Search for: All records

Mild cognitive impairment is the prodromal stage of Alzheimer’s disease. Its detection has been a critical task for establishing cohort studies and developing therapeutic interventions for Alzheimer’s. Various types of markers have been developed for detection. For example, imaging markers from neuroimaging have shown great sensitivity, while its cost is still prohibitive for large-scale screening of early dementia. Recent advances from digital biomarkers, such as language markers, have provided an accessible and affordable alternative. While imaging markers give anatomical descriptions of the brain, language markers capture the behavior characteristics of early dementia subjects. Such differences suggest the benefits of auxiliary information from the imaging modality to improve the predictive power of unimodal predictive models based on language markers alone. However, one significant barrier to the joint analysis is that in typical cohorts, there are only very limited subjects that have both imaging and language modalities. To tackle this challenge, in this paper, we develop a novel crossmodal augmentation tool, which leverages auxiliary imaging information to improve the feature space of language markers so that a subject with only language markers can benefit from imaging information through the augmentation. Our experimental results show that the multi-modal predictive model trained with language markers and auxiliary imaging information significantly outperforms unimodal predictive models. 

In recent years, behavioral markers such as spoken language and lexical preferences have been studied in the early detection of mild cognitive impairment (MCI) using conversations. While the combination of linguistic and acoustic signals have been shown to be effective in detecting MCI, they have generally been restricted to structured conversations in which the interviewee responds to fixed prompts. In this study, we show that linguistic and acoustic features can be combined synergistically to identify MCI in semi-structured conversations. Using conversational data from an on-going clinical trial ( Clinicaltrials.gov : NCT02871921), we find that the combination of linguistic and acoustic features on semi-structured conversations achieves a mean AUC of 82.7, significantly ( p < 0.01) out-performing linguistic-only (74.9 mean AUC) or acoustic-only (65.0 mean AUC) detections on hold-out data. Additionally, features (linguistic, acoustic and combination) obtained from semi-structured conversations outperform their counterparts obtained from structured weekly conversations in identifying MCI. Some linguistic categories are significantly better at predicting MCI status (e.g., death, home) than others.