St. Louis Community College

Abstract Childhood diarrheal disease remains a leading cause of morbidity and mortality among children under five years in sub-Saharan Africa, particularly in settings affected by inadequate sanitation, climate variability, malnutrition, and limited healthcare access. Conventional forecasting approaches are often constrained by sparse surveillance data, weak spatial representation, and limited incorporation of mechanistic disease dynamics. This study presents a Physics-Informed Multimodal Artificial Intelligence Digital Twin framework that integrates Physics-Informed Neural Networks, Graph Neural Networks, diffusion-reaction epidemiological modeling, multimodal fusion learning, and Digital Twin simulation to estimate and predict childhood diarrheal disease burden in Kenya, Somaliland, and Zimbabwe. Using public epidemiological, environmental, climate, sanitation, and synthetic proof-of-concept datasets, the framework modeled temporal disease dynamics, spatial transmission, pathogen-attributed burden, and outbreak trajectories while enforcing epidemiological consistency through physics-informed optimization. Results demonstrated robust forecasting performance, enhanced spatial transmission modeling, uncertainty-aware predictions, and realistic outbreak simulations across the three countries. Rotavirus, Shigella, and Cryptosporidium were identified as major contributors to modeled mortality burden, while unsafe water exposure, poor sanitation, malnutrition, and climate-sensitive transmission substantially increased disease risk. Compared with a Bayesian baseline model, the multimodal framework achieved superior nonlinear risk characterization, geospatial learning, and temporal prediction. These findings highlight the potential of scientific machine learning and digital twin systems for infectious disease surveillance, outbreak forecasting, climate-health analytics, and evidence-based public health decision-making in low-resource African settings.

This study examined student perspectives on flipped learning (FL), a pedagogy that shifts lectures outside the classroom to promote active, hands-on engagement during class. Twenty-four Science, Technology, Engineering, and Mathematics (STEM) faculty members from a 4-year university and a 2-year community college implemented FL after receiving professional development. The research employed a longitudinal quasi-experimental design, tracking the implementation of FL over a 4-year period. A sample of 1,466 students enrolled in these flipped courses provided feedback via end-of-course surveys. Survey data were analyzed using ordinal logistic regression to assess the impact of gender, race/ethnicity, institution type, and academic level on FL perceptions. Results revealed variations across demographics: male respondents expressed higher confidence, whereas nonbinary students strongly endorsed FL across metrics. Female students admitted having higher engagement and favorable classroom environments. The highest levels of positive perception were observed among Asian students, and non-White and senior-level (fourth-year) students reported stronger agreement on FL benefits. Perceptions were more favorable in the 2-year institution, highlighting FL’s unique impact in this environment. Overall, FL was positively associated with increased engagement and confidence across diverse student groups, suggesting that the model is a vital, resilient, and inclusive framework for STEM education.

Abstract Objectives: To develop and evaluate a deployable deep learning system with Gradient-weighted Class Activation Mapping (Grad-CAM) for tuberculosis screening from chest radiographs and to assess its classification performance and explainability across desktop and mobile deployment platforms. Materials and methods: This study used publicly available chest X-ray datasets containing Normal and Tuberculosis images. A DenseNet121-based transfer learning model was trained using stratified training, validation, and test splits with data augmentation and class weighting. Model performance was evaluated using accuracy, precision, recall, F1 score, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC). Grad-CAM was used to visualize regions influencing model predictions. The trained model was converted to TensorFlow Lite and deployed in both a Windows desktop application and a Flutter-based mobile application for offline inference and visualization. Results: The model demonstrated strong classification performance on the independent test dataset, with high accuracy and AUC values indicating effective discrimination between Normal and Tuberculosis cases. Grad-CAM visualizations showed that the model focused primarily on anatomically relevant lung regions, particularly the upper and mid-lung fields in Tuberculosis cases. Deployment testing confirmed consistent prediction outputs and Grad-CAM visualizations across both Windows and mobile platforms. Conclusion: The proposed deployable deep learning system with Grad-CAM provides accurate and interpretable tuberculosis screening from chest radiographs and demonstrates feasibility for offline mobile and desktop deployment. This approach has potential as an artificial intelligence-assisted screening and decision support tool in radiology, particularly in resource-limited and remote healthcare settings. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This research received no external funding. The study was conducted using institutional and personal resources, and no financial support was received from any funding agency, commercial entity, or non-profit organization. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes The datasets used and analyzed in this study are publicly available from Kaggle and can be accessed at: https://www.kaggle.com/. The original contributions presented in this study are included in the article and its Supplementary Material. Further inquiries can be directed to the corresponding author.

