EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Differential dementia detection from multimodal brain images in a real‐world dataset

Matthew Leming iD, Hyungsoon Im iD

Alzheimer's & Dementia · 2025

DOI: 10.1002/alz.70362 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Alzheimer's & Dementia, 2025. Verfasst von Matthew Leming und 1 weiteren Autor:innen. Beteiligte Einrichtung: Center for Systems Biology, Massachusetts General Hospital, Boston, USA. Hauptthemen laut MEDLINE: Dementia, Brain, Deep Learning, Artificial Intelligence. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NIH Office of the Director, MGH ECOR Fund for Medical Discovery Awards.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION Artificial intelligence (AI) models have been applied to differential dementia detection tasks in brain images from curated, high‐quality benchmark databases, but not real‐world data in hospitals. METHODS We describe a deep learning model specially trained for disease detection in heterogeneous clinical images from electronic health records without focusing on confounding factors. It encodes up to 14 multimodal images, alongside age and demographics, and outputs the likelihood of vascular dementia, Alzheimer's, Lewy body dementia, Pick's disease, mild cognitive impairment, and unspecified dementia. We use data from Massachusetts General Hospital (183,018 images from 11,015 patients) for training and external data (125,493 images from 6,662 patients) for testing. RESULTS Performance ranged between 0.82 and 0.94 area under the curve (AUC) on data from 1003 sites. DISCUSSION Analysis shows that the model focused on subcortical brain structures as the basis for its decisions. By detecting biomarkers in real‐world data, the presented techniques will help with clinical translation of disease detection AI. Highlights Our artificial intelligence (AI) model can detect neurodegenerative disorders in brain imaging electronic health record (EHR) data. It encodes up to 14 brain images and text information from a single patient's EHR. Attention maps show that the model focuses on subcortical brain structures. Performance ranged from 0.82 to 0.94 area under the curve (AUC) on data from 1003 external sites.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DementiaBrainDeep LearningArtificial IntelligenceMultimodal ImagingNeuroimagingHumansDiagnosis, DifferentialFemaleMaleAgedElectronic Health RecordsDatabases, FactualMagnetic Resonance ImagingAlzheimer Disease

Stichwörter der Autor:innen

AIMRIbiomarkersdeep learningdementia diagnosticselectronic health recordsmultimodal

Autor:innen und Institutionen

  • Center for Systems Biology, Massachusetts General Hospital, Boston, USA.
  • Massachusetts Alzheimer's Disease Research Center, Massachusetts General Hospital, Boston, USA.
  • Department of Radiology, Massachusetts General Hospital, Boston, USA.

ORCID-Profile: Matthew Leming, Hyungsoon Im

Förderung

  • NIGMS NIH HHS
  • NIH Office of the Director
  • MGH ECOR Fund for Medical Discovery Awards
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Leming, M., & Im, H. (2025). Differential dementia detection from multimodal brain images in a real‐world dataset. Alzheimer's & Dementia. https://doi.org/10.1002/alz.70362

Vancouver

Leming M, Im H. Differential dementia detection from multimodal brain images in a real‐world dataset. Alzheimer's & Dementia. 2025. doi:10.1002/alz.70362

BibTeX
@article{Leming2025,
  author = {Leming, Matthew and Im, Hyungsoon},
  title = {Differential dementia detection from multimodal brain images in a real‐world dataset},
  journal = {Alzheimer's & Dementia},
  year = {2025},
  doi = {10.1002/alz.70362}
}
Kostenlos starten →