Background: From the beginning of 2020, COVID-19 infection has changed our lives in many aspects and introduced limitations in the way people interact and communicate. In this paper, we are evaluating the effect of non-pharmaceutical interventions (NPI) in limiting the spread of the Severe Acute Respiratory Syndrome Coronavirus 2 pandemic during a wedding ceremony from Irbid, Northern Jordan. Agent-based modeling was used in a real wedding event that occurred at the beginning of the spread of the pandemic in Jordan. Two infected nationals of Jordan, who arrived in Jordan about a week before the event, initiated the spread of the pandemic within the contact community. Methods: In this work, a strict national NPI that the government implemented is developed by using an abstract model with certain characteristics similar to the Jordanian community. Thus, the Jordanian community is represented in terms of ages, occupations, and population movements. After that, the extent of the impact of the NPI measures on the local community is measured. Results: We observed the deterioration of the state of society while the epidemic is spreading among individuals in the absence of preventive measures. Also, the results show that the herd immunity case was an epidemic, with a high level of spread among the community with 918 cases during a short interval of time. On the other hand, the preventive measures scenario shows a totally controlled spread with only 74 cases applied on the same interval of time. Furthermore, a convergence in the actual results of the real system with the hypothetical system were detected in the case of applying the strict NPI measures. Finally, strict NPI at the community level following social gatherings seem to be effective measures to control the spread of the COVID- 19 pandemic.

Background: Distinguishing vitiligo from postinflammatory hypopigmentation (PIH) is clinically challenging because both conditions may present with similar depigmented lesions. Although deep learning has shown strong potential for dermatologic image classification, limited interpretability remains a barrier to clinical adoption. Objective: This study aimed to develop an interpretable deep learning framework for accurate differentiation between vitiligo and PIH using a lightweight convolutional neural network and an ensemble of explainability methods. Methods: A total of 332 clinical images (176 vitiligo and 156 PIH) were collected from King Abdullah University Hospital and publicly available online sources. Images were preprocessed and evaluated using patient-wise 5-fold cross-validation to eliminate patient-level data leakage. A pretrained MobileNetV2 model was fine-tuned by unfreezing the final 30 layers. To enhance interpretability, gradient-weighted class activation mapping (Grad-CAM), integrated gradients, and smooth gradients (SmoothGrad) were combined into an equal-weight ensemble explanation framework. Performance was assessed using accuracy, precision, recall, F ₁ -score, and the area under the receiver operating characteristic curve (AUC). Results: The proposed model achieved an overall accuracy of 94.88%, macroaveraged precision of 94.88%, recall of 94.84%, F ₁ -score of 94.86%, and an AUC of 0.9885 across the 5 validation folds. The ensemble framework produced clinically meaningful explanations in 98.48% of a representative 66-image validation subset used for interpretability analysis. Conclusions: The proposed framework combines high diagnostic performance with robust interpretability for distinguishing vitiligo from PIH. By integrating multiple complementary explanation methods, the approach enhances clinical transparency and may support dermatologists in the differential diagnosis of pigmentary disorders.

The rapid emergence of COVID-19 resulted in a pandemic that affected the well-being of millions of people. This research aims to help hospitals in Jordan forecast the prognosis of COVID-19 patients at the early stages using machine learning algorithms, which can promote their ability to build and assess strategic planning and decision making. We applied several machine learning algorithms to predict the prognosis of the admitted COVID-19 patients at early stages and classify the infected cases according to their severity of illness and other factors and then recommend the appropriate level of care, including ICU, intermediate, or general floor, using objective measures without any subjective evaluation by physicians. A total of 153 COVID-19 patient records were collected from King Abdullah University Hospital (KAUH), including demographics, comorbidities, length of stay, laboratory tests, chest x-ray severity score, and level of care. The results demonstrate that the highest F1-score was achieved by the XGB classifier (99% on average across different levels of care, followed by the gradient boosting classifier and SVM (97% and 96.6% respectively. In conclusion, our research can help reduce medical errors and improve patient safety. Additionally, it can significantly reduce the length of stay of patients.