Skip to main content

Table 2 Test results of ten networks trained on 34 genes to predict survival among 40 patients

From: Neural network analysis of lymphoma microarray data: prognosis and diagnosis near-perfect

DC NC DC NC
1.000000 0.956252 0.000000 0.189422
1.000000 0.958524 1.000000 0.983387
0.000000 0.030129 1.000000 0.966530
0.000000 0.051647 1.000000 0.972530
0.000000 0.015859 1.000000 0.986147
1.000000 0.960534 0.000000 0.025629
1.000000 0.959209 1.000000 0.934555
1.000000 0.988239 0.000000 0.153694
1.000000 0.883620 0.000000 0.058486
1.000000 0.983992 1.000000 0.985480
1.000000 0.828421 1.000000 0.949153
1.000000 0.527326 1.000000 0.956245
0.000000 0.046066 0.000000 0.147404
0.000000 0.025371 0.000000 0.025772
1.000000 0.987961 1.000000 0.782100
0.000000 0.145338 1.000000 0.977907
0.000000 0.130954 0.000000 0.223562
0.000000 0.148107 0.000000 0.039306
0.000000 0.020277 1.000000 0.982544
1.000000 0.956488 0.000000 0.025932
  1. DC indicates the actual donor class, with 0.0 being negative. NC gives the network evaluation. The NC cutoff throughout this work is: ≥ 0.50 is taken as 1 and <0.50 is taken as 0. * marks the errors