Temitope Emmanuel Komolafe

Background: Low grade nasopharyngeal papillary adenocarcinoma (LGNPPA) is an exceptionally rare epithelial malignancy of the nasopharynx that can mimic other benign and malignant nasopharyngeal tumors, leading to diagnostic challenges and delayed management. Due to indolent clinical behavior, accurate histopathological and immunohistochemical evaluation is essential for proper treatment planning. Case presentation: An 18-year female presented with five-year history of recurrent epistaxis, nasal obstruction, mucoid rhinorrhea, and hyponasal speech. Endoscopic examination revealed a multilobulated nasopharyngeal mass, and imaging findings suggested a vascular tumor. The patient underwent endoscopic excision of the lesion. Histopathological examinations demonstrated papillary glandular architecture consistent with LGNPPA and immunohistochemistry excluded metastatic disease. The postoperative course was uneventful and no recurrence or metastasis was observed during eight months of follow-up. Conclusion: The case shows that LGNPPA can present with long-standing nasal symptoms and may be clinically mistaken for other nasopharyngeal tumors. The discrepancy between preoperative clinical impression and postoperative pathological diagnosis underscores the importance of histopathological analysis and tailored surgical management for this rare neoplasm. Eight months follow-up shows no recurrence or metastasis; longer follow-up typically ≥ 2 years is recommended to confirm outcomes. Early intervention and complete endoscopic excision can lead to excellent clinical outcomes.

Background: Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality worldwide. Data on Acute exacerbation of COPD (AECOPD) among older adults is scarce. The study aims to assess the impact of early initiation of pulmonary rehabilitation (PR) during hospitalization on exercise capacity, dyspnea, sleep quality, fatigue, and the length of hospital stay in patients with AECOPD. Methods: A single-blind randomised controlled trial. The study took place in the Chest Diseases Department at Alzahraa University Hospital, Cairo, Egypt, between June and September 2025. Subject: 60 patients completed the study, randomised into two equal groups. Group of pulmonary rehabilitation (PR) and control group each included 30patients with a ratio of 1:1. Results: There were notable significant differences between groups; the PR group showed more improvement in walking distance measured by the 6-minute walk distance (6MWD), fatigue, sleep quality, dyspnea, and patients spent less time in the hospital. Our analysis found that fatigue and dyspnea were closely linked and central to patients’ experiences. Dyspnea was a stronger predictor of functional capacity than forced expiratory volume at 1st second (FEV1). Conclusion: Overall, these findings demonstrate that inpatient PR is effective in improving outcomes and physical performance while reducing healthcare utilization in elderly patients with AECOPD.

The increase in population of elderly people across the world is presenting a dauting challenge for palliative cares because elderly people are often encountered health challenges and other chronic diseases. This chapter delves into integration of artificial intelligence (AI)-powered wearable devices into elderly palliative cares. These advanced technologies allow proper monitoring of patient vital signs, track symptoms and adopt predictive analysis to prove patient's outcome. (AI)-powered wearable can monitor disease progression, allow remote monitoring which promote patient autonomy especially at home or hospices settings. We presented a comprehensive framework that include diagnostic and therapeutic advantages, case studies and other ethical issues such data privacy and informed consent. This chapter also present challenges such users' acceptability, we also mentioned other real-world applications such as CardioMEMS, Control-IQ, Sepsis Watch and the rest. We conclude the chapter by providing guidelines and recommendation to sharpen future research

