Table 8 Provides the comparison of performances of models generated in the present study with other approaches for drug ADR prediction
From: Computational models for the prediction of adverse cardiovascular drug reactions
Dataset | Feature | Algorithm | AUC | Sensitivity/recall | Precision | Accuracy |
|---|---|---|---|---|---|---|
Pauwels et al. 2011 | Substructures | RF | 0.62 | 0.97 | 0.93 | 91.30 |
SMO | 0.50 | 1.00 | 0.92 | 92.42 | ||
Present study | Biological | Random forest | 0.52 | 0.99 | 0.94 | 91.24 |
Chemical | 0.52 | 0.97 | 0.94 | 88.75 | ||
Phenotypic | 0.5 | 1.00 | 0.95 | 93.83 | ||
Biological + chemical | 0.53 | 0.96 | 0.94 | 89.06 | ||
Biological + phenotypic | 0.52 | 1.00 | 0.94 | 93.3 | ||
Chemical + phenotypic | 0.5 | 0.97 | 0.94 | 90.54 | ||
Biological + chemical + phenotypic | 0.54 | 0.96 | 0.94 | 89.07 | ||
Biological | Support vector machine | 0.51 | 0.99 | 0.93 | 93.56 | |
Chemical | 0.48 | 0.95 | 0.94 | 91.41 | ||
Phenotypic | 0.5 | 1.00 | 0.94 | 93.83 | ||
Biological + chemical | 0.53 | 0.95 | 0.94 | 90.24 | ||
Biological + phenotypic | 0.52 | 0.99 | 0.94 | 93.66 | ||
Chemical + phenotypic | 0.48 | 0.96 | 0.94 | 91.49 | ||
Biological + chemical + phenotypic | 0.47 | 0.95 | 0.94 | 90.92 |