Machine learning for the early diagnosis and multimodal profile of Alzheimer's disease based on miRNA of circulating exosomes

Machine learning for the early diagnosis and multimodal profile of Alzheimer's disease based on miRNA of circulating exosomes

Identifying new blood biomarkers to detect the risk to develop AD in the early stages is pivotal and necessary to i) carry out massive early diagnosis at low cost and ii) develop preventive treatments that delay the presentation of the first symptoms of the disease. Moreover, exosomes are being used as a biomarker source due to small vesicles able to cross the blood-brain barrier transporting proteins and microRNAs (miRNA). It has been shown that several miRNAs can modulate genes related to AD pathology which highly suggest that brain alterations could be studied by using miRNA extracted from circulating exosomes. Additionally, this strategy will be used as a screening method to early detection, safe, massive, and low-cost to AD in the Chilean population. On the other hand, machine learning will provide us a set of tools for the analysis and interpretation of patterns and data structures of miRNA. Here, we hypothesize that the algorithm developed through machine learning tools using a panel of miRNA extracted from circulating exosomes, predicts the risk of developing AD in the Chilean population and its multimodal characterization.

Director: Claudia Duran-Aniotz
Support: ANID/Fondef

Social Media
Instagram