Nisreen Nayef Awad Albzour

Ms. Nisreen Nayef Awad Albzour

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
31 December 2022 in Revue d'intelligence artificielle
Verified
Journal Article
Closed access
MAMohammad A Aljarrah
Mohammad A Aljarrah
AAAhmad Al-Jarrah
Ahmad Al-Jarrah
AJAmin Jarrah
Amin Jarrah
MAMohammad AlShurbaji
Mohammad AlShurbaji
Sharaf K. MagablehSharaf K. Magableh
Sharaf K. Magableh
MAMamoun O. Al-Shamali
Mamoun O. Al-Shamali
The Speaker identification process is not a new trend; however, for the Arabic Holy Quran recitation, there are still quite improvements that can make this process more accurate and reliable. This paper collected the input data from 14 native Arabic reciters, consisting of “Surah Al-Kawthar” speech signals from the Holy Quran. Moreover, this paper discusses the accuracy rates for 8 and 16 features. Indeed, a modified Vector Quantization (VQ) technique will be presented, in addition to realistically matching the centroids of the various codebooks and measuring systems’ effectiveness. Note that the VQ technique will be utilized to generate the codebooks by clustering these features into a finite number of centroids. The proposed system’s software was built and executed using MATLAB®. The proposed system’s total accuracy rate was 97.92% and 98.51% for 8 and 16 centroids codebooks, respectively. However, this study discussed two validation tactics to ensure that the outcomes are reliable and can be reproduced. Hence, the K-mean clustering algorithm has been used to validate the obtained results and discuss the outcomes of this study. Finally, it has been found that the improved VQ method gives a better result than the K-means method.

21 December 2022 in Research Square
Verified
Preprint
Open access
PDF file
HAHussein Al-Zoubi
Hussein Al-Zoubi
Nisreen Nayef Awad AlbzourNisreen Nayef Awad Albzour
Nisreen Nayef Awad Albzour
This paper mainly explores how driverless AI can help researchers accurately classify leukemia diagnosis. Since Leukemia is among the most common commonly occurring types of cancer and thus early detection and classification can be of paramount significance. In this paper, we proposed a reliable method to automate the classification of leukemia in which we used the automated machine learning (henceforth, AutoML) library available in H2O.ai to select the best classification model capable of detection and classification depending on peripheral blood smear (PBS) images. The proposed framework used three datasets of bone marrow images to detect Leukemia and accordingly to classify blood cells. we compared some previous studies conducted in this field adopting traditional classification approaches with our proposed model of hyperautomation. We divide these data between training and testing using threefold cross-validation. The final AI model produced the most accurate diagnostics, and its effectiveness was evaluated using the accuracy, specificity, F-score, recall, precision, and Area Under the Curve (AUC) from the Receiver Operating Characteristic (ROC) curve, and it achieves an elegant performance for Leukemia classification with AUC of 1 and 1 in the testing and validation sets, accordingly. Results indicate that almost every model trained on H2O.ai driverless works relatively better than other models that work with traditional software with less time and effort.

25 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
Nisreen Nayef Awad AlbzourNisreen Nayef Awad Albzour
Nisreen Nayef Awad Albzour
SLSarah S. Lam
Sarah S. Lam
Cervical cancer remains a significant global health concern and a leading cause of cancer-related deaths among women. Early detection through Pap smear tests is essential to reduce mortality rates; however, the manual examination is time consuming and prone to human error. This study proposes a deep learning framework that integrates U-Net for segmentation and a classification model to enhance diagnostic performance. The Herlev Pap Smear Dataset, a publicly available cervical cell dataset, was utilized for training and evaluation. The impact of segmentation on classification performance was evaluated by comparing the model trained on segmented images and another trained on non-segmented images. Experimental results showed that the use of segmented images marginally improved the model performance on precision (about 0.41 percent higher) and F1-score (about 1.30 percent higher), which suggests a slightly more balanced classification performance. While segmentation helps in feature extraction, the results showed that its impact on classification performance appears to be limited. The proposed framework offers a supplemental tool for clinical applications, which may aid pathologists in early diagnosis.

