Abstract Details

Title Predicting Aphasia Interpersonal Communication Performance from Clinically Available Multimodal Data using Machine Learning

Topic Aging, Dementia, and Behavioral Neurology

Presentation(s) P1 - Poster Session 1 (8:00 AM-9:00 AM)

Poster/Presentation
Number 13-004

Objective

Utilize routinely available clinical data from Persons with Aphasia (PWA) to predict detailed interpersonal communication with >80% accuracy (current gold standard). Employ explainable machine learning (ML) to identify key features influencing personalized language impairment. Generalize models to unseen PWA across etiologies of language impairment from Stroke to Alzheimer's Disease.

Background Clinical predictions of language performance in Persons with Aphasia (PWA) are limited to insights from lesion size, location, and patient demographics; having limited accuracy and specificity. Unfortunately, novel research algorithms have had limited clinical value because they rely on clinically unavailable data (e.g., fMRI), and focus on classifying patient severity rather than predicting language task impairments that can inform treatments.

Design/Methods We trained and validated random forest ML classifiers for noun accuracy using 6200 interpersonal communicative exchanges from 52 PWA (WAB-AQ 25-80, 41 chronic post-Stroke Aphasia, 11 Alzheimer’s Disease). Inputs included: 1) Clinical characteristics (language and cognitive testing, lesion volume, demographics); 2) White matter connectivity from DSI MRI across 83 cortical regions; and 3) Linguistic difficulty (semantic selection, phonemes, etc.) computed for any given word using naturalistic speech corpora. Classifiers were optimized using cross-validation and evaluated on new PWA and unseen language prompts.

Results The best classifiers (AUC=0.9-0.89) combined linguistic difficulty with brain networks or clinical testing. They significantly (p<0.05) outperformed single-datasets or combinations without linguistics (AUC=0.83-0.69). Key predictors included word length and retrieval difficulty, WAB-AQ sub-scores, and white matter connectivity of intact and differentially lesioned brain regions (e.g., left insula and inferior temporal gyri) obtained from structural MRI scans. Prospective generalization to new PWA, unseen language prompts, and translation from Stroke to Alzheimer's retained statistically similar (p>0.05) performance of the best model using all input data (AUC=0.85-0.93).

Conclusions

Our explainable ML model effectively predicts interpersonal communication performance in PWA using multimodal clinically available data. This approach generalizes to new patients, prompts, and etiologies.

Authors/Disclosures
Shreya Parchure PRESENTER	The institution of Ms. Parchure has received research support from National Institutes of Health (NIH). Ms. Parchure has received personal compensation in the range of $10,000-$49,999 for serving as a AI sporadic activity contractor with Inspirit AI.
Garima Gupta, MSc	Miss Gupta has nothing to disclose.
Leslie H. Vnenchak, Speech Pathologist	Ms. Vnenchak has nothing to disclose.
Olufunsho Faseyitan, MS	Mr. Faseyitan has nothing to disclose.
Apoorva Kelkar, MS (Drexel University)	Ms. Kelkar has nothing to disclose.
Denise Y. Harvey	The institution of Denise Y. Harvey has received research support from NATIONAL INSTITUTE ON DEAFNESS AND OTHER COMMUNICATION DISORDERS.
John D. Medaglia, PhD (Drexel University)	The institution of Dr. Medaglia has received research support from National Institutes of Health.
Harry B. Coslett, MD, FAAN (Univ of Pennsylvania)	The institution of Dr. Coslett has received research support from NIDCD, NINDS, NIA. Dr. Coslett has received publishing royalties from a publication relating to health care.
Roy H. Hamilton, MD, MS, FANA, FAAN	Dr. Hamilton has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Highland Instruments. Dr. Hamilton has received personal compensation in the range of $0-$499 for serving on a Scientific Advisory or Data Safety Monitoring board for Cognito Therapeutics. Dr. Hamilton has received personal compensation in the range of $10,000-$49,999 for serving as an officer or member of the Board of Directors for McKnight Brain Research Foundation. The institution of Dr. Hamilton has received research support from NIH. The institution of Dr. Hamilton has received research support from Department of Defense. The institution of Dr. Hamilton has received research support from Chan Zuckerberg Initiative.

��ɫ��

��ɫ��