Dinara Dinara Shyrynkanova

Dr. Dinara Dinara Shyrynkanova


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
4 June 2026 in Computers
Verified
Journal Article
Open access
PDF file
IKIndira Karymsakova
Indira Karymsakova
DKDinara Ошановна Kozhakhmetova
Dinara Ошановна Kozhakhmetova
DBDariga Bekenova
Dariga Bekenova
LALili Abdullah
Lili Abdullah
AZAleksandr Zolotov
Aleksandr Zolotov
ABAlina Bugubayeva
Alina Bugubayeva
Lung cancer is still one of the major contributors to cancer-related mortality. Treatment effectiveness depends directly on early diagnosis and accurate prediction of disease progression. This study focuses on the application of classical machine learning algorithms —including Logistic Regression, Support Vector Machine, Random Forest, and XGBoost —for questionnaire-based lung cancer risk assessment. A comparative study of six machine learning algorithms used to predict lung cancer based on survey data was conducted. According to the ROC-AUC metric, Random Forest model achieved the best result. In terms of F1-score and precision for the positive class, the support vector machine (SVM) demonstrated the highest efficiency. However, gradient boosting provided the most balanced results across key clinical metrics. SHAP (SHapley Additive exPlanations) analysis identified three preliminary predictors potentially associated with lung cancer risk in this sample: seeing a pulmonologist, unexplained weight loss, and loss of appetite. These preliminary results are consistent with clinical observations and suggest the potential interpretability of ensemble machine learning approaches in medical diagnostics, though confirmation on larger datasets is required. Overall, the preliminary results suggest the potential of using machine learning methods for lung cancer screening based on questionnaire data, particularly with an expanded training sample. Potential applications of early lung cancer diagnosis are discussed. Further research in this area will be conducted in conjunction with image recognition of computed tomography scans.

9 October 2026 in Computers
Verified
Journal Article
Open access
PDF file
IKIndira Karymsakova
Indira Karymsakova
DKDinara Ошановна Kozhakhmetova
Dinara Ошановна Kozhakhmetova
DSDinara Dinara Shyrynkanova
Dinara Dinara Shyrynkanova
DBDariga Bekenova
Dariga Bekenova
LKLazzat Kydyralina
Lazzat Kydyralina
SAShynggys Adilgazyuly
Shynggys Adilgazyuly
Background/Objective: Lung cancer remains a leading cause of cancer-related mortality, and access to low-dose CT screening is limited in resource-constrained settings. This study aimed to develop and evaluate an interpretable machine learning model for preliminary, symptom-based lung cancer risk discrimination using clinical indicators and lifestyle factors, without requiring imaging. Methods: A cross-sectional dataset of 561 participants (38 with a prior lung cancer diagnosis), following exclusion of a minors-eligible age bracket for which independent age verification was not possible, was analyzed. Five machine learning algorithms (Logistic Regression, Random Forest, XGBoost, LightGBM, CatBoost) were compared using a leakage-free pipeline, with ADASYN class balancing and hyperparameter tuning performed exclusively within cross-validation folds; feature selection was verified to be stable across folds (98% average overlap with the final feature set). The final model was selected solely on the basis of repeated cross-validated performance, without reference to the test set. Model interpretability was assessed using LIME, and a four-tier risk stratification system was developed and calibrated. Results: Random Forest achieved the best cross-validated F1-score (0.850 ± 0.092) among the five candidates and, given a clinically motivated preference for higher sensitivity at comparable F1, was selected as the final model. On the independent test set (n = 113), it achieved Accuracy = 0.956, Recall = 0.875, F1-score = 0.737, and AUC-ROC = 0.912. Sensitivity analysis indicated moderate reliance on a potential diagnostic proxy feature, and balancing-method comparisons (ADASYN, random oversampling, class weighting) confirmed that conclusions were not contingent on the specific resampling technique. Conclusions: The proposed model demonstrates solid discriminative performance and interpretability; however, given the cross-sectional design and limited number of positive cases, results should be interpreted as preliminary risk discrimination rather than validated early-detection prediction, warranting further prospective validation.