Eurasian Journal of Chemical, Medicinal and Petroleum Research

Abstract Background: Controlled ovarian stimulation (COS) is a critical component of assisted reproductive technology (ART), yet ovarian response remains highly heterogeneous despite the use of established biomarkers such as anti-Müllerian hormone (AMH) and antral follicle count (AFC). Artificial intelligence (AI), particularly machine learning (ML), has emerged as a potential decision-support technology for individualized gonadotropin dosing, prediction of oocyte yield, optimization of trigger timing, and selection of stimulation protocols. This systematic review synthesized current evidence concerning the clinical effectiveness, safety, and translational readiness of AI-guided personalized ovarian stimulation.
Methods: Published studies evaluating AI, ML, or algorithm-based personalization of ovarian stimulation in IVF/ICSI considered, with particular emphasis on gonadotropin starting-dose selection, mature oocyte prediction, trigger timing, ovarian response, live birth, clinical pregnancy, cycle cancellation, gonadotropin consumption, and ovarian hyperstimulation syndrome (OHSS). Evidence from randomized controlled trials (RCTs), prospective clinical studies, retrospective validation studies, systematic reviews, and relevant clinical guidelines synthesized narratively. Prediction-model quality and applicability considered using principles derived from PROBAST and emerging PROBAST+AI recommendations.
Results: AI models demonstrated promising predictive performance for ovarian response, total and mature oocyte yield, and trigger-day selection. Prospective clinical evidence remains limited. A multicenter prospective study involving 291 AI-assisted cycles reported 12.20 versus 11.24 MII oocytes and 16.01 versus 14.54 retrieved oocytes compared with historical controls, while total FSH exposure was 3671.95 versus 3846.29 IU; none of these differences reached statistical significance. Conventional individualized dosing trials demonstrated that reducing FSH in predicted hyper-responders reduced any-grade OHSS without reducing cumulative live birth, whereas increasing FSH in predicted poor responders did not improve cumulative live birth.
Conclusions: AI-guided ovarian stimulation is clinically promising but remains insufficiently validated for routine autonomous clinical decision-making. Current evidence supports AI primarily as a clinician-supervised decision-support technology. Large, prospective, externally validated, randomized trials incorporating live birth and safety outcomes are required before widespread implementation.

Abstract Adverse drug reactions (ADRs) and adverse drug events (ADEs) remain major threats to patient safety in hospitals, particularly among older adults, patients with multimorbidity, individuals exposed to polypharmacy, and patients experiencing rapid changes in physiological status. Conventional pharmacovigilance and medication-monitoring approaches depend heavily on retrospective reporting and clinical recognition, which may delay identification of preventable harm. Artificial intelligence (AI), particularly machine learning (ML), natural language processing, and deep learning, offers opportunities to transform pharmacovigilance from a predominantly reactive process into a predictive and continuously updated safety system. This systematic evidence synthesis examined the performance and clinical implications of AI-based models for predicting ADRs and ADEs among hospitalized patients, with particular attention to nursing practice. Evidence published in major biomedical databases synthesized with emphasis on model performance, predictors, validation, explainability, and implications for medication administration and clinical surveillance. Recent systematic reviews indicate that random forest, gradient boosting, support vector machines, regularized regression, and deep-learning architectures frequently used, with pooled predictive performance generally demonstrating moderate discrimination. A 2025 systematic review specifically examining hospitalized patients reported pooled sensitivity and specificity of 78.1% and 70.6%, respectively, for development-only models, 81.5%, and 79.5% for models undergoing external validation. Contemporary evidence also demonstrates increasing use of longitudinal EHR representations, clinical narratives, nursing documentation, and foundation models. However, heterogeneous outcome definitions, missing-data procedures, limited external validation, class imbalance, alert fatigue, algorithmic bias, and insufficient explainability remain substantial barriers to implementation. AI therefore conceptualized as an augmentation technology rather than a replacement for nurses or other clinicians. Effective implementation requires interdisciplinary governance, transparent algorithms, prospective evaluation, workflow integration, education, and continuous monitoring. Properly implemented, AI-supported ADR prediction may strengthen nursing vigilance, prioritize high-risk patients, improve medication safety, and facilitate earlier clinical intervention.

