Browse Articles
Discover research articles across all indexed journals
Performance Studies on machine learning based channel modelling for vehicular visible light communication
Enhanced space-variant deblurring of spacecraft images via detail-preserving techniques
Subchronic toxicity of 222 nm ultraviolet irradiation in rats for safe human translation and application guidelines
Accelerating genetic diagnosis in the NICU: neonatologist-driven rapid whole genome sequencing
Umbilical cord blood cell transcriptional and methylation signatures at birth are associated with BPD development and chorioamnionitis: a pilot study
Applying explainable artificial intelligence to interpret supervised ensemble learning models for robust credit card fraud detection
Abstract As the usage of digital financial transactions continue to swell, it becomes all the more crucial to employ classifiers with machine learning techniques in order to process credit card fraud detection. While complex ensemble models can reach incredible levels of predictive accuracy, the black-box nature of these algorithms often leaves us at a loss, and there hasn’t been much research on how interpretable these high-performing models are across different settings. To contribute to this research gap, this study assesses four supervised learning algorithms (Logistic Regression, Random Forest, XGBoost and LightGBM) based on their predictive performance and applicability with Explainable Artificial Intelligence (XAI) techniques. To optimize the generalizability of their findings, the models were extensively tested and compared against three disparate public credit card transaction datasets. The performance, as measured by different metrics such as accuracy, precision, recall, F1-score and ROC-AUC gives the best results to tree-based algorithms ensembles (especially XGBoost) with linear methods also providing decent improvement over baseline models. Data used as input for training consisted of the top-performing models, and then SHAP (SHapley Additive exPlanations) framework was applied to help identify leading feature importance and interpret complicated predictive output. This study provides a comprehensive outline linking predictive performance to explainability in every combination of models, yielding impactful results for developing effective, transparent and accountable financial security systems.
Expression analysis of blood samples shows elevated 5′-tRF-His-GTG in breast cancer patients
Abstract tRNA-derived fragments (tRFs) have emerged as promising non-invasive biomarkers for breast cancer. Understanding their diagnostic potential is essential for improving early detection and patient outcomes. This study aimed to investigate the expression level of the 5′-tRF-His-GTG in the blood of breast cancer patients and assess its potential as a diagnostic or prognostic biomarker. Candidate tRFs were identified through bioinformatic analyses using MINTbase, MODOMICS, and BBcancer, focusing on expression likelihood in biofluids and chemical modification profiles. A total of 56 blood samples, including 28 from breast cancer patients and 28 from healthy controls, were collected. Total RNA was extracted, and cDNA was synthesized via reverse transcription. Quantitative real-time PCR was performed to assess the expression level of tRF-32-XSXMSL73VL4YK. Statistical analysis was conducted using an independent t-test with a significance threshold of p < 0.05. tRF-32-XSXMSL73VL4YK, characterized by minimal chemical modifications, was selected for further investigation. It was significantly upregulated in breast cancer patients compared to healthy controls ( p < 0.001). However, no significant associations were found between its expression and clinicopathological features such as age, tumor size, TNM stage, or IHC markers ( p > 0.05). Our study identifies tRF-32-XSXMSL73VL4YK as a significantly upregulated 5’tRF-His-GTG in breast cancer, yet its expression shows no correlation with key clinical characteristics. While tRF-32-XSXMSL73VL4YK may not serve as a standalone diagnostic marker due to its lack of correlation with clinical features, its consistent upregulation suggests promise as a component of a multi-marker panel or as a prognostic biomarker.