Skip to main content

Table 3 Varying the input data

From: A three-stage, deep learning, ensemble approach for prognosis in patients with Parkinson’s disease

Method MAPE MAE MSE r R2
Ensemble approach 18.36%
(11.74%, 24.98%)
4.70
(3.56, 5.84)
34.53
(18.81, 50.25)
0.84 0.71
DaTscan + MDS-UPDRS-III + Clinical Information 19.89%
(12.48%, 27.30%)
5.04
(3.78, 6.29)
40.41
(22.09, 58.74)
0.81 0.66
DaTscan + MDS-UPDRS-III (No Clinical Information) 19.89%
(13.63%, 26.15%)
5.22
(4.09, 6.35)
39.37
(24.48, 54.25)
0.81 0.66
MDS-UPDRS-III + Clinical (No DaTscan Information) 26.33%
(17.76%, 34.91%)
6.63
(5.11, 8.14)
65.85
(36.14, 95.57)
0.64 0.41
DaTscan + Clinical (No MDS-UPDRS-III Information) 35.48%
(22.50%, 48.46%)
9.15
(6.90, 11.39)
131.71
(73.60, 189.81)
0.04
(n.s.)
0.00
  1. Data in parentheses are 95% confidence intervals
  2. MAPE, mean absolute percentage error; MAE, mean absolute error; MSE, mean squared error; n.s., not significant; r, Pearson correlation coefficient; R2, coefficient of determination. Unless indicated, values for r were significant (P < 0.001)