Skip to main content

Table 4 Parameter optimization for all classifiers.

From: A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

AlgorithmParametersBalanced accuracy
Clinical outcome = ‘Death from disease’,
Data=Fischer-M, centralities
DNN [8,8,8,2]o=Adam, lr=1e-3, d=0.387.3% (+0.0)
GEDFNalr=1e-2, h=[64,16], b=879.5% (+8.6)
SVMt=RBF, c=64, g=0.2575.4% (+5.9)
RFn=10075.1% (+3.1)
Clinical outcome = ‘Disease progression’,
Data=Fischer, centralities
DNN [4,2,2,2]o=Adam, lr=1e-3, d=0.384.7% (+0.0)
GEDFNalr=1e-4, h=[16,4], b=3281.2% (+0.4)
SVMt=RBF, c=16, g=0.062581.8% (+2.0)
RFn=10078.1% (+3.2)
  1. One row corresponds to the best model for a given clinical outcome and algorithm. The optimal parameter values are provided (o: optimizer, lr: learning rate, d: dropout, h: sizes of the second and third GEDFN hidden layers, b: batch size, t: SVM kernel type, c: cost, g: gamma, n: number of trees). The gain in balanced accuracy with respect to the models run with default parameters is indicated between parentheses (from Table 3 for DNN)
  2. afor GEDFN, the corresponding omics data is used as input instead of the topological features