Fact · Typing and writing speed
0.98AUC (area under the ROC curve)
In a 2017 study, a machine-learning ensemble using keystroke timing separated early-stage Parkinson's from controls with an AUC of 0.98 across two separate groups of participants.
Checked against its source on October 16, 2026
In the source's own words
“this approach was able to successfully discriminate between early-PD subjects and controls with 96% sensitivity, 97% specificity and an AUC of 0.98”
High-accuracy detection of early Parkinson's Disease using multiple characteristics of finger movement while typing, Warwick R. Adams, PLOS ONE, 2017, Abstract.
Open the original (DOI 10.1371/journal.pone.0188226)- What it measures
- An AUC of 1.0 would be perfect separation and 0.5 would be chance. The study reports 96 percent sensitivity and 97 percent specificity on the same comparison.
- What it does not show
- A high score on a small study. Independent replication in larger groups is needed before the figure can be treated as typical.