Next Article in Journal
HPA Axis in the Pathomechanism of Depression and Schizophrenia: New Therapeutic Strategies Based on Its Participation
Next Article in Special Issue
Restless Legs Syndrome: Known Knowns and Known Unknowns
Previous Article in Journal
Glial PAMPering and DAMPening of Adult Hippocampal Neurogenesis
Previous Article in Special Issue
Blood Serum Cytokines in Patients with Subacute Spinal Cord Injury: A Pilot Study to Search for Biomarkers of Injury Severity
Article

Screening of Parkinson’s Disease Using Geometric Features Extracted from Spiral Drawings

1
Harvard College, Harvard University, Cambridge, MA 02138, USA
2
Global Alliance for Medical Innovation, Cambridge, MA 02138, USA
3
Trinity College of Arts and Sciences, Duke University, Durham, NC 27708, USA
4
Pratt School of Engineering, Duke University, Durham, NC 27708, USA
5
School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA
6
Cognitive Neurology Unit, Beth Israel Deaconess Medical Center, Boston, MA 02215, USA
7
Harvard Medical School, Harvard University, Boston, MA 02115, USA
*
Author to whom correspondence should be addressed.
Authors Contributed Equally.
Academic Editors: Lorenzo Rocci, Anna Latorre and Daniele Belvisi
Brain Sci. 2021, 11(10), 1297; https://doi.org/10.3390/brainsci11101297
Received: 25 August 2021 / Revised: 24 September 2021 / Accepted: 24 September 2021 / Published: 29 September 2021
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). View Full-Text
Keywords: Parkinson’s Disease; biomarker; Archimedean Spiral; disease screening; digitized drawing; machine learning; feature extraction Parkinson’s Disease; biomarker; Archimedean Spiral; disease screening; digitized drawing; machine learning; feature extraction
Show Figures

Figure 1

MDPI and ACS Style

Chandra, J.; Muthupalaniappan, S.; Shang, Z.; Deng, R.; Lin, R.; Tolkova, I.; Butts, D.; Sul, D.; Marzouk, S.; Bose, S.; Chen, A.; Bhaskar, A.; Mantena, S.; Press, D.Z. Screening of Parkinson’s Disease Using Geometric Features Extracted from Spiral Drawings. Brain Sci. 2021, 11, 1297. https://doi.org/10.3390/brainsci11101297

AMA Style

Chandra J, Muthupalaniappan S, Shang Z, Deng R, Lin R, Tolkova I, Butts D, Sul D, Marzouk S, Bose S, Chen A, Bhaskar A, Mantena S, Press DZ. Screening of Parkinson’s Disease Using Geometric Features Extracted from Spiral Drawings. Brain Sciences. 2021; 11(10):1297. https://doi.org/10.3390/brainsci11101297

Chicago/Turabian Style

Chandra, Jay, Siva Muthupalaniappan, Zisheng Shang, Richard Deng, Raymond Lin, Irina Tolkova, Dignity Butts, Daniel Sul, Sammer Marzouk, Soham Bose, Alexander Chen, Anushka Bhaskar, Sreekar Mantena, and Daniel Z. Press. 2021. "Screening of Parkinson’s Disease Using Geometric Features Extracted from Spiral Drawings" Brain Sciences 11, no. 10: 1297. https://doi.org/10.3390/brainsci11101297

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop