The healthcare sector faces intricate challenges that demand innovative solutions to enhance patient outcomes and streamline operations. The advent of Artificial Intelligence (AI) has unleashed groundbreaking potential in numerous healthcare domains, including diagnostics, patient care, and disease management. This study explores the incorporation of AI-driven methodologies for the advanced monitoring of diabetes and kidney diseases. It underscores the development of predictive models that utilize six Machine Learning (ML) and four deep learning (DL) models: Our comprehensive data analysis and rigorous model evaluation showcase AI’s capability to significantly enhance clinical practices, fostering a proactive healthcare environment marked by precision, personalization, and predictive care. Our results demonstrate substantial enhancements in the accuracy of disease monitoring. For diabetes prediction, the Gradient Boosting (GB) and Random Forest (RF) models achieved up to 89.61% accuracy, while the hybrid LSTM+CNN model outperformed other DL models with an accuracy of 89.7%. For kidney disease prediction, the RF model reached 97.5% accuracy, and the LSTM-CNN model demonstrated a remarkable accuracy of 98.9%. These findings underscore the transformative potential of AI in healthcare, fostering a proactive environment characterized by precision, personalization, and predictive care. Integrating AI within CURA’s virtual wards facilitates earlier disease detection and timely interventions and enables more tailored treatment plans, ultimately optimizing healthcare delivery and patient management.

Internet and communication technologies have been growing at a rapid pace, enabling data sharing and many other applications. Online trading and e-commerce are important applications that provide ease of business as well as flexibility for buyers. In this paper, we provide an overview of social commerce (s-commerce) in the context of Saudi Arabia. This paper explains s-commerce, the background of Saudi Arabia, and its digital economy vision. This paper also highlights the importance of social media and networking, as well as novel web technologies for s-commerce. We also highlight the research gap in the analysis of s-commerce potential in the Saudi market. This paper conducts a detailed analysis of s-commerce in Saudi Arabia based on a sequential explanatory research design with a quantitative and qualitative phase. The quantitative phase involves a survey based on 504 responses. The qualitative phase involves interview questions of 25 participants. Based on this study, seven themes (each with two or more factors) to enhance s-commerce in Saudi Arabia were identified. Finally, future opportunities and challenges are also discussed in detail.

The growing incidence of agricultural fires in arid and semi-arid regions necessitates the development of advanced, scalable systems for early detection. This study presents FlameGuard, a geospatial AI framework developed to classify fire confidence levels using thermal satellite imagery-based data from the FIRMS dataset and multi-model predictive architectures. The framework integrates a spectral rule-based model—Spectral Algorithm for Fire Detection (SAFD)—with machine learning and deep learning classifiers. Baseline models demonstrated strong performance, with Random Forest achieving 97.41% accuracy (\(\hbox {F1}=0.953\)), XGBoost 98.20% (\(\hbox {F1}=0.961\)), and the Keras neural network 99.10% (\(\hbox {F1}=0.980\)). Transformer-based large language models (LLMs) further advanced this benchmark: Minos reached 100% accuracy (F1 = 0.993) and ViRanker 99.63% (\(\hbox {F1}=0.982\)). The ablation study confirmed that removing multi-sensor data (MODIS or VIIRS) or preprocessing components reduced performance by up to 3–4%, underscoring the synergy between satellite fusion and optimized pipelines. Ten-fold cross-validation validated the superior calibration and reliability of LLMs (Expected Calibration Error, ECE \(\approx\) 0.031), with efficient training (\(\approx\)78.5 s) and real-time inference (\(<0.36\) s). Comparative analysis revealed that FlameGuard surpassed NASA’s FIRMS (75% accuracy, 3–6 h latency), MODIS fire alerts (70%, 4–6 h), and recent research (88–94%), achieving 99% accuracy, sub-hour detection latency, and IoT-ground-truth validation. All models were deployed within the FlameGuard smart map interface, enabling real-time visualization of fire risks, thermal anomalies, and confidence levels. The platform delivers interpretable, high-precision analytics to support proactive environmental monitoring and early response planning in fire-prone agricultural regions.