Resting-State fMRI and Machine Learning as Diagnostic Tools for Alzheimer's Disease DOI Open Access
Sajjad Iraji,

Fateme Darvishzadeh Mahani,

Hojjat M Dikdaragh

et al.

Annals of Military and Health Sciences Research, Journal Year: 2024, Volume and Issue: 22(2)

Published: Aug. 19, 2024

: Alzheimer's disease (AD) presents a significant challenge in healthcare, necessitating accurate and timely diagnosis for effective management. Resting-state functional magnetic resonance imaging (Rs-fMRI) has emerged as valuable tool understanding neural correlates the early detection of AD. This article reviews recent advancements utilizing Rs-fMRI combination with machine learning (ML) techniques AD diagnosis. First, we discuss underlying principles Rs-fMRI, highlighting its ability to detect alterations brain connectivity (FC) patterns associated We then explore potential ML algorithms, particularly support vector machines (SVMs), analyzing data discriminating between patients healthy controls. indicate challenges opportunities integrating ML, such preprocessing, feature selection, model interpretation. also address importance large-scale, multi-site studies validate robustness generalizability proposed approaches. Overall, integration holds great promise non-invasive, objective, sensitive diagnostic AD, potentially enabling personalized treatment strategies. However, further are warranted optimize methodologies, enhance interpretability, facilitate clinical translation.

Language: Английский

Resting-State fMRI and Machine Learning as Diagnostic Tools for Alzheimer's Disease DOI Open Access
Sajjad Iraji,

Fateme Darvishzadeh Mahani,

Hojjat M Dikdaragh

et al.

Annals of Military and Health Sciences Research, Journal Year: 2024, Volume and Issue: 22(2)

Published: Aug. 19, 2024

: Alzheimer's disease (AD) presents a significant challenge in healthcare, necessitating accurate and timely diagnosis for effective management. Resting-state functional magnetic resonance imaging (Rs-fMRI) has emerged as valuable tool understanding neural correlates the early detection of AD. This article reviews recent advancements utilizing Rs-fMRI combination with machine learning (ML) techniques AD diagnosis. First, we discuss underlying principles Rs-fMRI, highlighting its ability to detect alterations brain connectivity (FC) patterns associated We then explore potential ML algorithms, particularly support vector machines (SVMs), analyzing data discriminating between patients healthy controls. indicate challenges opportunities integrating ML, such preprocessing, feature selection, model interpretation. also address importance large-scale, multi-site studies validate robustness generalizability proposed approaches. Overall, integration holds great promise non-invasive, objective, sensitive diagnostic AD, potentially enabling personalized treatment strategies. However, further are warranted optimize methodologies, enhance interpretability, facilitate clinical translation.

Language: Английский

Citations

0