10 June 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Nisreen Nayef Awad AlbzourNisreen Nayef Awad Albzour
Nisreen Nayef Awad Albzour
Background. Clinical machine-learning models are increasingly evaluated for trustworthiness as well as predictive accuracy. Two pillars of trust — the reliability of predicted probabilities (calibration) and the reliability of feature-level explanations — are usually studied in isolation. How these two pillars behave together under cross-cohort distribution shift remains an open question, with direct implications for clinical deployment.Methods. Seven classifiers — Logistic Regression, Random Forest, XGBoost, LightGBM, an MLP, and two soft-voting hybrid MLP-plus-tree ensembles — were trained on the SEER breast cancer cohort (n = 4,024; 84.7% five-year alive) and externally validated on the METABRIC cohort (n = 1,904; 42.1% alive) using six shared clinical features. Three calibration methods (temperature scaling, Platt scaling, isotonic regression) were compared, with the best selected per model by Expected Calibration Error (ECE) on the SEER validation partition. SHAP attribution was computed for every model using the family-appropriate exact or sampling-based explainer; importance rankings were validated through cross-validation stability, clinical-alignment scoring, and cross-model Spearman rank correlation. Cross-cohort transfer was assessed separately for calibration (ECE, MCE, Brier, NLL on METABRIC after applying the SEER-fit calibrator) and for feature importance (per-model Spearman rank correlation between SEER and METABRIC mean |SHAP| vectors).Results. Isotonic regression reduced SEER test ECE by 50–92% across all seven models. The same SEER-fit calibrators, applied unchanged to METABRIC, increased ECE by a factor of two to three for every model on both the imputed and complete-case external cohorts, a direct consequence of the base-rate shift from 84.7% to 42.1% alive. By contrast, SHAP feature-importance rankings transferred strongly across cohorts in the five-model base-model analysis: tree-based models (RF, XGB, LGBM) achieved SEER–METABRIC Spearman rank correlations of ρ ≈ 0.94 (p < 0.01), with Age and Nodes Positive top-ranked in both cohorts; LR and MLP showed positive but non-significant agreement (ρ = 0.66 and 0.71, respectively) in the six-feature setting. Cross-model agreement was very high among the tree-based and hybrid models (ρ > 0.91), and the top-ranked features for every model lay within the established set of breast-cancer prognostic factors.Conclusions. Calibration and feature importance dissociate under prevalence shift: probability scale is cohort-specific, but feature ranking is cohort-stable. This two-layer view supports a concrete deployment rule — feature-level explanations can be reported with confidence across cohorts, but predicted probabilities require per-cohort recalibration on a labeled sample of the target population. Treating calibration and explanation as separate transferability questions clarifies what can and cannot be carried across cohorts in clinical machine-learning practice.

7 July 2026 in Cancers
Verified
Journal Article
Open access
PDF file
Nisreen Nayef Awad AlbzourNisreen Nayef Awad Albzour
Nisreen Nayef Awad Albzour
SLSarah S. Lam
Sarah S. Lam
Background/Objectives: Manual Pap smear analysis for cervical cancer screening is limited by inter-observer variability, time constraints, and restricted expert availability. Although convolutional neural networks (CNNs) have automated cervical cell classification, they remain limited in modeling long-range spatial dependencies and often lack clinical interpretability. Methods: In this study, Vision Transformer (ViT) architectures were systematically optimized to enhance automated cervical cancer screening and improve interpretability. The Herlev dataset (917 images: 242 normal, 675 abnormal) was utilized to optimize ViT-Tiny, a lightweight ViT architecture designed for reduced computational complexity, through a comprehensive evaluation of augmentation strategies, class weighting, and hyperparameters. Results: The optimal configuration achieved a cross-validation accuracy of approximately 95% (94.89% for the best replicated configuration), in which random horizontal flipping and class weighting (0.7 × 1.3) were identified as most effective. Gradient-weighted Class Activation Mapping (Grad-CAM) analysis confirmed that model attention corresponded to clinically relevant morphological features, including nuclei regions, cell boundaries, and chromatin texture, which align with cytopathological criteria. Conclusions: These findings indicate that Vision Transformers can deliver accurate and interpretable decision support for cervical cancer screening by combining competitive classification performance with attention-based transparency relevant to medical AI. Further validation on larger, multi-center datasets remains necessary before clinical deployment.

1 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
Nisreen Nayef Awad AlbzourNisreen Nayef Awad Albzour
Nisreen Nayef Awad Albzour
Fine-grained emotion classification from social-media text is typically evaluated by accuracy and F1, and class imbalance is typically addressed by reweighting the loss or rebalancing the data. This accuracy-centric view, however, overlooks whether a model's confidence can be trusted, a property that matters as much as accuracy when classifiers are deployed in decision-support settings where uncertain cases may be deferred to a human. In this work we compare a Bidirectional Long Short-Term Memory (BiLSTM) network and a distilled transformer, DistilBERT, a compact variant of Bidirectional Encoder Representations from Transformers (BERT), on six-way emotion classification, but reframe the comparison around reliability as a first-class criterion. Beyond accuracy and F1, we evaluate calibration (Expected Calibration Error, ECE), probabilistic quality (negative log-likelihood, NLL), and selective-prediction quality (area under the riskcoverage curve, AURC), under three imbalance-handling strategies (balanced subsampling, class weighting, and focal loss) using a shared data split and five random seeds with paired significance tests. We find that configurations that are statistically indistinguishable on accuracy diverge sharply on reliability: DistilBERT is not only more accurate than BiLSTM but markedly better calibrated, with an ECE roughly 5.6× lower and correspondingly stronger selective-prediction behavior. We further find that on this balanced subset, where the imbalance focal loss is intended to address has already been removed, focal loss yields no significant accuracy benefit while measurably degrading calibration, and that a single post-hoc temperature-scaling step recovers the lost calibration more dependably than any choice of training-time loss. These results argue for treating reliability metrics as standard practice, and post-hoc calibration as a default, in the evaluation of fine-grained emotion classifiers.