EEG microstate features under visual feedback gain conditions exhibit high sensitivity in identifying early Parkinson's disease patients.

Twenty-nine early Parkinson's disease patients were recruited, but 20 were included in the final analysis after data quality screening. Only 20 early Parkinson's disease patients and 18 healthy controls were analysed, so the sample is small. The 100% classification accuracy came from tenfold cross-validation within this same small sample, and the authors say an independent external validation set is required. Participants stopped anti-Parkinson's medication 12 h before testing, but the authors say prior medication effects on EEG microstates cannot be entirely ruled out. The study included only right-handed people with normal or corrected vision and early Parkinson's disease (Hoehn-Yahr stage 1-2.5), so it may not apply to more advanced disease or other visual or handedness profiles.

The study was funded by several Chinese research programmes, including the National Natural Science Foundation of China and Henan Province projects. No competing interests are stated in the supplied text.

Do not treat 100% classification accuracy as proof that this EEG task can diagnose early Parkinson's disease. The accuracy came from a small dataset of 20 patients and 18 controls using tenfold cross-validation within the same sample, and the authors say an independent external validation set is needed.