics, estimate relative volume of lungs affected by lesions and evaluate the lung damage stage. Our modelswere trained on data from different medical centers. We compared predictions of our models with those of six experiencedradiologists and our segmentation model outperformed most of them. On the task of classification of disease severity, ourmodel outperformed all the radiologists.

Pavel Blinov, Manvel Avetisian, Vladimir Kokh et al.

In this paper we study the problem of predicting clinical diagnoses from textual Electronic Health Records (EHR) data. We show the importance of this problem in medical community and present comprehensive historical review of the problem and proposed methods. As the main scientific contributions we present a modification of Bidirectional Encoder Representations from Transformers (BERT) model for sequence classification that implements a novel way of Fully-Connected (FC) layer composition and a BERT model pretrained only on domain data. To empirically validate our model, we use a large-scale Russian EHR dataset consisting of about 4 million unique patient visits. This is the largest such study for the Russian language and one of the largest globally. We performed a number of comparative experiments with other text representation models on the task of multiclass classification for 265 disease subset of ICD-10. The experiments demonstrate improved performance of our models compared to other baselines, including a fine-tuned Russian BERT (RuBERT) variant. We also show comparable performance of our model with a panel of experienced medical experts. This allows us to hope that implementation of this system will reduce misdiagnosis.

Manvel Avetisian, Vladimir Kokh, Alex Tuzhilin et al.

Segmentation of ischemic stroke and intracranial hemorrhage on computed tomography is essential for investigation and treatment of stroke. In this paper, we modified the U-Net CNN architecture for the stroke identification problem using non-contrast CT. We applied the proposed DL model to historical patient data and also conducted clinical experiments involving ten experienced radiologists. Our model achieved strong results on historical data, and significantly outperformed seven radiologist out of ten, while being on par with the remaining three.