skip to main content

This content will become publicly available on December 1, 2022

Title: Detection of dementia on voice recordings using deep learning: a Framingham Heart Study
Abstract Background Identification of reliable, affordable, and easy-to-use strategies for detection of dementia is sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality to assess cognition but methods that could automatically analyze such data are not readily available. Methods and findings We used 1264 voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 min in duration, on average, and contained at least two speakers (participant and examiner). 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 (DE). We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the audio recordings to classify if the recording included a participant with only NC or only DE and to differentiate between recordings corresponding to those that had DE from those who did not have DE (i.e., NDE (NC+MCI)). Based on 5-fold cross-validation, the LSTM model achieved a mean (±std) area under the receiver operating characteristic curve (AUC) of 0.740 ± 0.017, mean balanced more » accuracy of 0.647 ± 0.027, and mean weighted F1 score of 0.596 ± 0.047 in classifying cases with DE from those with NC. The CNN model achieved a mean AUC of 0.805 ± 0.027, mean balanced accuracy of 0.743 ± 0.015, and mean weighted F1 score of 0.742 ± 0.033 in classifying cases with DE from those with NC. For the task related to the classification of participants with DE from NDE, the LSTM model achieved a mean AUC of 0.734 ± 0.014, mean balanced accuracy of 0.675 ± 0.013, and mean weighted F1 score of 0.671 ± 0.015. The CNN model achieved a mean AUC of 0.746 ± 0.021, mean balanced accuracy of 0.652 ± 0.020, and mean weighted F1 score of 0.635 ± 0.031 in classifying cases with DE from those who were NDE. Conclusion This proof-of-concept study demonstrates that automated deep learning-driven processing of audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can facilitate dementia screening. « less
Authors:
; ; ; ;
Award ID(s):
1914792 1664644 1645681
Publication Date:
NSF-PAR ID:
10303605
Journal Name:
Alzheimer's Research & Therapy
Volume:
13
Issue:
1
ISSN:
1758-9193
Sponsoring Org:
National Science Foundation
More Like this
  1. 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 characteristicmore »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.« less
  2. Introduction: Alzheimer’s disease (AD) causes progressive irreversible cognitive decline and is the leading cause of dementia. Therefore, a timely diagnosis is imperative to maximize neurological preservation. However, current treatments are either too costly or limited in availability. In this project, we explored using retinal vasculature as a potential biomarker for early AD diagnosis. This project focuses on stage 3 of a three-stage modular machine learning pipeline which consisted of image quality selection, vessel map generation, and classification [1]. The previous model only used support vector machine (SVM) to classify AD labels which limited its accuracy to 82%. In this project, random forest and gradient boosting were added and, along with SVM, combined into an ensemble classifier, raising the classification accuracy to 89%. Materials and Methods: Subjects classified as AD were those who were diagnosed with dementia in “Dementia Outcome: Alzheimer’s disease” from the UK Biobank Electronic Health Records. Five control groups were chosen with a 5:1 ratio of control to AD patients where the control patients had the same age, gender, and eye side image as the AD patient. In total, 122 vessel images from each group (AD and control) were used. The vessel maps were then segmented from fundusmore »images through U-net. A t-test feature selection was first done on the training folds and the selected features was fed into the classifiers with a p-value threshold of 0.01. Next, 20 repetitions of 5-fold cross validation were performed where the hyperparameters were solely tuned on the training data. An ensemble classifier consisting of SVM, gradient boosting tree, and random forests was built and the final prediction was made through majority voting and evaluated on the test set. Results and Discussion: Through ensemble classification, accuracy increased by 4-12% relative to the individual classifiers, precision by 9-15%, sensitivity by 2-9%, specificity by at least 9-16%, and F1 score by 712%. Conclusions: Overall, a relatively high classification accuracy was achieved using machine learning ensemble classification with SVM, random forest, and gradient boosting. Although the results are very promising, a limitation of this study is that the requirement of needing images of sufficient quality decreased the amount of control parameters that can be implemented. However, through retinal vasculature analysis, this project shows machine learning’s high potential to be an efficient, more cost-effective alternative to diagnosing Alzheimer’s disease. Clinical Application: Using machine learning for AD diagnosis through retinal images will make screening available for a broader population by being more accessible and cost-efficient. Mobile device based screening can also be enabled at primary screening in resource-deprived regions. It can provide a pathway for future understanding of the association between biomarkers in the eye and brain.« less
  3. Abstract We examined the association between bilingualism, executive function (EF), and brain volume in older monolinguals and bilinguals who spoke English, Spanish, or both, and were cognitively normal (CN) or diagnosed with Mild Cognitive Impairment (MCI) or dementia. Gray matter volume (GMV) was higher in language and EF brain regions among bilinguals, but no differences were found in memory regions. Neuropsychological performance did not vary across language groups over time; however, bilinguals exhibited reduced Stroop interference and lower scores on Digit Span Backwards and category fluency. Higher scores on Digit Span Backwards were associated with a younger age of English acquisition, and a greater degree of balanced bilingualism was associated with lower scores in category fluency. The initial age of cognitive decline did not differ between language groups. The influence of bilingualism appears to be reflected in increased GMV in language and EF regions, and to a lesser degree, in EF.
  4. Abstract

