Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review
Alzheimer's & Dementia · 2023-12 · 19 (12) · 5885-5904
DOI: 10.1002/alz.13412 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Alzheimer's & Dementia, online erschienen am 10.08.2023. Verfasst von Robin J Borchert und 32 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK. Hauptthemen laut MEDLINE: Alzheimer Disease, Neurodegenerative Diseases. Die Arbeit wurde bisher 130-mal zitiert (Crossref) und nennt 189 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medical Research Council.
Abstract (Originalsprache)
Introduction
Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.
Methods
We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.
Results
A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.
Discussion
The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice. Highlights There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK.
- Department of Radiology, University of Cambridge, Cambridge, UK.
- Department of Computer Science and Technology, University of Cambridge, Cambridge, UK.
- Department of Pharmacology and Physiology, University of Montreal, Montreal, Canada.
- Centre de recherche de l'Institut Universitaire de Gériatrie (CRIUGM), Montreal, Canada.
- Centre for Clinical Brain Sciences, The University of Edinburgh, Edinburgh, UK.
ORCID-Profile: Robin J Borchert, Tiago Azevedo, AmanPreet Badhwar, Jose Bernal, Matthew Betts, Rose Bruffaerts, Michael C Burkhart, Ilse Dewachter, Helena M Gellersen, Audrey Low, Ilianna Lourida, Luiza Machado, Christopher R Madan, Maura Malpetti, Jhony Mejia, Sofia Michopoulou, Carlos Muñoz-Neira, Jack Pepys, Marion Peres, Veronica Phillips, Siddharth Ramanan, Stefano Tamburin, Hanz M Tantiangco, Lokendra Thakur, Alessandro Tomassini, Ashwati Vipin, Eugene Tang, Danielle Newby, Janice M Ranson, David J Llewellyn, Michele Veldsman, Timothy Rittman
Förderung
- Medical Research Council
Zitieren
APA
Borchert, R. J., Azevedo, T., Badhwar, A., Bernal, J., Betts, M., Bruffaerts, R., Burkhart, M. C., Dewachter, I., Gellersen, H. M., Low, A., Lourida, I., Machado, L., Madan, C. R., Malpetti, M., Mejia, J., Michopoulou, S., Muñoz-Neira, C., Pepys, J., Peres, M., …, & Rittman, T. (2023). Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review. Alzheimer's & Dementia, 19(12), 5885-5904. https://doi.org/10.1002/alz.13412
Vancouver
Borchert RJ, Azevedo T, Badhwar A, Bernal J, Betts M, Bruffaerts R, et al. Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review. Alzheimer's & Dementia. 2023;19(12):5885-5904. doi:10.1002/alz.13412
BibTeX
@article{Borchert2023,
author = {Borchert, Robin J and Azevedo, Tiago and Badhwar, AmanPreet and Bernal, Jose and Betts, Matthew and Bruffaerts, Rose and Burkhart, Michael C and Dewachter, Ilse and Gellersen, Helena M and Low, Audrey and Lourida, Ilianna and Machado, Luiza and Madan, Christopher R and Malpetti, Maura and Mejia, Jhony and Michopoulou, Sofia and Muñoz-Neira, Carlos and Pepys, Jack and Peres, Marion and Phillips, Veronica and Ramanan, Siddharth and Tamburin, Stefano and Tantiangco, Hanz M and Thakur, Lokendra and Tomassini, Alessandro and Vipin, Ashwati and Tang, Eugene and Newby, Danielle and Deep Dementia Phenotyping (DEMON) Network, Deep Dementia Phenotyping (DEMON) Network and Ranson, Janice M and Llewellyn, David J and Veldsman, Michele and Rittman, Timothy},
title = {Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review},
journal = {Alzheimer's & Dementia},
year = {2023},
volume = {19},
number = {12},
pages = {5885--5904},
doi = {10.1002/alz.13412}
}
EUVIMED