Artificial intelligence classifies primary progressive aphasia from connected speech
Brain · 03.09.2024 · 147 (9) · 3070-3082
DOI: 10.1093/brain/awae196 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain, online erschienen am 24.06.2024. Verfasst von Neguine Rezaii und 7 weiteren Autor:innen. Beteiligte Einrichtung: Frontotemporal Disorders Unit, Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA. Hauptthemen laut MEDLINE: Aphasia, Primary Progressive, Artificial Intelligence, Speech. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIDCD NIH HHS, NCRR NIH HHS, NINDS NIH HHS.
Abstract (Originalsprache)
Neurodegenerative dementia syndromes, such as primary progressive aphasias (PPA), have traditionally been diagnosed based, in part, on verbal and non-verbal cognitive profiles. Debate continues about whether PPA is best divided into three variants and regarding the most distinctive linguistic features for classifying PPA variants. In this cross-sectional study, we initially harnessed the capabilities of artificial intelligence and natural language processing to perform unsupervised classification of short, connected speech samples from 78 pateints with PPA. We then used natural language processing to identify linguistic features that best dissociate the three PPA variants. Large language models discerned three distinct PPA clusters, with 88.5% agreement with independent clinical diagnoses. Patterns of cortical atrophy of three data-driven clusters corresponded to the localization in the clinical diagnostic criteria. In the subsequent supervised classification, 17 distinctive features emerged, including the observation that separating verbs into high- and low-frequency types significantly improved classification accuracy. Using these linguistic features derived from the analysis of short, connected speech samples, we developed a classifier that achieved 97.9% accuracy in classifying the four groups (three PPA variants and healthy controls). The data-driven section of this study showcases the ability of large language models to find natural partitioning in the speech of patients with PPA consistent with conventional variants. In addition, the work identifies a robust set of language features indicative of each PPA variant, emphasizing the significance of dividing verbs into high- and low-frequency categories. Beyond improving diagnostic accuracy, these findings enhance our understanding of the neurobiology of language processing.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Frontotemporal Disorders Unit, Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
- Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
- Department of Psychology, Emory University, Atlanta, GA 30322, USA.
- Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School, Boston, MA 02129, USA.
- Massachusetts Alzheimer's Disease Research Center, Harvard Medical School, Boston, MA 02114, USA.
ORCID-Profile: Bradford C Dickerson
Förderung
- NIDCD NIH HHS
- NCRR NIH HHS
- NINDS NIH HHS
- Center for Functional Neuroimaging Technologies
- Athinoula A. Martinos Center for Biomedical Imaging
- Primary Care Innovation Fund
- NIA NIH HHS
- NIH HHS
Zitieren
APA
Rezaii, N., Hochberg, D., Quimby, M., Wong, B., Brickhouse, M., Touroutoglou, A., Dickerson, B. C., & Wolff, P. (2024). Artificial intelligence classifies primary progressive aphasia from connected speech. Brain, 147(9), 3070-3082. https://doi.org/10.1093/brain/awae196
Vancouver
Rezaii N, Hochberg D, Quimby M, Wong B, Brickhouse M, Touroutoglou A, et al. Artificial intelligence classifies primary progressive aphasia from connected speech. Brain. 2024;147(9):3070-3082. doi:10.1093/brain/awae196
BibTeX
@article{Rezaii2024,
author = {Rezaii, Neguine and Hochberg, Daisy and Quimby, Megan and Wong, Bonnie and Brickhouse, Michael and Touroutoglou, Alexandra and Dickerson, Bradford C and Wolff, Phillip},
title = {Artificial intelligence classifies primary progressive aphasia from connected speech},
journal = {Brain},
year = {2024},
volume = {147},
number = {9},
pages = {3070--3082},
doi = {10.1093/brain/awae196}
}
EUVIMED