Dataset Information

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 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.

SUBMITTER: Xue C

PROVIDER: S-EPMC8409004 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe prevalence of dementia is expected to soar as the average life expectancy increases, but recent estimates suggest that the age-specific incidence of dementia is declining in high-income countries. Temporal trends are best derived through continuous monitoring of a population over a long period with the use of consistent diagnostic criteria. We describe temporal trends in the incidence of dementia over three decades among participants in the Framingham Heart Study.MethodsParticipants in the Framingham Heart Study have been under surveillance for incident dementia since 1975. In this analysis, which included 5205 persons 60 years of age or older, we used Cox proportional-hazards models adjusted for age and sex to determine the 5-year incidence of dementia during each of four epochs. We also explored the interactions between epoch and age, sex, apolipoprotein E ε4 status, and educational level, and we examined the effects of these interactions, as well as the effects of vascular risk factors and cardiovascular disease, on temporal trends.ResultsThe 5-year age- and sex-adjusted cumulative hazard rates for dementia were 3.6 per 100 persons during the first epoch (late 1970s and early 1980s), 2.8 per 100 persons during the second epoch (late 1980s and early 1990s), 2.2 per 100 persons during the third epoch (late 1990s and early 2000s), and 2.0 per 100 persons during the fourth epoch (late 2000s and early 2010s). Relative to the incidence during the first epoch, the incidence declined by 22%, 38%, and 44% during the second, third, and fourth epochs, respectively. This risk reduction was observed only among persons who had at least a high school diploma (hazard ratio, 0.77; 95% confidence interval, 0.67 to 0.88). The prevalence of most vascular risk factors (except obesity and diabetes) and the risk of dementia associated with stroke, atrial fibrillation, or heart failure have decreased over time, but none of these trends completely explain the decrease in the incidence of dementia.ConclusionsAmong participants in the Framingham Heart Study, the incidence of dementia has declined over the course of three decades. The factors contributing to this decline have not been completely identified. (Funded by the National Institutes of Health.).

Project description:This study was sought to investigate the feasibility of using smartphone-based breathing sounds within a deep learning framework to discriminate between COVID-19, including asymptomatic, and healthy subjects. A total of 480 breathing sounds (240 shallow and 240 deep) were obtained from a publicly available database named Coswara. These sounds were recorded by 120 COVID-19 and 120 healthy subjects via a smartphone microphone through a website application. A deep learning framework was proposed herein that relies on hand-crafted features extracted from the original recordings and from the mel-frequency cepstral coefficients (MFCC) as well as deep-activated features learned by a combination of convolutional neural network and bi-directional long short-term memory units (CNN-BiLSTM). The statistical analysis of patient profiles has shown a significant difference (p-value: 0.041) for ischemic heart disease between COVID-19 and healthy subjects. The Analysis of the normal distribution of the combined MFCC values showed that COVID-19 subjects tended to have a distribution that is skewed more towards the right side of the zero mean (shallow: 0.59±1.74, deep: 0.65±4.35, p-value: <0.001). In addition, the proposed deep learning approach had an overall discrimination accuracy of 94.58% and 92.08% using shallow and deep recordings, respectively. Furthermore, it detected COVID-19 subjects successfully with a maximum sensitivity of 94.21%, specificity of 94.96%, and area under the receiver operating characteristic (AUROC) curves of 0.90. Among the 120 COVID-19 participants, asymptomatic subjects (18 subjects) were successfully detected with 100.00% accuracy using shallow recordings and 88.89% using deep recordings. This study paves the way towards utilizing smartphone-based breathing sounds for the purpose of COVID-19 detection. The observations found in this study were promising to suggest deep learning and smartphone-based breathing sounds as an effective pre-screening tool for COVID-19 alongside the current reverse-transcription polymerase chain reaction (RT-PCR) assay. It can be considered as an early, rapid, easily distributed, time-efficient, and almost no-cost diagnosis technique complying with social distancing restrictions during COVID-19 pandemic.