Skip to main content
Fig. 2 | BioMedical Engineering OnLine

Fig. 2

From: Evaluating the ability of a predictive vision-based machine learning model to measure changes in gait in response to medication and DBS within individuals with Parkinson’s disease

Fig. 2

Spaghetti plots of MDS-UPDRS-gait scores labelled by the clinician (a) and model (b) in on and off states, grouped by patient and clinical visit. Green lines indicate paired walks where the mds-updrs-gait score was higher in the off state than the on state (indicating improvement in gait on treatment), while red lines denote the pairs where the mds-updrs-gait score was higher on treatment (indicating worsening gait). Yellow is used to denote pairs where no change was noted between the two treatment conditions. The navy lines represent the mean prediction for each treatment condition. Note that a small random jitter factor was applied to each clinician annotated score to improve the visualization

Back to article page