This review explores the use of neuroimaging and artificial intelligence (AI), including machine learning (ML), for early Alzheimer’s disease (AD) detection. The authors work to assess biomarkers and detection methods, analyzing gaps in current research. The review covers studies from 2013 to 2022, focusing on AI, ML, and statistical modeling applied to MRI and PET scans for early AD diagnosis. It emphasizes the importance of understanding AD’s onset and progression, marked by amyloid-beta and tau protein accumulation, and differentiates between early-onset AD and late-onset AD based on age and symptoms.

The study also examines the use of neuroimaging techniques like EEG, MRI, and PET in identifying AD biomarkers, highlighting the significance of MRI-derived volumetric biomarkers and PET scan molecular markers in distinguishing AD from other conditions. Additionally, the authors discuss the value of longitudinal data analysis with neuroimaging for tracking AD over time. The paper concludes by underscoring the need for further research in advanced neuroimaging biomarkers, enhanced data preprocessing, feature extraction, and more precise and dependable AI and ML models for early AD detection.

Reference: Aberathne I, Kulasiri D, Samarasinghe S. Detection of Alzheimer’s disease onset using MRI and PET neuroimaging: longitudinal data analysis and machine learning. Neural Regen Res. 2023;18(10):2134-2140. doi: 10.4103/1673-5374.367840.