Samad Amini1, Lifu Zhang1, Boran Hao1, Aman Gupta1, Mengting Song1, Cody Karjadi2, Honghuang Lin3, Vijaya B Kolachalama3,4,5, Rhoda Au6,2, Ioannis Ch Paschalidis1,4. 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. Faculty of Computing & Data Sciences, Boston University, Boston, MA, USA. 5. Department of Computer Science, Boston University, Boston, MA, USA. 6. Departments of Anatomy & Neurobiology, Neurology, and Epidemiology, Boston University School of Medicine and School of Public Health, Boston, MA, USA.
Abstract
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.
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.
Entities:
Keywords:
Alzheimer’s disease; artificial intelligence; clock test; deep learning; dementia
Authors: Geert Litjens; Thijs Kooi; Babak Ehteshami Bejnordi; Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Mohsen Ghafoorian; Jeroen A W M van der Laak; Bram van Ginneken; Clara I Sánchez Journal: Med Image Anal Date: 2017-07-26 Impact factor: 8.545
Authors: Claudia L Satizabal; Alexa S Beiser; Vincent Chouraki; Geneviève Chêne; Carole Dufouil; Sudha Seshadri Journal: N Engl J Med Date: 2016-02-11 Impact factor: 91.245
Authors: Weiming Lin; Tong Tong; Qinquan Gao; Di Guo; Xiaofeng Du; Yonggui Yang; Gang Guo; Min Xiao; Min Du; Xiaobo Qu Journal: Front Neurosci Date: 2018-11-05 Impact factor: 4.677