Breast cancer detection through mammography interpretation remains difficult because of the minimal nature of abnormalities that experts need to identify alongside the variable interpretations between readers. The potential of CNNs for medical image analysis faces two limitations: they fail to process both local information and wide contextual data adequately and do not provide explainable AI (XAI) operations which doctors need to accept them in clinics. The researcher developed the MammoFormer framework which unites transformer-based architecture with multi-feature enhancement components and XAI functionalities within one framework. Seven different architectures consisting of CNNs, Vision Transformer, Swin Transformer, and ConvNext were tested alongside four enhancement techniques, including original images, negative transformation, adaptive histogram equalization, and histogram of oriented gradients. The MammoFormer framework addresses critical clinical adoption barriers of AI mammography systems through: (1) systematic optimization of transformer architectures via architecture-specific feature enhancement, achieving up to 13% performance improvement, (2) comprehensive explainable AI integration providing multi-perspective diagnostic interpretability, and (3) a clinically deployable ensemble system combining CNN reliability with transformer global context modeling. The combination of transformer models with suitable feature enhancements enables them to achieve equal or better results than CNN approaches. ViT achieves 98.3% accuracy alongside AHE while Swin Transformer gains a 13.0% advantage through HOG enhancements. Five XAI techniques, including Integrated Gradients, GradCAM, Occlusion, DeepLIFT and Saliency maps demonstrate that transformer models effectively recognize diagnostically significant features by capturing long-range dependencies in mammograms. Using HOG features provides the most reliable enhancement impact (98.4% average accuracy) among all visualization methods. MammoFormer establishes a clinical breast cancer screening workflow with diagnostic precision and interpretability through its simultaneous implementation of architectural design with feature enhancement and explainability features.

As the day unfolds, we can no longer overemphasize on the negative impact of fake drugs in under-developed countries and in the whole world at large. The healthcare system has greatly been negatively affected by the illegal production of counterfeit drugs which results compromised patient safety, waste of money for healthcare, and causing lack of trust on the healthcare system in place. In this chapter on personalising medicine for fake drug prevention with AI-driven Digital Twin, digital twins are emerging as powerful tools. The virtual patient models combine multimodal data, such as clinical, genomic, and imaging information, in order to simulate an individual's health trajectory and response to treatment.

This study aimed at exploring the integration of artificial intelligence in English as a Foreign Language learning and how it has changes conventional pedagogical practices in the field of education. It examines how AI-driven speech synthesis can personalize the EFL learning experience, enhance language proficiency, and foster greater learner autonomy. By analysing the underlying technologies, pedagogical applications, and ethical considerations, the chapter seeks to bridge the gap between technological potential and practical implementation in EFL classrooms.

This paper is an exploratory study that looks at how teaching and learning are affected by higher generative artificial intelligence (HGAI) models, notably ChatGPT-4, ChatGPT-4.5 and the anticipated ChatGPT-5. With the ability to produce more dynamic and individualized learning environments, it contends that these models represent a critical turning point for educational technology. The study examines the benefits and drawbacks of ChatGPT in the classroom, taking into account how it might improve students' critical thinking and problem-solving skills. It also suggests strategies for educators and policymakers to maximize its use in accordance with the sustainable development goals for education. The study discusses safe and beneficial ways to use these new HGAI technologies to improve education and advance students' learning. It also provides suggestions on how policymakers, teachers, scholars, and tech experts could use ChatGPT to maximize teaching and learning in order to improve STEM education and achieve Sustainable Development Goals on Education.

Early warning of failure would let costly episodes of large language model (LLM) agents be stopped early. Across five model families and five task domains (3421 usable rollouts), we study a black-box signal: the divergence of a rollout’s judged goal progress from sibling rollouts of the same task after k steps. Under our original judging protocol, cohort divergence predicted failure (pooled AUROC 0.73 in retail). A judge swap revealed that the judge had received a task identifier in place of the task objective. After re-judging with the correct objective, the cohort signal fell to chance in retail and airline (0.47 to 0.52), and a single-rollout judge score had the higher point estimate in eight of ten combinations of domain and horizon. In paired contrasts, before adjustment for multiple comparisons, cohort divergence was significantly worse in two and better in one. Of three pre-specified failure-onset profiles, one met its criterion under the original protocol and none under the corrected one. Task-preserving perturbations produced no detectable amplification of divergence. In an abort simulation, under the stated cost assumptions, the cohort monitor lost tokens for every model, and the judge monitor saved tokens for two of five and had no usable operating point for the other three. Judge instructions are thus a first-order threat to validity in agent-monitoring research.