Skip to main content
. 2026 Sep 16;16:1891664. doi: 10.3389/fcimb.2026.1891664

Figure 7.

Two line charts compare net benefit versus threshold probability for different prediction models and reference strategies in derivation and external validation cohorts. Colored lines represent 7-variable model, logLDAR alone, APACHE II, SOFA, and SAPS II, while dashed and dotted black lines indicate treat all and treat none strategies, respectively. Net benefit decreases as threshold probability increases, with the 7-variable model generally performing best in both cohorts shown in panels A and B.

Decision curve analysis comparing net benefit of the 7-variable model, logLDAR alone, and conventional severity scores (APACHE II, SOFA, SAPS II) in (A) the derivation cohort and (B) the external validation cohort across a range of threshold probabilities.