AI for Neurodegenerative Experimental Models: Advancements and Applications

To develop powerful disease models, one has to appreciate the brain, but so many human research failures take place and translation of ideas and medicines found in model systems has been extraordinarily difficult. Here we describe how ML and AI techniques using machines and intelligent machines have been applied in unconventional therapies to study a particular dementia. We outline universal difficulties in replication and translation from human to diverse other species or to hypothetical systems in translational cognitive research, and we stress tools and best practices that may be used to measure and assess them. Ultimately, we look at how, in moving toward more natural interpretation, the use of AI and ML techniques could serve as additional enhancers for cross-model repeatability and translation to human biology. AI and ML techniques, when applied to unconventional medicine, are far from mature, but if built upon sufficient reliable and repeatable experimental evidence, they hold out a huge amount of promise to advance early studies and subsequent translation. Artificial Intelligence has brought a revolutionary change to model development and its analysis in neurodegenerative diseases research. More precisely, these diseases, which are described as Alzheimer’s, Parkinson’s, and Amyotrophic Lateral Sclerosis, show such complex challenges due to their multifactorial etiology and heterogeneous pathologies. Traditional experimental models, in the form of animal and cellular models, have been crucial for unpacking these conditions but still often are ineffective at fully capturing their full complexity.