Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

An Artificial Intelligence-Assisted Method for Dementia Detection Using Images from the Clock Drawing Test

Journal Article · · Journal of Alzheimer's Disease
DOI:https://doi.org/10.3233/jad-210299· OSTI ID:1848384
 [1];  [1];  [1];  [1];  [1];  [2];  [3];  [4];  [5];  [6]
  1. Department of Electrical & Computer Engineering, Division of Systems Engineering, and Department of Biomedical Engineering, Boston University, Boston, MA, USA
  2. Framingham Heart Study, Boston University, Boston, MA, USA
  3. Department of Medicine, Boston University School of Medicine, Boston, MA, USA
  4. Department of Medicine, Boston University School of Medicine, Boston, MA, USA; Faculty of Computing & Data Sciences, Boston University, Boston, MA, USA; Department of Computer Science, Boston University, Boston, MA, USA
  5. Departments of Anatomy & Neurobiology, Neurology, and Epidemiology, Boston University School of Medicine and School of Public Health, Boston, MA, USA; Framingham Heart Study, Boston University, Boston, MA, USA
  6. Department of Electrical & Computer Engineering, Division of Systems Engineering, and Department of Biomedical Engineering, Boston University, Boston, MA, USA; Faculty of Computing & Data Sciences, Boston University, Boston, MA, USA
+ Show Author Affiliations

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.

Research Organization:
Boston Univ., MA (United States)
Sponsoring Organization:
USDOE Advanced Research Projects Agency - Energy (ARPA-E)
DOE Contract Number:
AR0001282
OSTI ID:
1848384
Journal Information:
Journal of Alzheimer's Disease, Vol. 83, Issue 2; ISSN 1387-2877
Country of Publication:
United States
Language:
English

References (29)

The neuropathological diagnosis of Alzheimer’s disease journal August 2019
The Framingham Heart Study and the epidemiology of cardiovascular disease: a historical perspective journal March 2014
Incidence of Dementia over Three Decades in the Framingham Heart Study journal February 2016
Cognitive impairment in Parkinson's disease, Alzheimer's dementia, and vascular dementia: the role of the clock-drawing test: Clock-drawing test in dementia journal February 2018
P2–113: The utility of the clock drawing test for cognitive impairment screening journal July 2006
Association of the Qualitative Clock Drawing Test with Progression to Dementia in Non-Demented Older Adults journal September 2020
Does the Combination of the MMSE and Clock Drawing Test (Mini-Clock) Improve the Detection of Mild Alzheimer's Disease and Mild Cognitive Impairment? journal November 2010
Age and Graphomotor Decision Making Assessed with the Digital Clock Drawing Test: The Framingham Heart Study journal November 2017
Digital Clock Drawing: Differentiating “ Thinking ” versus “ Doing ” in Younger and Older Adults with Depression journal September 2014
Learning classification models of cognitive conditions from subtle behaviors in the digital Clock Drawing Test journal October 2015
Machine Learning Analysis of Digital Clock Drawing Test Performance for Differential Classification of Mild Cognitive Impairment Subtypes Versus Alzheimer’s Disease journal March 2020
Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications journal March 2017
A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data journal June 2019
Development and validation of an interpretable deep learning framework for Alzheimer’s disease classification journal May 2020
Automated classification of Alzheimer's disease and mild cognitive impairment using a single MRI and deep neural networks journal January 2019
A Robust Deep Model for Improved Classification of AD/MCI Patients journal September 2015
The use of PET in Alzheimer disease journal February 2010
Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification journal December 2011
Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs journal December 2016
Convolutional Neural Networks-Based MRI Image Analysis for the Alzheimer’s Disease Prediction From Mild Cognitive Impairment journal November 2018
70-year legacy of the Framingham Heart Study journal May 2019
How technology is reshaping cognitive assessment: Lessons from the Framingham Heart Study. journal November 2017
The Kolmogorov-Smirnov Test for Goodness of Fit journal March 1951
The Chi-square test of independence journal January 2013
Neural transfer learning for assigning diagnosis codes to EMRs journal May 2019
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning journal May 2016
A survey on deep learning in medical image analysis journal December 2017
The meaning and use of the area under a receiver operating characteristic (ROC) curve. journal April 1982
Failure to demonstrate efficacy of aducanumab: An analysis of the EMERGE and ENGAGE trials as reported by Biogen, December 2019 journal November 2020

Similar Records

Related Subjects

Neurosciences & Neurology