Assessing the Utility of Language and Voice Biomarkers to Predict Cognitive Impairment in the Framingham Heart Study Cognitive Aging Cohort Data

Thomas, J. A. C.; Burkhardt, Hannah A; Chaudhry, Safina; Ngo, Anthony; Sharma, Saransh; Zhang, Larry; Au, Rhoda; Ghomi, Reza Hosseini

doi:10.3233/jad-190783

Cited by 20 publications

(28 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This aspect places us in a unique position compared to previously published work that depended on derived measures. 20,21 Second, our approach can process audio recordings of variable lengths, which means that one does not have to format or select a specific window of the audio recording for analysis. This important strength underscores the generalizability of our work because one can process voice recordings containing various combinations of neuropsychological tests that are not bounded within a time frame.…”

Section: Discussionmentioning

confidence: 99%

Detection of dementia on raw voice recordings using deep learning: A Framingham Heart Study

Xue

Karjadi

Paschalidis

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Identification of reliable, affordable and easy-to-use strategies for detection of dementia are sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality to assess cognition but methods that could automatically analyze such data without any pre-processing are not readily available. Methods: We used a subset of 1264 digital voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 minutes in duration, on average, and contained at least two speakers (participant and clinician). Of the total voice recordings, 483 were of participants with normal cognition (NC), 451 recordings were of participants with mild cognitive impairment (MCI), and 330 were of participants with dementia. We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the raw audio recordings to classify if the recording included a participant with only NC or only dementia, and also to differentiate between recordings corresponding to non-demented (NC+MCI) and demented participants. Findings: Based on 5-fold cross-validation, the LSTM model achieved a mean (+/-std) area under the sensitivity-specificity curve (AUC) of 0.744+/-0.038, mean accuracy of 0.680+/-0.032, mean sensitivity of 0.719+/-0.112, and mean specificity of 0.652+/-0.089 in predicting cases with dementia from those with normal cognition. The CNN model achieved a mean AUC of 0.805+/-0.027, mean accuracy of 0.740+/-0.033, mean sensitivity of 0.735+/-0.094, and mean specificity of 0.750+/-0.083 in predicting cases with only dementia from those with only NC. For the task related to classification of demented participants from non-demented ones, the LSTM model achieved a mean AUC of 0.659+/-0.043, mean accuracy of 0.701+/-0.057, mean sensitivity of 0.245+/-0.161 and mean specificity of 0.856+/-0.105. The CNN model achieved a mean AUC of 0.730+/-0.039, mean accuracy of 0.735+/-0.046, mean sensitivity of 0.443+/-0.113, and mean specificity of 0.840+/-0.076 in predicting cases with dementia from those who were not demented. Interpretation: This proof-of-concept study demonstrates the potential that raw audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can provide a level of screening for dementia.

show abstract

Section: Discussionmentioning

confidence: 99%

Detection of dementia on raw voice recordings using deep learning: A Framingham Heart Study

Xue

Karjadi

Paschalidis

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A recent analysis by Thomas et al [13] extensively characterized the utility of speech features in predicting binary cognitive status (control vs. impaired) in a subset of the FHS Cognitive Aging Cohort, extending work by Alhanai et al [12]. The results of the analysis notably showed an area under the AUC of 0.908 for an ElasticNet model trained on linguistic features, and improved performance (0.943) when the model incorporated demographic variables and acoustic features.…”

Section: Introductionmentioning

confidence: 90%

“…The FHS has conducted incident studies of dementia since 1976 and first began collecting digital voice recordings of assessments in 2005. One central objective is to capture age-related cognitive changes across the entire adult lifespan [13]. The study obtains anthropomorphic, lifestyle, organ function [19], genetic [20], and other health-related phenotypic [21] data.…”

Section: Datamentioning

confidence: 99%

“…In this work, we provide in-depth contextual analysis of linguistic features in detecting cognitive impairment and examine how to improve their clinical viability. First, based on the optimistic performance of language in predicting cognitive status from our research team's previous work, we pursue a deeper dive into the primary dimensions of language, including syntactic, semantic, and lexical information, to expand the feature set reported by Thomas et al [13]. We perform an error analysis to gauge deficits of the models in predicting cognitive status in key demographic groups.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neuropsychological test validation of speech markers of cognitive impairment in the Framingham Cognitive Aging Cohort

