Alzheimer’s disease is a neurodegenerative disease leading to memory loss and dementia. Managing this common disease requires early diagnosis and effective treatment strategies. However, Alzheimer’s disease has proven to be extremely complex with diverse etiological factors and extensive biological and clinical heterogeneity. Big biomedical data collected from cases and health controls hold the promise to better diagnosis and treatment, but require powerful computational and statistical methods for addressing disease complexity. This Collection will feature peer-reviewed papers focusing on the development, evaluation, and application of new artificial intelligence methods and software for the analysis of Alzheimer’s disease data. Topics will include:
• Machine learning methods for early Alzheimer’s prediction and diagnosis
• Feature selection methods for reducing data dimensionality
• Methods for interpreting machine learning models of Alzheimer’s
• Methods for improving the fairness of machine learning models
• Automated machine learning methods for expanding access of tools and software
• Large language models for the analysis of text from research or clinical studies of Alzheimer’s
• Deep learning neural network methods for the analysis of brain images from Alzheimer’s patients
• Evolutionary and nature-inspired algorithms for the analysis of Alzheimer’s disease data
• Algorithms and databases for Alzheimer’s knowledge engineering to inform machine learning models
• Evaluation and deployment of machine learning models for the clinical care of Alzheimer’s patients