Skip to main content

Table 12 FOG detection: One-freezer-held-out cross validation for the 2-layer LSTM model with and without most frequent freezer

From: Prediction and detection of freezing of gait in Parkinson’s disease from plantar pressure data using long short-term memory neural-networks

  With P07’s data in training set Without P07’s data in training set
Held out participant Sensitivity (%) Specificity (%) Sensitivity (%) Specificity (%)
1 83.0 92.5 42.2 93.8
2 77.2 90.3 82.3 90.0
3 72.5 92.8 61.1 95.0
6 85.9 90.2 63.5 94.4
8 86.2 81.2 81.4 85.8
9 92.2 89.8 92.4 87.4
Mean ± SD 82.8 ± 6.4 89.5 ± 3.9 70.5 ± 16.7 91.1 ± 3.6