Learning Linguistic Biomarkers for Predicting Mild Cognitive Impairment using Compound Skip-grams

TL;DR

This paper introduces a machine learning approach that uses compound skip-gram features to identify linguistic biomarkers, improving the prediction of Mild Cognitive Impairment from verbal transcripts, especially in small datasets.

Contribution

It proposes a novel use of compound skip-gram features for linguistic biomarker extraction to enhance MCI prediction accuracy.

Findings

Compound skip-gram features improved AUC in MCI prediction.

Model performed well on small MCI datasets.

Linguistic biomarkers identified can aid early diagnosis.

Abstract

Predicting Mild Cognitive Impairment (MCI) is currently a challenge as existing diagnostic criteria rely on neuropsychological examinations. Automated Machine Learning (ML) models that are trained on verbal utterances of MCI patients can aid diagnosis. Using a combination of skip-gram features, our model learned several linguistic biomarkers to distinguish between 19 patients with MCI and 19 healthy control individuals from the DementiaBank language transcript clinical dataset. Results show that a model with compound of skip-grams has better AUC and could help ML prediction on small MCI data sample.