Search

Alzheimer's disease (AD) is the most common cause of dementia, marked by cognitive decline and memory loss. Recently, machine learning and deep learning techniques have introduced promising solutions for improving AD detection through MRI, especially in settings where specialists may not be readily available. These techniques offer the potential to assist general practitioners and non-specialists in busy clinical environments. However, the 'black box' nature of many AI techniques makes it challenging for non-expert physicians to fully trust their diagnostic accuracy. In this review, we critically evaluate current explainable AI (XAI) methods applied to AD detection and highlight their limitations. In addition, a new interpretability framework, called "Feature-Augmented", was theoretically designed to improve model interpretability. This approach remains underexplored, primarily due to the scarcity of explainable AD-specific datasets. Furthermore, we underscore the importance of AI models being accurate and explainable, which enhance diagnostic confidence and patient care outcomes. [ABSTRACT FROM AUTHOR]

Background/Aims: This study aimed to identify, clinically and molecularly, the causality of Rabson-Mendenhall syndrome in an Emirati family. It is one of the monogenic syndromes of abnormal glucose homeostasis, which result from insulin receptor defects. Methods: A novel nonsynonymous variant in the INSR gene was uncovered by whole exome sequencing and confirmed using Sanger sequencing in the patient and his parents. Various in silico tools were utilized to analyze the functional consequences of the variant. Results: Results revealed a previously unreported INSR variant in the family: c.421C>T (p.Arg141Trp). Homozygosity for the variant was found in the patient, while both parents were heterozygous. Conclusion: The nonsynonymous protein change hit a highly conserved arginine residue in the insulin-binding α-subunit of the receptor and was deemed 'functionally damaging' by a myriad of bioinformatics tools. This report is a step forward along the way of achieving a better molecular and clinical characterization of Rabson-Mendenhall syndrome. [ABSTRACT FROM AUTHOR]

e-Learning, of late, has been witnessing an unprecedented expansion as an opportunity for higher education. This expanding alternative mode calls for ensuring and imparting a sound and qualitative education. So the present case study made an attempt to discuss key aspects of a quality management model for eLearning currently operating at the University of KKU and illustrates the issues related to the quality dimensions of e-learning. Some of these dimensions are: learning process, administrative processes, teaching materials, resources and SWOT (Strengths, Weakness, Opportunities, Threats) analysis etc. This study reiterates the relevance of imparting qualitative education through e-learning for quality improvement in ways that facilitate how staff are empowered and supported to develop meaningful eLearning resources for students, how quality improvement is managed, and how organizational learning takes place. The findings of the study further demonstrate that if the concept of e-learning is imparted with a better approach and perspective, the reach will be phenomenal. [ABSTRACT FROM AUTHOR]

The WDR62 gene encodes a scaffold protein of the c- Jun N-terminal kinase ( JNK) pathway. It plays a critical role in laying out various cellular layers in the cerebral cortex during embryogenesis, and hence the dramatic clinical features resulting from WDR 62 mutations. These mutations are associated with autosomal recessive primary microcephaly 2, with or without cortical malformations ( MCPH2). Using whole exome sequencing we uncovered a novel WDR 62 variant; c.390G > A, from two Sudanese siblings whose parents are first cousins. The patients suffered MCPH2 with incomplete lissencephaly and developmental delay. The mutation affects the last nucleotide of exon4, and probably leads to aberrant splicing, which may result in a truncated protein lacking all functional domains. [ABSTRACT FROM AUTHOR]