Conventional means of Parkinson’s Disease (PD) screening rely on qualitative tests typically administered by trained neurologists. Tablet technologies that enable data collection during handwriting and drawing tasks may provide low-cost, portable, and instantaneous quantitative methods for high-throughput PD screening. However, past efforts to use data from tablet-based drawing processes to distinguish between PD and control populations have demonstrated only moderate classification ability. Focusing on digitized drawings of Archimedean spirals, the present study utilized data from the open-access ParkinsonHW dataset to improve existing PD drawing diagnostic pipelines. Random forest classifiers were constructed using previously documented features and highly-predictive, newly-proposed features that leverage the many unique mathematical characteristics of the Archimedean spiral. This approach yielded an AUC of 0.999 on the particular dataset we tested on, and more importantly identified interpretable features with good promise for generalization across diverse patient cohorts. It demonstrated the potency of mathematical relationships inherent to the drawing shape and the usefulness of sparse feature sets and simple models, which further enhance interpretability, in the face of limited sample size. The results of this study also inform suggestions for future drawing task design and data analytics (feature extraction, shape selection, task diversity, drawing templates, and data sharing).
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.