    Early diagnosis of Alzheimer’s disease plays a pivotal role in patient care and clinical trials. In this study, we have developed a new approach based on 3D deep convolutional neural networks to accurately differentiate mild Alzheimer’s disease dementia from mild cognitive impairment and cognitively normal individuals using structural MRIs. For comparison, we have built a reference model based on the volumes and thickness of previously reported brain regions that are known to be implicated in disease progression. We validate both models on an internal held-out cohort from The Alzheimer's Disease Neuroimaging Initiative (ADNI) and on an external independent cohort from The National Alzheimer's Coordinating Center (NACC). The deep-learning model is accurate, achieved an area-under-the-curve (AUC) of 85.12 when distinguishing between cognitive normal subjects and subjects with either MCI or mild Alzheimer’s dementia. In the more challenging task of detecting MCI, it achieves an AUC of 62.45. It is also significantly faster than the volume/thickness model in which the volumes and thickness need to be extracted beforehand. The model can also be used to forecast progression: subjects with mild cognitive impairment misclassified as having mild Alzheimer’s disease dementia by the model were faster to progress to dementia over time. Anmore »analysis of the features learned by the proposed model shows that it relies on a wide range of regions associated with Alzheimer's disease. These findings suggest that deep neural networks can automatically learn to identify imaging biomarkers that are predictive of Alzheimer's disease, and leverage them to achieve accurate early detection of the disease.

    « less
  5. Abstract STUDY QUESTION

    Can we derive adequate models to predict the probability of conception among couples actively trying to conceive?

    SUMMARY ANSWER

    Leveraging data collected from female participants in a North American preconception cohort study, we developed models to predict pregnancy with performance of ∼70% in the area under the receiver operating characteristic curve (AUC).

    WHAT IS KNOWN ALREADY

    Earlier work has focused primarily on identifying individual risk factors for infertility. Several predictive models have been developed in subfertile populations, with relatively low discrimination (AUC: 59–64%).

    STUDY DESIGN, SIZE, DURATION

    Study participants were female, aged 21–45 years, residents of the USA or Canada, not using fertility treatment, and actively trying to conceive at enrollment (2013–2019). Participants completed a baseline questionnaire at enrollment and follow-up questionnaires every 2 months for up to 12 months or until conception. We used data from 4133 participants with no more than one menstrual cycle of pregnancy attempt at study entry.

    PARTICIPANTS/MATERIALS, SETTING, METHODS

    On the baseline questionnaire, participants reported data on sociodemographic factors, lifestyle and behavioral factors, diet quality, medical history and selected male partner characteristics. A total of 163 predictors were considered in this study. We implemented regularized logistic regression, support vector machines, neural networks and gradient boosted decisionmore »trees to derive models predicting the probability of pregnancy: (i) within fewer than 12 menstrual cycles of pregnancy attempt time (Model I), and (ii) within 6 menstrual cycles of pregnancy attempt time (Model II). Cox models were used to predict the probability of pregnancy within each menstrual cycle for up to 12 cycles of follow-up (Model III). We assessed model performance using the AUC and the weighted-F1 score for Models I and II, and the concordance index for Model III.

    MAIN RESULTS AND THE ROLE OF CHANCE

    Model I and II AUCs were 70% and 66%, respectively, in parsimonious models, and the concordance index for Model III was 63%. The predictors that were positively associated with pregnancy in all models were: having previously breastfed an infant and using multivitamins or folic acid supplements. The predictors that were inversely associated with pregnancy in all models were: female age, female BMI and history of infertility. Among nulligravid women with no history of infertility, the most important predictors were: female age, female BMI, male BMI, use of a fertility app, attempt time at study entry and perceived stress.

    LIMITATIONS, REASONS FOR CAUTION

    Reliance on self-reported predictor data could have introduced misclassification, which would likely be non-differential with respect to the pregnancy outcome given the prospective design. In addition, we cannot be certain that all relevant predictor variables were considered. Finally, though we validated the models using split-sample replication techniques, we did not conduct an external validation study.

    WIDER IMPLICATIONS OF THE FINDINGS

    Given a wide range of predictor data, machine learning algorithms can be leveraged to analyze epidemiologic data and predict the probability of conception with discrimination that exceeds earlier work.

    STUDY FUNDING/COMPETING INTEREST(S)

    The research was partially supported by the U.S. National Science Foundation (under grants DMS-1664644, CNS-1645681 and IIS-1914792) and the National Institutes for Health (under grants R01 GM135930 and UL54 TR004130). In the last 3 years, L.A.W. has received in-kind donations for primary data collection in PRESTO from FertilityFriend.com, Kindara.com, Sandstone Diagnostics and Swiss Precision Diagnostics. L.A.W. also serves as a fibroid consultant to AbbVie, Inc. The other authors declare no competing interests.

    TRIAL REGISTRATION NUMBER

    N/A.

    « less