Abstract The discovery of effective and environmentally friendly organic corrosion inhibitors remains constrained by slow experimental screening and fragmented computational workflows . This study presents an integrated hybrid framework combining density functional theory (DFT), molecular dynamics (MD) simulations, and machine learning (ML) for high-throughput screening of organic corrosion inhibitors. DFT provides quantum-level insights into electronic structure and adsorption energetics through frontier molecular orbital analysis (EHOMO, ELUMO, energy gap ΔE), while MD captures time-dependent interfacial behavior and competitive ion interactions . A comprehensive dataset of 284 phenyl phthalimide derivatives was generated through DFT and MD simulations, with electronic properties correlated to experimental inhibition efficiency values . Among various ML models evaluated, Artificial Neural Networks demonstrated the highest prediction accuracy, achieving R² values of 93.18% for EHOMO and 91.12% for ELUMO . SHAP and PFI feature importance analyses revealed that descriptors B06[C-N] and qnmax are essential for inhibitor efficacy . The integrated framework addresses key limitations in current approaches including data scarcity, non-standardized descriptor selection, insufficient physical interpretability, and poor generalization across chemically diverse systems . Experimental validation through electrochemical impedance spectroscopy (EIS) and potentiodynamic polarization confirmed the predictive capability of the ML models, with excellent agreement between predicted and measured inhibition efficiencies. This work establishes a unified, scalable, and physically informed computational framework for rational design and discovery of next-generation corrosion inhibitors.

Abstract Electrochemical characterization techniques have become indispensable for understanding corrosion phenomena, enabling both fundamental mechanistic insights and practical corrosion monitoring across diverse industrial applications. This comprehensive review systematically examines the principles, applications, and data interpretation strategies for key electrochemical methods used in corrosion research. Cyclic voltammetry (CV) has emerged as a powerful mechanistic probe, capturing real-time redox activity and surface transformations, though historically underutilized due to the irreversible nature of corrosion reactions . Electrochemical impedance spectroscopy (EIS) remains the most versatile technique, providing frequency-dependent information on charge transfer resistance, double-layer capacitance, and diffusion processes, with applications ranging from reinforced concrete diagnosis to nanostructured coating evaluation . Potentiodynamic polarization enables rapid determination of corrosion current density, Tafel slopes, and pitting potentials through the Stern–Geary relationship . Electrochemical noise analysis detects spontaneous current and potential fluctuations sensitive to localized corrosion events such as metastable pit growth . Recent advances in machine learning have revolutionized data interpretation, with hybrid models achieving R² > 0.99 prediction accuracy for corrosion rate forecasting through integration of swarm intelligence optimization with deep learning architectures . Four-dimensional impedance analysis has emerged for time-varying systems, enabling instantaneous impedance determination during non-stationary corrosion processes . This review concludes that effective corrosion characterization requires integrated approaches combining complementary techniques with advanced data analytics, bridging laboratory mechanistic understanding with field-applicable monitoring solutions.

Abstract Breast cancer remains one of the leading causes of cancer-related mortality among women globally, highlighting the critical need for early detection and accurate diagnosis. Recent advances in artificial intelligence (AI), encompassing both machine learning (ML) and deep learning (DL) approaches, have demonstrated significant potential in enhancing diagnostic accuracy, reducing human error, and supporting clinical decision-making. This systematic review critically analyzes existing studies that employ AI for breast cancer detection, focusing on methodological approaches, dataset characteristics, model performance, and interpretability. ML-based techniques, including support vector machines, random forests, and gradient boosting, show promising results in structured datasets, particularly where dataset sizes are limited, and interpretability is essential. In contrast, DL approaches, primarily convolutional neural networks and their variants, outperform ML in raw image analysis, multi-modal imaging, and complex feature extraction, achieving higher accuracy and sensitivity. Hybrid models integrating ML and DL, often augmented with radiomics features, offer a balanced framework, combining high predictive performance with improved interpretability. Additionally, explainable AI (XAI) techniques are increasingly applied to DL models, mitigating the “black-box” problem and fostering clinical trust. Despite these advancements, challenges remain, including the need for large, high-quality, multi-institutional datasets, computational resource demands, and generalizability across diverse populations. Low-resource and portable AI solutions offer potential for broader accessibility, though with modest reductions in predictive performance. Overall, AI demonstrates transformative potential in early breast cancer detection, particularly when combined with hybrid and explainable frameworks. Future research should prioritize multi-modal integration, rigorous cross-center validation, and deployment strategies that balance accuracy, interpretability, and accessibility, ultimately facilitating clinical adoption and improving patient outcomes.