Zhang

Ngo

Thomas

et al. 2021

Exploration of Medicine

Self Cite

View full text Add to dashboard Cite

Aim: Although clinicians primarily diagnose dementia based on a combination of metrics such as medical history and formal neuropsychological tests, recent work using linguistic analysis of narrative speech to identify dementia has shown promising results. We aim to build upon research by Thomas JA & Burkardt HA et al. (J Alzheimers Dis. 2020;76:905–2) and Alhanai et al. (arXiv:1710.07551v1. 2020) on the Framingham Heart Study (FHS) Cognitive Aging Cohort by 1) demonstrating the predictive capability of linguistic analysis in differentiating cognitively normal from cognitively impaired participants and 2) comparing the performance of the original linguistic features with the performance of expanded features. Methods: Data were derived from a subset of the FHS Cognitive Aging Cohort. We analyzed a sub-selection of 98 participants, which provided 127 unique audio files and clinical observations (n = 127, female = 47%, cognitively impaired = 43%). We built on previous work which extracted original linguistic features from transcribed audio files by extracting expanded features. We used both feature sets to train logistic regression classifiers to distinguish cognitively normal from cognitively impaired participants and compared the predictive power of the original and expanded linguistic feature sets, and participants’ Mini-Mental State Examination (MMSE) scores. Results: Based on the area under the receiver-operator characteristic curve (AUC) of the models, both the original (AUC = 0.882) and expanded (AUC = 0.883) feature sets outperformed MMSE (AUC = 0.870) in classifying cognitively impaired and cognitively normal participants. Although the original and expanded feature sets had similar AUC, the expanded feature set showed better positive and negative predictive value [expanded: positive predictive value (PPV) = 0.738, negative predictive value (NPV) = 0.889; original: PPV = 0.701, NPV = 0.869]. Conclusions: Linguistic analysis has been shown to be a potentially powerful tool for clinical use in classifying cognitive impairment. This study expands the work of several others, but further studies into the plausibility of speech analysis in clinical use are vital to ensure the validity of speech analysis for clinical classification of cognitive impairment.

show abstract

“…For example, the Framingham Heart Study (FHS) is developing a smartphone platform with multiple applications including digital voice. Voice (spoken utterances and language) is measured through device agnostic technologies and FHS research shows that linguistic and acoustic measures can be used as biomarkers of cognitive function ( 26 – 28 ). However, while speech and language assessments are likely to be very sensitive, additional work is needed to determine the best way to capture speech samples.…”

Section: Implementing Digital Devices In Ad Clinical Studiesmentioning

confidence: 99%

Using Digital Tools to Advance Alzheimer’s Drug Trials During a Pandemic: The EU/US CTAD Task Force

et al. 2021

View full text Add to dashboard Cite

The 2020 COVID-19 pandemic has disrupted Alzheimer’s disease (AD) clinical studies worldwide. Digital technologies may help minimize disruptions by enabling remote assessment of subtle cognitive and functional changes over the course of the disease. The EU/US Clinical Trials in Alzheimer’s Disease (CTAD) Task Force met virtually in November 2020 to explore the opportunities and challenges associated with the use of digital technologies in AD clinical research. While recognizing the potential of digital tools to accelerate clinical trials, improve the engagement of diverse populations, capture clinically meaningful data, and lower costs, questions remain regarding the stability, validity, generalizability, and reproducibility of digital data. Substantial concerns also exist regarding regulatory acceptance and privacy. Nonetheless, the Task Force supported further exploration of digital technologies through collaboration and data sharing, noting the need for standardization of digital readouts. They also concluded that while it may be premature to employ remote assessments for trials of novel experimental medications, remote studies of non-invasive, multi-domain approaches may be feasible at this time.

show abstract

Assessing the Utility of Language and Voice Biomarkers to Predict Cognitive Impairment in the Framingham Heart Study Cognitive Aging Cohort Data

Cited by 20 publications

References 40 publications

Detection of dementia on raw voice recordings using deep learning: A Framingham Heart Study

Detection of dementia on raw voice recordings using deep learning: A Framingham Heart Study

Neuropsychological test validation of speech markers of cognitive impairment in the Framingham Cognitive Aging Cohort

Using Digital Tools to Advance Alzheimer’s Drug Trials During a Pandemic: The EU/US CTAD Task Force

Contact Info

Product

Resources

About