Figure 2 | Scientific Reports

Figure 2

From: Model-based and Model-free Machine Learning Techniques for Diagnostic Prediction and Classification of Clinical Outcomes in Parkinson’s Disease

Figure 2

Pair correlations of some features, separately for each of the three datasets used in the study. (A) Michigan data boxplots illustrating significant differences in MDS_TREM (p = 0.5465), MDS_PIGD (p < 0.001), H and Y scale (p < 0.001), gaitSpeed_Off (p < 0.001) between PD patients with and without a history of falls, based on MWW test. (No = 0, Yes = 1). (B) Tel-Aviv data boxplots illustrating significant differences in Tremor_score (p = 0.01094), PIGD_score (p < 0.001), H and Y scale (p < 0.001) and FOG_Q (p < 0.001) between PD patients with and without a history of falls, based on MWW test. (No = 0, Yes = 1).

Back to article page