Endpoint | Description | Calculation |
---|---|---|

Concordance | Proportion of compounds where the model accurately predicted clinical measure | (TP + TN)/ Total # of compounds |

Sensitivity | Proportion of +HSE or scheduled drugs accurately identified by the model | TP/(TP+FN) |

Specificity | Proportion of drugs that do not induce +HSE or are unscheduled accurately identified by the model | TN/(TN+FP) |

Positive Predictive Value (PPV) | Proportion of drugs that are TPs relative to all drugs with a positive result | TP/(TP+FP) |

Negative Predictive Value (NPV) | Proportion of drugs that are TNs relative to all drugs with a negative result | TN/(TN+FN) |

Adjusted PPV | PPV adjusted for a pretest probability (prevalence) of 0.3 | (sensitivity x prevalence)/ [sensitivity x prevalence + (1 – specificity) x (1 – prevalence)] |

Adjusted NPV | NPV adjusted for a pretest probability (prevalence) of 0.7 | specificity x (1 – prevalence)/ [specificity x (1 – prevalence) + (1 – sensitivity) x prevalence)] |

Value added PPV (VaPPV) | Quantitative measurement of value added for positive results relative to pretest probability | Adjusted PPV – prevalence |

Value added NPV (VaNPV) | Quantitative measurement of value added for negative results relative to pretest probability | Adjusted NPV – (1 – prevalence) |

Proportionate reduction in uncertainty (PRU) positive (+) | Proportion by which model reduces uncertainty in predicting drugs with +HSE or are scheduled | VaPPV/(1 – prevalence) |

Proportionate reduction in uncertainty (PRU) negative (–) | Proportion by which model reduces uncertainty in predicting drugs without +HSE or are unscheduled | VaNPV/prevalence |

FN, false negative; FP, false positive; TN, true negative; TP, true positive.