Table 3.

The selected features per each feature vector (FV) scenario used as input to the K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF) classifiers.

FV scenarios	Selected features
Scenario 1 (N=27)	{Timed|i∈(1, .., 6)}
Scenario 2 (N=27)	{age, Timed|i∈(1, .., 6)}
Scenario 3 (N=21)	{jFishingscore|j∈(max, min, avg, std, median)}
Scenario 4 (N=21)	{Timed, jFishingscore|i∈(1, .., 6)&j∈(max, min, avg, std, median)}
Scenario 5 (N=21)	{age, Timed, jFishingscore|i∈(1, .., 6)&j∈(max, min, avg, std, median)}

N denotes the number of patients with PD included in each FV scenario.