Sandugash Serikbayeva

Sandugash Serikbayeva


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2025 in Technologies
Verified
Journal Article
Open access
PDF file
VRValiya Ramazanova
Valiya Ramazanova
MSMadina Sambetbayeva
Madina Sambetbayeva
SSSandugash Serikbayeva
Sandugash Serikbayeva
Aigerim YerimbetovaAigerim Yerimbetova
Aigerim Yerimbetova
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
GKGulzhamal Kalman
Gulzhamal Kalman
This article addresses the task of building personalized educational recommendations based on a heterogeneous knowledge graph that integrates data from university curricula, job vacancies, and online courses. To solve the problem of course recommendations by their relevance to a user’s competencies, a graph neural network (GNN)-based approach is proposed, specifically utilizing and comparing the Heterogeneous Graph Transformer (HGT) architecture, Graph Sample and Aggregate network (GraphSAGE), and Heterogeneous Graph Attention Network (HAN). Experiments were conducted on a heterogeneous graph comprising various node and relation types. The models were evaluated using regression and ranking metrics. The results demonstrated the superiority of the HGT-based recommendation model as a link regression task, especially in terms of ranking metrics, confirming its suitability for generating accurate and interpretable recommendations in educational systems. The proposed approach can be useful for developing adaptive learning recommendations aligned with users’ career goals.

31 March 2026 in Frontiers in Artificial Intelligence
Verified
Journal Article
Open access
ASAnar Sultangaziyeva
Anar Sultangaziyeva
MSMadina Sambetbayeva
Madina Sambetbayeva
NMNurzhan Mukazhanov
Nurzhan Mukazhanov
BABayangali Abdygalym
Bayangali Abdygalym
SSSandugash Serikbayeva
Sandugash Serikbayeva
Introduction: Clinical exome sequencing reports contain valuable genetic and phenotypic information but are typically stored in unstructured text form, making automated biomedical information extraction challenging. For the Russian language, publicly available annotated corpora for genetic report analysis remain extremely limited. Methods: We present GENEXOM, the first multi-level annotated corpus of Russian-language clinical exome sequencing reports designed for biomedical information extraction. The corpus includes 5,318 reports (318 authentic and 5,000 synthetic) and comprises 16 entity types and 7 relation types aligned with HGVS, OMIM, ClinVar, and ACMG/AMP standards. Annotation was performed in the Label Studio platform by expert geneticists. Baseline transformer models (RuBERT, RuBioBERT, ModernBERT) were fine-tuned for Named Entity Recognition (NER) and Relation Extraction (RE). Results: The annotation achieved span-level F1-IAA = 0.83 and macro κ = 0.79 ± 0.04, indicating substantial inter-annotator agreement. Among the evaluated models, ModernBERT achieved the best performance with F1 = 0.88 ± 0.03 for NER and F1 = 0.836 ± 0.04 for RE on the held-out test set. Discussion: The GENEXOM corpus provides a linguistically and clinically adapted resource for Russian medical NLP and supports downstream tasks such as variant interpretation, phenotype–disease mapping, and biomedical knowledge graph construction. The corpus and accompanying code are publicly available for research purposes.

27 August 2026 in Information
Verified
Journal Article
Open access
PDF file
ASAssem Shayakhmetova
Assem Shayakhmetova
MSMadina Sambetbayeva
Madina Sambetbayeva
Vladimir BarakhninVladimir Barakhnin
Vladimir Barakhnin
ASAnar Sultangaziyeva
Anar Sultangaziyeva
Nurzhan Kakenovich MukazhanovNurzhan Kakenovich Mukazhanov
Nurzhan Kakenovich Mukazhanov
RBRaushan Begim
Raushan Begim
The growing volume of unstructured clinical and genetic text calls for automated processing methods that can meaningfully support clinical decision-making. Most existing work, however, treats the analysis of patient clinical descriptions and the interpretation of genetic reports as unrelated tasks, disregarding the sequence in which real diagnostic decisions unfold. We study two stage-specific families of classification tasks corresponding to the two points at which such decisions are taken—pre-genetic triage from clinical narratives, and post-genetic interpretation of completed genetic reports—and evaluate each family under a single leakage-controlled protocol using TF-IDF text representation with classical machine learning. All experiments use a corpus of 546 records with confirmed provenance, partitioned by a group-constrained master split (349 train/88 validation/109 test, seed 42) in which all 181 text-similarity candidate pairs are confined to a single partition. Task subsets contain 299 and 326 documents at the first stage and 375 and 461 at the second. Text representation relied on Word TF-IDF, Character TF-IDF and combined Word + Character TF-IDF with Logistic Regression and Linear SVM; every configuration was selected on validation Macro F1 alone, with the test partition opened only after selection. RuBERT-tiny2, XLM-RoBERTa base and PubMedBERT were fine-tuned as transformer baselines over three seeds each. Under this protocol, the first stage reached Macro F1 = 0.6876 (Accuracy = 0.8308, ROC-AUC = 0.8500) and the second-stage Macro F1 = 0.8225 (Accuracy = 0.8571, ROC-AUC = 0.9377) for the binary classification of diagnostic status. A controlled comparison holding the documents, split, vectorizer, classifier and hyperparameters fixed and varying only the label version increased Accuracy from 0.5738 to 0.8361 (exact McNemar p = 0.000145), whereas Macro F1 increased numerically from 0.5165 to 0.5966 but not significantly (paired bootstrap p = 0.354; 95% CI of the difference [−0.091, 0.229]). Two Russian and multilingual encoders collapsed to the majority class (Macro F1 = 0.4583), while an English biomedical encoder scored higher than the classical comparator (0.7705 ± 0.0119 against 0.6876) without reaching significance (paired bootstrap p = 0.463). Thus, the controlled experiment supports improved overall correctness, mainly associated with the majority class, but does not establish improved balanced class-wise performance at this sample size. In the second-stage leakage analysis, removing the diagnostic conclusion reduced Macro F1 from 0.8225 to 0.6478 (paired bootstrap p = 0.001), masking the exact label-generating rules reduced it to 0.7455 (p = 0.021), and combined masking reduced it to 0.6389 (p < 0.001). The unmasked Stage 2 score therefore depends materially on explicit report cues and should not be interpreted as evidence of independent diagnostic reasoning. The contribution of this work is a stage-oriented formulation of clinical genetic text classification in which the target variable of each task is aligned with the information available at the corresponding point of the diagnostic pathway, evaluated under a reproducible leakage-controlled protocol with bootstrap confidence intervals and paired significance testing. A unified single-model baseline on the joint target reached Macro F1 = 0.5238, below either stage-specific model on its own target. Because the labels are rule-derived rather than independently expert-validated, the corpus is small, and no external validation was performed, these results characterize what is achievable on this corpus rather than demonstrating clinical readiness.