Peer-reviewed research
Touchscreen typing-pattern analysis for detecting fine motor skills decline in early-stage Parkinson's disease
Dimitrios Iakovakis and Stelios Hadjidimitriou, Scientific Reports, 2018 · DOI 10.1038/s41598-018-25999-0
Read the originalRead on October 16, 2026
- What it is
- Researchers analyzed the timing and pressure of keystrokes on touchscreen smartphones during natural typing, and classified early-stage Parkinson's patients against controls. The method was tested on matched groups of 18 patients and 15 controls.
- How much weight it carries
- Peer-reviewed. Very small matched groups, so the accuracy estimates are wide and unlikely to hold unchanged in a larger population.
Facts taken from this source
- In a 2018 study, a touchscreen-typing method separated early Parkinson's patients from matched controls with an AUC of 0.92, in groups of 18 patients and 15 controls.
“This method achieved an AUC = 0.92 and 0.82/0.81 sensitivity/specificity (matched groups of 18 early PD patients/15 controls)” (Abstract)