Using Machine Learning to Explain Paraphasias in Narratives of People With Aphasia.
Purpose: This study examines how personal, clinical, and word-level features explain paraphasias when using machine learning--based error analysis on the narratives of people with aphasia (PWA). Method: We used AphasiaBank as the source of narrative transcript data for 236 PWA. We tested machine lea...
| Publicado en: | Perspectives of the ASHA Special Interest Groups Vol. 10; no. 2; pp. 451 - 463 |
|---|---|
| Autores principales: | , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
American Speech-Language-Hearing Association
Apr2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=184219911&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 184219911 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 2381473X KTSD jtl: Perspectives of the ASHA Special Interest Groups issn: 2381473X maglogo: N pubinfo: dt: Apr2025 vid: 10 iid: 2 pid: 42 pub: American Speech-Language-Hearing Association place: Rockville, Maryland artinfo: ui: 184219911 184219911 184219911 10.1044/2024_PERSP-23-00291 184219911 ppf: 451 ppct: 12 formats: fmt: @attributes: type: P tig: atl: Using Machine Learning to Explain Paraphasias in Narratives of People With Aphasia. aug: au: Zavaleta, Rosa Brue, Jacob Sen, Sandip Wilson, Laura affil: Department of Communication Sciences & Disorders, The University of Tulsa, OK sug: subj: Aphasia Therapy Machine Learning Utilization Speech Production Measurement Methods Language Disorders Therapy Speech Disorders Therapy Narratives Human Funding Source Male Female Middle Age Models, Theoretical Natural Language Processing Algorithms Random Forest Apraxia Communication Speech Physiology Sensitivity and Specificity Descriptive Statistics Comparative Studies ROC Curve Questionnaires Middle Aged: 45-64 years Male Female ab: Purpose: This study examines how personal, clinical, and word-level features explain paraphasias when using machine learning--based error analysis on the narratives of people with aphasia (PWA). Method: We used AphasiaBank as the source of narrative transcript data for 236 PWA. We tested machine learning classification algorithms including decision trees and random forests on the utterances of PWA, including nonparaphasic words and intended words when paraphasias were produced. We classified target words as paraphasic or nonparaphasic based on PWA's age; aphasia severity, duration, and type; presence of apraxia or dysarthria; and word-level features including part of speech, word frequency, imageability, syllable count, and location in the utterance. We measured the models' predictive accuracy across classification thresholds on held-out test sets, and we used feature analysis to compare feature importance. Results: At the word level, our random forest model achieved an area under curve (AUC) of 0.896. We found a sensitivity of 0.821 for semantic paraphasias, 0.764 for phonemic paraphasias, and 0.872 for neologistic paraphasias. The most salient features, in order of importance, were word frequency, imageability, part of speech, age, severity, and syllable count, followed by aphasia duration, location of word, presence of apraxia, type of aphasia (e.g., fluent), and presence of dysarthria. Our random forest model that included information about surrounding words achieved AUC scores ranging from 0.881 to 0.899. Additionally, we developed a model that was trained on surrounding words and their respective features, but not given the actual error word. The best model achieved an AUC of 0.745. Conclusions: Machine learning can aid in the explanation of paraphasias. In this study, we analyzed word- and person-level features and highlighted the nonrandom nature of paraphasic productions. Furthermore, this lays the groundwork for developing machine learning models with clinical applications at the various stages of treatment of PWA. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|