Alzheimer’s disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer’s disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer’s disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer’s disease and cognitively normal subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset (n = 417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n = 382), the Framingham Heart Study (n = 102), and the National Alzheimer’s Coordinating Center (NACC) (n = 582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n = 11), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer’s disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.

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.

Background The Clock Drawing Test (CDT) has been widely used in clinic for cognitive assessment. Recently, a digital Clock Drawing Text (dCDT) that is able to capture the entire sequence of clock drawing behaviors was introduced. While a variety of domain-specific features can be derived from the dCDT, it has not yet been evaluated in a large community-based population whether the features derived from the dCDT correlate with cognitive function. Objective We aimed to investigate the association between dCDT features and cognitive performance across multiple domains. Methods Participants from the Framingham Heart Study, a large community-based cohort with longitudinal cognitive surveillance, who did not have dementia were included. Participants were administered both the dCDT and a standard protocol of neuropsychological tests that measured a wide range of cognitive functions. A total of 105 features were derived from the dCDT, and their associations with 18 neuropsychological tests were assessed with linear regression models adjusted for age and sex. Associations between a composite score from dCDT features were also assessed for associations with each neuropsychological test and cognitive status (clinically diagnosed mild cognitive impairment compared to normal cognition). Results The study included 2062 participants (age: mean 62, SD 13 years, 51.6% women), among whom 36 were diagnosed with mild cognitive impairment. Each neuropsychological test was associated with an average of 50 dCDT features. The composite scores derived from dCDT features were significantly associated with both neuropsychological tests and mild cognitive impairment. Conclusions The dCDT can potentially be used as a tool for cognitive assessment in large community-based populations.