scholarly journals Automatic, Qualitative Scoring of the Clock Drawing Test (CDT) Based on U-Net, CNN and Mobile Sensor Data

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5239
Author(s):  
Ingyu Park ◽  
Unjoo Lee
Keyword(s):  
Deep Learning ◽  
Scoring System ◽  
Learning Algorithms ◽  
Sensor Data ◽  
Smart Devices ◽  
Mobile Sensor ◽  
Convolutional Network ◽  
Clock Drawing Test ◽  
Clock Drawing ◽  
Drawing Test

The Clock Drawing Test (CDT) is a rapid, inexpensive, and popular screening tool for cognitive functions. In spite of its qualitative capabilities in diagnosis of neurological diseases, the assessment of the CDT has depended on quantitative methods as well as manual paper based methods. Furthermore, due to the impact of the advancement of mobile smart devices imbedding several sensors and deep learning algorithms, the necessity of a standardized, qualitative, and automatic scoring system for CDT has been increased. This study presents a mobile phone application, mCDT, for the CDT and suggests a novel, automatic and qualitative scoring method using mobile sensor data and deep learning algorithms: CNN, a convolutional network, U-Net, a convolutional network for biomedical image segmentation, and the MNIST (Modified National Institute of Standards and Technology) database. To obtain DeepC, a trained model for segmenting a contour image from a hand drawn clock image, U-Net was trained with 159 CDT hand-drawn images at 128 × 128 resolution, obtained via mCDT. To construct DeepH, a trained model for segmenting the hands in a clock image, U-Net was trained with the same 159 CDT 128 × 128 resolution images. For obtaining DeepN, a trained model for classifying the digit images from a hand drawn clock image, CNN was trained with the MNIST database. Using DeepC, DeepH and DeepN with the sensor data, parameters of contour (0–3 points), numbers (0–4 points), hands (0–5 points), and the center (0–1 points) were scored for a total of 13 points. From 219 subjects, performance testing was completed with images and sensor data obtained via mCDT. For an objective performance analysis, all the images were scored and crosschecked by two clinical experts in CDT scaling. Performance test analysis derived a sensitivity, specificity, accuracy and precision for the contour parameter of 89.33, 92.68, 89.95 and 98.15%, for the hands parameter of 80.21, 95.93, 89.04 and 93.90%, for the numbers parameter of 83.87, 95.31, 87.21 and 97.74%, and for the center parameter of 98.42, 86.21, 96.80 and 97.91%, respectively. From these results, the mCDT application and its scoring system provide utility in differentiating dementia disease subtypes, being valuable in clinical practice and for studies in the field.

The Four-Point Scoring System for the Clock Drawing Test Does Not Differentiate between Alzheimer's Disease and Vascular Dementia

2010 ◽  
Vol 106 (3) ◽  
pp. 941-948 ◽  
Author(s):  
April R. Wiechmann ◽  
James R. Hall ◽  
Sid O'bryant
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Vascular Dementia ◽  
Sensitivity And Specificity ◽  
Scoring System ◽  
Cutoff Score ◽  
Characteristic Analysis ◽  
Clock Drawing Test ◽  
Clock Drawing ◽  
Drawing Test

The purpose of this study was to explore the sensitivity and specificity of the Clock Drawing Test by using a widely employed four-point scoring system to discriminate between patients with Alzheimer's disease or vascular dementia. Receiver operating characteristic analysis indicated that the Clock Drawing Test was able to distinguish between normal elders and those with a dementia diagnosis. The cutoff score for differentiating patients with Alzheimer's disease from normal participants was = 3. The cutoff score for differentiating those with vascular disease from normal participants was = 3. Overall, the four-point scoring system demonstrated good sensitivity and specificity for identifying cognitive dysfunction associated with dementia; however, the current findings do not support the utility of the four-point scoring system in discriminating Alzheimer's disease and vascular dementia.

scholarly journals Automatic, Qualitative Scoring of the Interlocking Pentagon Drawing Test (PDT) Based on U-Net and Mobile Sensor Data

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1283 ◽  
Author(s):  
Ingyu Park ◽  
Yun Joong Kim ◽  
Yeo Jin Kim ◽  
Unjoo Lee
Keyword(s):  
Performance Test ◽  
Sampling Period ◽  
Field Studies ◽  
Sensor Data ◽  
Mobile Sensor ◽  
Scoring Method ◽  
Convolutional Network ◽  
Mobile Phone Application ◽  
Drawing Test ◽  
Sensitivity Specificity

