Validation of dementia diagnostics toolbox using interactive iPad technology. (31st December 2021)

• Record Type: Journal Article
• Authors: Chandra, Jay; Muthupalaniappan, Siva; Shang, Zisheng; Bose, Soham; Deng, Richard; Pecyna, Eryk; Chen, Alexander; Lin, Raymond; Butts, Dignity; Capo‐Battaglia, Athena
• Is Part Of: Alzheimer's & dementia. Volume 17(2021)Supplement 11
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-12-31
• Subjects: Alzheimer's disease -- Periodicals; Alzheimer Disease -- Periodicals; Dementia -- Periodicals; Démence; Maladie d'Alzheimer; Périodique électronique (Descripteur de forme); Ressource Internet (Descripteur de forme); 616.83
• DOI: 10.1002/alz.052988
• Languages: English
• ISSNs: 1552-5260

Abstract

Abstract: Background: Conventional means for dementia diagnosis rely on qualitative tests usually administered after significant pathogenesis. Past studies suggest the utility of more quantitative analytical approaches such as handwriting/drawing tasks (Impedevo et al., 2018). Such tools would provide low‐cost, portable, and instantaneous quantitative diagnostics for more efficient patient screening. However, efforts to realize these methods have faced challenges such as low sample size, incomplete feature extraction, and lack of task diversity. We attempted to create a tablet application that uses pen‐tracking technology to surmount these challenges. Method: As fine motor control provides fundamental markers of neurological health (Bisio et al., 2017; Thomas et al., 2017), rigorous statistical analysis of simple drawing tasks on a tablet permitted differentiation between neuronormative patients and dementia patients with high fidelity. We have started testing our data analysis pipeline with open access datasets: PaHaW (Drotár et al., 2016), Isuniba (Impedovo et al, 2013), ParkinsonHW (Isenkul et al., 2014). These datasets contain drawing data for healthy individuals and those with both dementia and other neurodegenerative diseases. They contain similar raw data that the in‐house iPad app collects. From that raw data, we extracted predictive features, including velocity, acceleration, jerk, curvature, and measures of variation. Result: We have successfully created an iPad app that is able to record the dynamic handwriting process with an Apple Pencil. Our platform has the potential to generate more standardized datasets with improved documentation compared to existing archives. Patients trace complex figures such as spirals and infinity symbols at varying speeds over multiple trials. Additionally, the subjects are asked to remember and draw a shape that was presented to them at the beginning of the test. The app collects key data such as the position of the pen tip, velocity of pen movement, pen angle relative to the surface, and pressure exerted on the surface. Conclusion: We plan to deploy our in‐house iPad app in clinical trials to collect pen‐tracking data with which to facilitate differential diagnoses for neurodegenerative diseases afflicting Alzheimer's and Parkinson's patients. The validation of such a platform would improve upon existing diagnostic datasets and lower major barriers to dementia screening.