From: Bayesian probit regression model for the diagnosis of pulmonary fibrosis: proof-of-principle
Gene Signature Model | Area Under the Curve | Sensitivity | Specificity | Positive Predictive Value | Negative Predictive Value | Overall Accuracy | Wilcoxon Rank-sum (p-value) |
---|---|---|---|---|---|---|---|
All IPF | 0.774 | 45% | 100% | 100% | 47% | 63% | 0.0023 |
IPF Biopsy | 0.682 | 71% | 67% | 81% | 53% | 70% | 0.048 |
IPF Explant | 0.944 | 74% | 100% | 100% | 65% | 83% | < 0.0001 |