Dataset Information

Attentive pairwise interaction network for AI-assisted clock drawing test assessment of early visuospatial deficits.

ABSTRACT: Dementia is a debilitating neurological condition which impairs the cognitive function and the ability to take care of oneself. The Clock Drawing Test (CDT) is widely used to detect dementia, but differentiating normal from borderline cases requires years of clinical experience. Misclassifying mild abnormal as normal will delay the chance to investigate for potential reversible causes or slow down the progression. To help address this issue, we propose an automatic CDT scoring system that adopts Attentive Pairwise Interaction Network (API-Net), a fine-grained deep learning model that is designed to distinguish visually similar images. Inspired by how humans often learn to recognize different objects by looking at two images side-by-side, API-Net is optimized using image pairs in a contrastive manner, as opposed to standard supervised learning, which optimizes a model using individual images. In this study, we extend API-Net to infer Shulman CDT scores from a dataset of 3108 subjects. We compare the performance of API-Net to that of convolutional neural networks: VGG16, ResNet-152, and DenseNet-121. The best API-Net achieves an F1-score of 0.79, which is a 3% absolute improvement over ResNet-152's F1-score of 0.76. The code for API-Net and the dataset used have been made available at https://github.com/cccnlab/CDT-API-Network .

SUBMITTER: Raksasat R

PROVIDER: S-EPMC10593802 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Attentive pairwise interaction network for AI-assisted clock drawing test assessment of early visuospatial deficits.

Raksasat Raksit R Teerapittayanon Surat S Itthipuripat Sirawaj S Praditpornsilpa Kearkiat K Petchlorlian Aisawan A Chotibut Thiparat T Chunharas Chaipat C Chatnuntawech Itthi I

Scientific reports 20231023 1

Dementia is a debilitating neurological condition which impairs the cognitive function and the ability to take care of oneself. The Clock Drawing Test (CDT) is widely used to detect dementia, but differentiating normal from borderline cases requires years of clinical experience. Misclassifying mild abnormal as normal will delay the chance to investigate for potential reversible causes or slow down the progression. To help address this issue, we propose an automatic CDT scoring system that adopts ...[more]

PMID: 37872267

Similar Datasets

Project description:BackgroundThe digital Clock Drawing Test (dCDT) has been recently used as a more objective tool to assess cognition. However, the association between digitally obtained clock drawing features and structural neuroimaging measures has not been assessed in large population-based studies.ObjectiveWe aimed to investigate the association between dCDT features and brain volume.MethodsThis study included participants from the Framingham Heart Study who had both a dCDT and magnetic resonance imaging (MRI) scan, and were free of dementia or stroke. Linear regression models were used to assess the association between 18 dCDT composite scores (derived from 105 dCDT raw features) and brain MRI measures, including total cerebral brain volume (TCBV), cerebral white matter volume, cerebral gray matter volume, hippocampal volume, and white matter hyperintensity (WMH) volume. Classification models were also built from clinical risk factors, dCDT composite scores, and MRI measures to distinguish people with mild cognitive impairment (MCI) from those whose cognition was intact.ResultsA total of 1656 participants were included in this study (mean age 61 years, SD 13 years; 50.9% women), with 23 participants diagnosed with MCI. All dCDT composite scores were associated with TCBV after adjusting for multiple testing (P value <.05/18). Eleven dCDT composite scores were associated with cerebral white matter volume, but only 1 dCDT composite score was associated with cerebral gray matter volume. None of the dCDT composite scores was associated with hippocampal volume or WMH volume. The classification model for differentiating MCI and normal cognition participants, which incorporated age, sex, education, MRI measures, and dCDT composite scores, showed an area under the curve of 0.897.ConclusionsdCDT composite scores were significantly associated with multiple brain MRI measures in a large community-based cohort. The dCDT has the potential to be used as a cognitive assessment tool in the clinical diagnosis of MCI.

Project description:BackgroundPost-stroke neurocognitive disorder, though common, is often overlooked by clinicians. Moreover, although the Montreal Cognitive Assessment (MoCA) has proven to be a valid screening test for neurocognitive disorder, even more time saving tests would be preferred. In our study, we aimed to determine the diagnostic accuracy of the Clock Drawing Test (CDT) for post-stroke neurocognitive disorder and the association between the CDT and MoCA.MethodsThis study is part of the Norwegian Cognitive Impairment After Stroke study, a multicentre prospective cohort study following patients admitted with acute stroke. At the three-month follow-up, patients were classified with normal cognition, mild neurocognitive disorder, or major neurocognitive disorder according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition criteria. Any neurocognitive disorder compromised both mild- and major neurocognitive disorder. The CDT at the three-month assessment was given scores ranging from 0 to 5. Patients able to complete the CDT and whose cognitive status could be classified were included in analyses. The CDT diagnostic accuracy for post-stroke neurocognitive disorder was identified using receiver operating characteristic curves, sensitivity, specificity, positive predictive value, and negative predictive value. The association between the MoCA and CDT was analysed with Spearman's rho.ResultsOf 554 participants, 238 (43.0%) were women. Mean (SD) age was 71.5 (11.8) years, while mean (SD) National Institutes of Health Stroke Scale score was 2.6 (3.7). The area under the receiver operating characteristic curve of the CDT for major neurocognitive disorder and any neurocognitive disorder was 0.73 (95% CI, 0.68-0.79) and 0.68 (95% CI, 0.63-0.72), respectively. A CDT cutoff of < 5 yielded 68% sensitivity and 60% specificity for any neurocognitive disorder and 78% sensitivity and 53% specificity for major neurocognitive disorder. Spearman's correlation coefficient between scores on the MoCA and CDT was 0.50 (95% CI, 0.44-0.57, p < .001).ConclusionsThe CDT is not accurate enough to diagnose post-stroke neurocognitive disorder but shows acceptable accuracy in identifying major neurocognitive disorder. Performance on the CDT was associated with performance on MoCA; however, the CDT is inferior to MoCA in identifying post-stroke neurocognitive disorder.Trial registrationClinicalTrials.gov (NCT02650531). Retrospectively registered January 8, 2016.

Dataset Information

Attentive pairwise interaction network for AI-assisted clock drawing test assessment of early visuospatial deficits.

Publications

Attentive pairwise interaction network for AI-assisted clock drawing test assessment of early visuospatial deficits.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets