Artificial Intelligence Role in Advancement of Human Brain Connectome Studies Publisher

Summary: AI enhances brain connectome studies, aiding early diagnosis of neurological diseases, but data bias limits use, review finds. #BrainHealth #AIResearch

Shekouh D¹ ; Sadat Kaboli H² ; Ghaffarzadehesfahani M³ ; Khayamdar M⁴ ; Hamedani Z⁵ ; Oraeeyazdani S⁶ ; Zali A⁶ ; Amanzadeh E⁶
Source: Frontiers in Neuroinformatics Published:2024

Abstract

Neurons are interactive cells that connect via ions to develop electromagnetic fields in the brain. This structure functions directly in the brain. Connectome is the data obtained from neuronal connections. Since neural circuits change in the brain in various diseases, studying connectome sheds light on the clinical changes in special diseases. The ability to explore this data and its relation to the disorders leads us to find new therapeutic methods. Artificial intelligence (AI) is a collection of powerful algorithms used for finding the relationship between input data and the outcome. AI is used for extraction of valuable features from connectome data and in turn uses them for development of prognostic and diagnostic models in neurological diseases. Studying the changes of brain circuits in neurodegenerative diseases and behavioral disorders makes it possible to provide early diagnosis and development of efficient treatment strategies. Considering the difficulties in studying brain diseases, the use of connectome data is one of the beneficial methods for improvement of knowledge of this organ. In the present study, we provide a systematic review on the studies published using connectome data and AI for studying various diseases and we focus on the strength and weaknesses of studies aiming to provide a viewpoint for the future studies. Throughout, AI is very useful for development of diagnostic and prognostic tools using neuroimaging data, while bias in data collection and decay in addition to using small datasets restricts applications of AI-based tools using connectome data which should be covered in the future studies. Copyright © 2024 Shekouh, Sadat Kaboli, Ghaffarzadeh-Esfahani, Khayamdar, Hamedani, Oraee-Yazdani, Zali and Amanzadeh.