Retraction to: npj Digital Medicine https://doi.org/10.1038/s41746-021-00502-8, published online 03 September 2021

The authors have retracted this article because the classification described in the paper was performed on an inaccurate use of a data pre-processing tool, which resulted in an information leak from train to test samples. This has resulted in incorrect classification metrics. However, the statistical differences between features of PD and non-PD populations indicate that this is still an area worthy of further investigation. All authors agree with this retraction.