Drawing-Based Automatic Dementia Screening Using Gaussian Process Markov Chains

Lam, Man Fai; Liu, Xunying; Meng, Helen; Tsoi, Kelvin K.

doi:10.24251/hicss.2018.353

Cited by 2 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, 83% of long-term survivors of Parkinson's disease showed dementia, with impairment of their visuospatial functions and executive functions [4]. As up to half of Parkinson's patients show visuospatial dysfunction, the PDT has also been used for the distinction of dementia in Parkinson's disease and Alzheimer's disease cases [5][6][7][8][9][10]. However, the conventional PDT scoring method shows a low sensitivity in detecting visuospatial dysfunction in Parkinson's disease.…”

Section: Introductionmentioning

confidence: 99%

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

Park

Kim

et al. 2020

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Park

Kim

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

Rhythmic musical intervention improves response time of memory tests: A pilot study on the application of a digital cognitive assessment

Hao,

Tran,

Bat

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

Background Memory complaints are the early symptoms of cognitive impairment, and they usually bring anxiety about cognitive deterioration among the elderly population. Musical interventions were demonstrated to relieve dementia symptoms. This pilot study investigated the potential benefits of rhythmic musical intervention, African drumming, on cognitive function and mood status with traditional and digital assessments for elderly participants. Method Participants were recruited through social media. The musical intervention was arranged by drumming instructors certified by the Hong Kong Association of African Drumming. Participants joined regular training classes with eight lessons, which covered rhythmic clapping and drumming, power control, and overall performance with songs. The inclusion criteria included the following: (1) age over 50; (2) self-reported complaints of memory loss; (3) the ability to use digital devices, such as a smartphone; and (4) can understand the content of questionnaires and follow the intervention schedules. Those with hearing impairment, failure to use Chinese, and active psychosis or dementia were excluded. Cognitive function was measured by the Hong Kong version of the Montreal Cognitive Assessment (HK-MoCA) and a digital platform, ScreenMat. Anxiety and depression levels were assessed by the State–Trait Anxiety Inventory (STAI) and Geriatric Depression Scale (GDS-15). All assessments were performed before and after the drumming classes. The outcomes were compared using the Wilcoxon signed rank test with 0.05 as the significance level. Result Twenty-two participants joined this study with an attendance rate of 90%. The overall cognitive function of the participants was good with an average score of 27 for HK-MoCA. After eight sessions of African drum intervention, the cognitive function did not show a significant improvement, but the response time of answering the digital cognitive questions was significantly faster than before the intervention (−39.9 s, p = 0.03). The response time for the short-term memory function was most significantly reduced (−13.5 s, p = 0.017). The anxiety and depression scores (i.e. STAI and GDS) also significantly improved ( p < 0.001) after the intervention. Conclusion Rhythmic musical intervention is not only effective in improving emotional status, but also potentially good for improving cognitive symptoms, including the response time of the memory test. Digital behavioral analysis may bring new insights for future research on cognitive assessment.

show abstract

Drawing-Based Automatic Dementia Screening Using Gaussian Process Markov Chains

Abstract: Abstract

Cited by 2 publications

References 42 publications

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

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

Rhythmic musical intervention improves response time of memory tests: A pilot study on the application of a digital cognitive assessment

Contact Info

Product

Resources

About