The analysis of pooled cross-sectional data plays a vital role in various disciplines, including epidemiology, economics, and the social sciences, by enabling the identification of trends and patterns over time. This study develops statistical models specifically designed to analyze pooled cross-sectional data while accounting for measurement error, with a particular focus on estimating the prevalence of malnutrition among children under five years of age in Cameroon. Measurement error is a persistent issue in surveys, especially in resource-limited settings where data collection accuracy may be compromised. To address this, the research employs logistic regression within a Bayesian framework to reduce the impact of measurement error on malnutrition prevalence estimates, thereby providing more reliable information for policymakers and public health professionals. Through both simulation studies and application to real-world data from Cameroon, the study demonstrates the effectiveness of the proposed models in improving the accuracy and precision of estimates, offering deeper insights into childhood malnutrition in the country. This work advances statistical methodologies for survey data analysis by providing robust tools to address measurement error and support evidence-based interventions to combat malnutrition in Cameroon and similar contexts worldwide.

Diabetic Retinopathy (DR) is a leading complication of prolonged diabetes, which poses a significant threat to vision and may lead to permanent blindness. Early identification and timely intervention are crucial to preventing disease progression. Traditionally, DR diagnosis relies on medical examination of retinal fundus images by expert ophthalmologists, which is time-consuming and resource intensive. However, deep learning techniques, particularly medical imaging, have demonstrated remarkable performance in the automated detection and classification of DR. This study proposes an ensemble-based deep learning framework using feature-level fusion stacking, which integrates four complementary convolutional neural networks named ReXInDen and three complementary convolutional neural networks named ReXDen for automated DR detection from retinal fundus images. These frameworks extract high-level features from each backbone, concatenate them into a unified representation, and classify using a feedforward neural network. Three datasets were utilized to validate the model including a region-specific dataset collected from Bangladeshi medical sources. The proposed ReXInDen model achieved accuracies of 98.27%, and 98.69% on Dataset 1 and Dataset 2, while ReXDen achieved the highest accuracy of 99.05% on Dataset 3. These results indicate a substantial improvement over individual models and demonstrate the potential of the ensemble approach to support early-stage DR detection. Moreover, these models show promise for integration into automated DR screening tools that can aid in reducing the global burden of diabetic vision loss. • Develop an ensemble method combining different convolutional models for medical image-based diagnosis. • Apply advanced image filtering techniques to improve retinal image clarity before analysis. • Merge features from multiple models and classify them using a feedforward neural network. • Validate the method using three datasets, including one from local healthcare providers. • Achieve 99.05 percent accuracy with the ensemble method on the combined dataset.

Brain tumor segmentation remains a significant challenge in medical image analytics due to the limited ability of current models to detect small lesions, capture spectral information, and represent anatomical context effectively. This study introduces the Frequency-Quantum-Graph Network (FQG-Net), an analytical framework that integrates quantum computing principles, adaptive frequency-domain processing, and graph-based contextual learning to enhance segmentation precision. The model employs quantum entanglement and superposition effects to enrich feature representation, an adaptive frequency enhancement mechanism to amplify tumor-specific spectral characteristics, and a graph neural contextual memory to preserve spatial and anatomical relationships. Multimodal MRI data are processed through selective quantum residual blocks that dynamically activate network components based on analytical requirements, ensuring both efficiency and stability. Empirical evaluations across multiple benchmark datasets demonstrate that FQG-Net delivers consistent improvements over state-of-the-art segmentation models, achieving higher accuracy, stronger generalization across datasets, and superior performance in detecting small and heterogeneous tumor regions. These findings highlight the analytical strength of quantum-enhanced deep learning and its potential to advance precision diagnostics in healthcare imaging. • Present an analytical model combining quantum learning and graph memory for brain tumor segmentation. • Develop an adaptive frequency module to enhance tumor feature detection in medical imaging. • Integrate quantum attention with contextual graph learning for precise lesion identification. • Employ multimodal imaging analytics to improve diagnostic accuracy and generalizability. • Demonstrate consistent cross-dataset performance, validating robustness in clinical analytics.

Medical students experience disproportionately high rates of depression due to intense academic pressures and clinical demands. Without timely, targeted intervention, they face increased risks of academic underperformance and adverse outcomes. Existing predictive models often adopt a one-size-fits-all approach to predict depression for the entire student population. This approach may perform poorly for sparsely represented subgroups, such as medical students. To address this limitation, we propose a hierarchical Bayesian predictive model that estimates medical students’ depression severity, even when medical students comprise only a small fraction of the overall dataset. Our hierarchical Bayesian modeling framework generalizes across subgroups via partial pooling, offering a novel analytical contribution to healthcare modeling in which subgroup imbalance is prevalent. Based on data from nearly 168,000 students, our model reduces the mean absolute error of predictions by at least 31% compared to baseline models, including XGBoost and deep neural networks. Statistical analysis using Wilcoxon Rank-Sum Tests with Bonferroni correction across more than 650 previously unseen medical students confirms that our model's performance is significantly superior to established baselines. Beyond improved predictive accuracy, our model identifies key depression-related stressors, including financial hardship, international student status, smoking frequency, and eating disorders. Accurate predictions and identified stressors help clinicians and academic administrators to recognize at-risk medical students and deliver timely, targeted interventions. • Propose a hierarchical Bayesian model to forecast depression severity in medical students. • Apply partial pooling to improve predictions for underrepresented student groups. • Reduce prediction error by over 31% compared to standard machine learning models. • Identify key healthcare-related risk factors influencing depression severity. • Enable tailored interventions through stratified analysis for depression mitigation and prevention.

Traumatic brain injury (TBI) requires timely and reliable severity assessment to support critical clinical decision-making. This study proposes an interpretable machine learning framework for TBI severity prediction using two datasets: the public HPTBI dataset and a newly developed 103_TBI dataset comprising 504 patients. After data preprocessing and feature selection, ensemble learning models-particularly Random Forest and XGBoost-achieved accuracies exceeding 94%. To enhance transparency and clinical trust, we introduce a dual-layer interpretability strategy that integrates post-hoc explanation techniques (SHAP, LIME, PFI, PDP, and counterfactual analysis) with a knowledge-graph-based evaluation of feature interactions. The attribution methods show high agreement ( c o r r e l a t i o n > 0 . 91 ) and consistently identify key clinical predictors such as the Glasgow Coma Scale (GCS), midline shift, and pulse rate. These insights align closely with expert judgment, supporting the clinical credibility of the model explanations. Additionally, the knowledge graph reveals multivariate relationships critical to outcome determination. By integrating predictive models with clinical interpretability techniques, the proposed framework offers reliable clinical support to assist neurotrauma triage and expert validation. This work therefore demonstrates the potential of integrating explainable AI with domain knowledge to advance TBI severity prediction. • Develop an interpretable ML framework to assess traumatic brain injury severity. • Integrate clinical, imaging, and laboratory data to enhance predictive accuracy. • Apply ensemble learning and data balancing to improve model performance reliability. • Combine interpretability tools with knowledge graph for transparent decisions. • Identify critical predictors (GCS and midline shift) to support clinical triage