Introduction Accurate detection and staging of dementia are crucial for early intervention and effective patient management. Magnetic resonance imaging (MRI) serves as a valuable diagnostic tool, and deep learning models have the potential to enhance its accuracy and efficiency. Objective This study introduces KARNet, a novel deep-learning framework that integrates the Kolmogorov-Arnold network (KAN) architecture with a modified residual neural network (ResNet-18) and principal component analysis (PCA) to classify four stages of dementia: non-demented, very mild dementia, mild dementia, and moderate dementia. Methods To optimize model performance, we employ transfer learning by modifying a pre-trained ResNet-18 as a feature extractor, followed by a KAN layer as the classifier. PCA is adopted to reduce training time and computational complexity. Additionally, an ablation study and hyperparameter optimization are conducted to evaluate the robustness of the proposed model and improve performance. Results Experimental results demonstrate that KARNet achieves a classification accuracy of 98.5%, outperforming the existing state-of-the-art models. Evaluation on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset confirms its effectiveness in enhancing classification accuracy and model reliability for dementia staging. Conclusion The findings suggest that KARNet is a promising deep-learning framework for the early diagnosis and monitoring of dementia stages using MRI, offering a potential advancement in automated dementia assessment.

This book comprehensively explores the latest technological advancements in healthcare, with a particular focus on the application of cutting-edge technologies, such as artificial intelligence (AI), computer vision, and robotics. The focus extends across crucial domains, such as disease diagnosis and monitoring, medical imaging, and the facilitation of remote healthcare services. The book provides a comprehensive overview of AI techniques for intelligent diagnoses, discussing how machine learning and deep learning models enhance accuracy and speed in medical imaging, diagnostics, and patient care. It also delves into the integration of AI with other disciplines, such as data science, computer vision, edge computing, robotics, and web development, to tackle complex medical challenges. Moreover, it highlights current trends and future prospects in surgery, rehabilitation, neuroscience, and automated healthcare systems, offering valuable insights into the future of technology-driven healthcare solutions. The chapters are authored by researchers and professionals from every region of the globe, including Africa, Asia, the Americas, Europe, and Oceania. This global contribution highlights the versatility and broad perspectives of the shared insights and conclusions presented in the book. This book is an essential guide for healthcare professionals, researchers, and enthusiasts eager to understand and actively contribute to shaping the future of healthcare through the integration of AI and other disciplines.

Medical imaging technology has become an indispensable part of modern clinical diagnosis and disease research. The application of artificial intelligence (AI) in medical imaging analysis has revolutionized healthcare diagnostics and treatment. Computer-aided diagnosis systems, utilizing machine learning algorithms, have significantly enhanced diagnostic accuracy and efficiency, particularly in radiology and pathology. AI techniques, through methods such as image segmentation, classification, and lesion detection, enable rapid and precise marking of abnormal structural areas, thereby reducing the misdiagnosis caused by human subjective factors. Moreover, AI facilitates in-depth analysis of medical information, supporting disease prediction and surgical efficacy assessment. Despite facing challenges such as ethical considerations, regulatory constraints, and data privacy, collaborative interdisciplinary research efforts and responsible AI utilization hold the promise of ushering in a new era of precision medicine, offering more accurate, efficient, and personalized healthcare services for every patient.

Alzheimer’s disease (AD) is a leading cause of disability worldwide. Early detection is critical for preventing progression and formulating effective treatment plans. This study aims to develop a novel deep learning (DL) model, Hybrid-RViT, to enhance the detection of AD. The proposed Hybrid-RViT model integrates the pre-trained convolutional neural network (ResNet-50) with the Vision Transformer (ViT) to classify brain MRI images across different stages of AD. The ResNet-50 adopted for transfer learning, facilitates inductive bias and feature extraction. Concurrently, ViT processes sequences of image patches to capture long-distance relationships via a self-attention mechanism, thereby functioning as a joint local-global feature extractor. The Hybrid-RViT model achieved a training accuracy of 97% and a testing accuracy of 95%, outperforming previous models. This demonstrates its potential efficacy in accurately identifying and classifying AD stages from brain MRI data. The Hybrid-RViT model, combining ResNet-50 and ViT, shows superior performance in AD detection, highlighting its potential as a valuable tool for medical professionals in interpreting and analyzing brain MRI images. This model could significantly improve early diagnosis and intervention strategies for AD.