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. An 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.
Neuropsychological test validation of speech markers of cognitive impairment in the Framingham Cognitive Aging Cohort
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.
more »
« less
- Award ID(s):
- 1735095
- NSF-PAR ID:
- 10290673
- Date Published:
- Journal Name:
- Exploration of Medicine
- Volume:
- 2
- Issue:
- 3
- ISSN:
- 2692-3106
- Page Range / eLocation ID:
- 232 to 252
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
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.more » « less
-
Background: Widespread dementia detection could increase clinical trial candidates and enable appropriate interventions. Since the Clock Drawing Test (CDT) can be potentially used for diagnosing dementia-related disorders, it can be leveraged to develop a computer-aided screening tool. Objective: To evaluate if a machine learning model that uses images from the CDT can predict mild cognitive impairment or dementia. Methods: Images of an analog clock drawn by 3,263 cognitively intact and 160 impaired subjects were collected during in-person dementia evaluations by the Framingham Heart Study. We processed the CDT images, participant’s age, and education level using a deep learning algorithm to predict dementia status. Results: When only the CDT images were used, the deep learning model predicted dementia status with an area under the receiver operating characteristic curve (AUC) of 81.3% ± 4.3%. A composite logistic regression model using age, level of education, and the predictions from the CDT-only model, yielded an average AUC and average F1 score of 91.9% ±1.1% and 94.6% ±0.4%, respectively. Conclusion: Our modeling framework establishes a proof-of-principle that deep learning can be applied on images derived from the CDT to predict dementia status. When fully validated, this approach can offer a cost-effective and easily deployable mechanism for detecting cognitive impairment.more » « less
-
Background and Objectives The goal of this work was to determine the relationship between diffusion microstructure and early changes in Alzheimer disease (AD) severity as assessed by clinical diagnosis, cognitive performance, dementia severity, and plasma concentrations of neurofilament light chain. Methods Diffusion MRI scans were collected on cognitively normal participants (CN) and patients with early mild cognitive impairment (EMCI), late mild cognitive impairment, and AD. Free water (FW) and FW-corrected fractional anisotropy were calculated in the locus coeruleus to transentorhinal cortex tract, 4 magnocellular regions of the basal forebrain (e.g., nucleus basalis of Meynert), entorhinal cortex, and hippocampus. All patients underwent a battery of cognitive assessments; neurofilament light chain levels were measured in plasma samples. Results FW was significantly higher in patients with EMCI compared to CN in the locus coeruleus to transentorhinal cortex tract, nucleus basalis of Meynert, and hippocampus (mean Cohen d = 0.54; p fdr < 0.05). FW was significantly higher in those with AD compared to CN in all the examined regions (mean Cohen d = 1.41; p fdr < 0.01). In addition, FW in the hippocampus, entorhinal cortex, nucleus basalis of Meynert, and locus coeruleus to transentorhinal cortex tract positively correlated with all 5 cognitive impairment metrics and neurofilament light chain levels (mean r 2 = 0.10; p fdr < 0.05). Discussion These results show that higher FW is associated with greater clinical diagnosis severity, cognitive impairment, and neurofilament light chain. They also suggest that FW elevation occurs in the locus coeruleus to transentorhinal cortex tract, nucleus basalis of Meynert, and hippocampus in the transition from CN to EMCI, while other basal forebrain regions and the entorhinal cortex are not affected until a later stage of AD. FW is a clinically relevant and noninvasive early marker of structural changes related to cognitive impairment.more » « less
-
Abstract Objective: The current cross-sectional study examined cognition and performance-based functional abilities in a continuing care senior housing community (CCSHC) that is comparable to other CCSHCs in the US with respect to residents’ demographic characteristics. Method: Participants were 110 older adult residents of the independent living unit. We assessed sociodemographics, mental health, neurocognitive functioning, and functional capacity. Results: Compared to normative samples, participants performed at or above expectations in terms of premorbid functioning, attention span and working memory, processing speed, timed set-shifting, inhibitory control, and confrontation naming. They performed below expectation in verbal fluency and verbal and visual learning and memory, with impairment rates [31.4% (>1 SD below the mean) and 18.49% (>1.5 SD below the mean)] well above the general population (16% and 7%, respectively). Within the cognitive test battery, two tests of delayed memory were most predictive of a global deficit score. Most cognitive test scores correlated with performance-based functional capacity. Conclusions: Overall, results suggest that a subset of older adults in the independent living sector of CCSHCs are cognitively and functionally impaired and are at risk for future dementia. Results also argue for the inclusion of memory tests in abbreviated screening batteries in this population. We suggest that CCSHCs implement regular cognitive screening procedures to identify and triage those older adults who could benefit from interventions and, potentially, a transition to a higher level of care.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.37349/emed.2021.00044
