Fig. 3: Hyperkinetic model for digital speech features selection and accuracy to detect changes in hyperkinetic symptoms of PD.
From: Digital speech biomarkers can measure acute effects of levodopa in Parkinson’s disease
a Regression coefficients, 95% Confidence Intervals, and Relative importances plots from the backward stepwise linear regression model to predict changes in hyperkinetic symptoms of PD (Marconi dyskinesia rating scale axial subscore). b Actual value of the change in Marconi dyskinesia rating scale axial subscore (grey) vs the predicted value and respective 95% CI (purple). *p < 0.05, **p < 0.01, ***p < 0.001. Int sd Standard deviation of Intensity, MPT Maximal phonation time, LTAS Long-term averaged spectrum, sd Standard deviation, kurt Kurtosis, skew Skewness, CI Confidence Interval, MAE Mean absolute error, RMSE Root mean squared error. Created in https://BioRender.com.