We implemented a mobile phone application of the pentagon drawing test (PDT), called mPDT, with a novel, automatic, and qualitative scoring method for the application based on U-Net (a convolutional network for biomedical image segmentation) coupled with mobile sensor data obtained with the mPDT. For the scoring protocol, the U-Net was trained with 199 PDT hand-drawn images of 512 × 512 resolution obtained via the mPDT in order to generate a trained model, Deep5, for segmenting a drawn right or left pentagon. The U-Net was also trained with 199 images of 512 × 512 resolution to attain the trained model, DeepLock, for segmenting an interlocking figure. Here, the epochs were iterated until the accuracy was greater than 98% and saturated. The mobile senor data primarily consisted of x and y coordinates, timestamps, and touch-events of all the samples with a 20 ms sampling period. The velocities were then calculated using the primary sensor data. With Deep5, DeepLock, and the sensor data, four parameters were extracted. These included the number of angles (0–4 points), distance/intersection between the two drawn figures (0–4 points), closure/opening of the drawn figure contours (0–2 points), and tremors detected (0–1 points). The parameters gave a scaling of 11 points in total. The performance evaluation for the mPDT included 230 images from subjects and their associated sensor data. The results of the performance test indicated, respectively, a sensitivity, specificity, accuracy, and precision of 97.53%, 92.62%, 94.35%, and 87.78% for the number of angles parameter; 93.10%, 97.90%, 96.09%, and 96.43% for the distance/intersection parameter; 94.03%, 90.63%, 92.61%, and 93.33% for the closure/opening parameter; and 100.00%, 100.00%, 100.00%, and 100.00% for the detected tremor parameter. These results suggest that the mPDT is very robust in differentiating dementia disease subtypes and is able to contribute to clinical practice and field studies.

A reduced scoring system for the Clock Drawing Test using a population-based sample

2012 ◽  
Vol 24 (11) ◽  
pp. 1738-1748 ◽  
Author(s):  
Alexandra Jouk ◽  
Holly Tuokko
Keyword(s):  
Scoring System ◽  
Scoring Systems ◽  
Population Based ◽  
Clinical Samples ◽  
Scoring Method ◽  
Clock Drawing Test ◽  
Clock Drawing ◽  
Dementia Screening ◽  
Drawing Test ◽  
Drawing Task

ABSTRACTBackground: Many scoring systems exist for clock drawing task variants, which are common dementia screening measures, but all have been derived from clinical samples. This study evaluates and combines errors from two published scoring systems for the Clock Drawing Test (CDT), the Lessig and Tuokko methods, in order to create a simple yet optimal scoring procedure to screen for dementia using a Canadian population-based sample.Methods: Clock-drawings from 356 participants (80 with dementia, 276 healthy controls) from the Canadian Study on Health and Aging were analyzed using logistic regression and Receiver Operating Characteristic curves to determine a new, simplified, population-based CDT scoring system. The new Jouk scoring method was then compared to other commonly used systems (e.g. Shulman, Tuokko, Watson, Wolf-Klein).Results: The Jouk scoring system reduced the Lessig system even further to include five critical errors: missing numbers, repeated numbers, number orientation, extra marks, and number distance, and produced a sensitivity of 81% and a specificity of 68% with a cut-off score of one error. With regard to other traditionally used scoring methods, the Jouk procedure had one of the most balanced sensitivities/specificities when using a population-based sample.Conclusions: The results from this study improve our current state of knowledge concerning the CDT by validating the simplified scoring system proposed by Lessig and her colleagues in a more representative sample to mimic conditions a general clinician or researcher will encounter when working among a wide-ranging population and not a dementia/memory clinic. The Jouk CDT scoring system provides further evidence in support of a simple and reliable dementia-screening tool that can be used by clinicians and researchers alike.

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

2021 ◽  
pp. 1-9
Author(s):  
Samad Amini ◽  
Lifu Zhang ◽  
Boran Hao ◽  
Aman Gupta ◽  
Mengting Song ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cognitive Impairment ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
Cost Effective ◽  
Learning Model ◽  
Modeling Framework ◽  
Clock Drawing Test ◽  
Clock Drawing ◽  
Drawing Test

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.

Clock Drawing Test: A Simple Scoring System for the Accurate Screening of Cognitive Impairment in Patients with Mild Cognitive Impairment and Dementia

2018 ◽  
Vol 45 (5-6) ◽  
pp. 326-334 ◽  
Author(s):  
Martin Rakusa ◽  
Joze Jensterle ◽  
Janez Mlakar
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Scoring System ◽  
Mini Mental State Examination ◽  
Screening Method ◽  
Mixed Dementia ◽  
Clock Drawing Test ◽  
Clock Drawing ◽  
Drawing Test ◽  
State Examination

Background/Aim: The Clock Drawing Test (CDT) is a valid alternative screening tool to the Mini-Mental State Examination (MMSE) and, crucially, it may be completed faster. The aim of our study was to standardize and simplify the CDT scoring system for screening in three common conditions: mild cognitive impairment (MCI), Alzheimer’s disease (AD) and mixed dementia (MD). Methods: We included 188 subjects (43 healthy volunteers, 49 patients with MCI, 54 patients with AD, and 42 patients with MD), who performed the MMSE and CDT. The CDT was evaluated using a modified 4-point scoring system. Results: The healthy subjects had the highest median values for the MMSE and CDT, followed by patients with MCI, AD and MD. The optimal cut-off for all patients and each patient group separately was 3 out of 4 points. Sensitivity was 89% for AD, 93% for MD and 83% for all patients, while specificity was 91%. The MMSE produced similar results. In comparison to the MMSE, sensitivity for MCI was significantly higher using the CDT (20 vs. 69%, respectively). Conclusion: A simple, 4-point scoring system may be used as a screening method for fast and accurate detection of cognitive impairment in patients with MCI, AD and MD.

Sign in / Sign up

Export Citation Format

Share Document