Abstract Background Accurate estimation of childhood diarrheal disease burden in Africa remains challenging because of limited surveillance, incomplete mortality data, pathogen-attribution uncertainty, and complex environmental and socioeconomic drivers. This study developed the African Diarrheal Disease Integrated Risk Intelligence and Burden Estimation Architecture (AFRIDIARRHEA), a multimodal fusion framework for estimating under-five diarrheal burden in resource-constrained settings. Methods AFRIDIARRHEA integrates Bayesian epidemiological modeling, machine learning, temporal forecasting, geospatial analytics, pathogen attribution, environmental intelligence, and uncertainty quantification within a unified framework. Synthetic datasets representing Kenya, Zimbabwe, and Somaliland were used to evaluate mortality, morbidity, hospitalization burden, pathogen-attributed mortality, and predictive performance. Results The framework identified substantial heterogeneity in disease burden across countries, with Zimbabwe exhibiting the highest modeled mortality and morbidity burden and Somaliland the highest hospitalization burden. Rotavirus and Shigella were the dominant contributors to pathogen-attributed mortality. The multimodal fusion model outperformed the Bayesian baseline and individual component models, achieving improved predictive accuracy, robust uncertainty calibration, and strong agreement with benchmark estimates. Conclusions AFRIDIARRHEA demonstrates the potential of multimodal fusion modeling for integrated estimation of childhood diarrheal burden, pathogen attribution, and uncertainty in African settings. The framework provides a scalable, transparent, and policy-relevant approach for supporting vaccine prioritization, WASH investments, outbreak preparedness, and child survival programs in data-limited environments.

Green synthesis of silver nanoparticles (AgNPs) offers an environmentally sustainable approach for producing functional nanomaterials, yet optimization of synthesis conditions remains challenging because transport phenomena, reduction chemistry, and nanoparticle growth are strongly coupled. This study presents a Physics-Chemistry-Materials-Informed Neural Digital Twin (PCMINN-DT) that integrates a Physics-Informed Neural Network (PINN) for diffusion-reaction transport, a Chemistry-Informed Neural Network (ChINN) for phytochemical-mediated silver-ion reduction kinetics, and a Materials-Informed Neural Network (MINN) for nanoparticle growth and aggregation within a unified scientific machine-learning framework. The informed neural modules are coupled to a digital twin incorporating Monte Carlo uncertainty propagation, virtual UV-Vis, DLS, XRD, and FTIR characterization, and multi-objective optimization for synthesis design. The framework was developed and evaluated using synthetic physics-consistent datasets to systematically assess its scientific consistency, predictive capability, and digital-twin performance prior to experimental calibration and validation. The results demonstrate that the integrated framework accurately enforces governing physical, chemical, and materials-science constraints while predicting nanoparticle size, aggregation tendency, silver-ion release, reactive oxygen species generation, and antibacterial performance. Monte Carlo analysis indicates robust predictive behavior under simulated process variability, and autonomous optimization identifies synthesis conditions that maximize predicted antibacterial activity and colloidal stability while minimizing aggregation and toxicity. The proposed framework establishes a scalable foundation for AI-guided nanoparticle engineering and provides a pathway toward experimentally calibrated digital twins for sustainable nanomaterials design.