LDAR was the most consistent albumin-derived index for urosepsis ICU mortality
Source check: Source checked. Not independent scientific confirmation.
Finding: In retrospective derivation and external cohorts, LDAR showed the most consistent prognostic performance among six albumin-derived indices. The LASSO-feature MLP had external AUC 0.762 (95% CI 0.687–0.840); SOFA plus logLDAR had AUC 0.782, with no significant difference (DeLong P=0.512). Cohort-definition differences may contribute to performance differences. This is prognostic association and risk stratification, not evidence of clinical benefit or causality.
Technology: LASSO-selected features and multilayer perceptron
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- LASSO selected predictors for an MLP estimating 28-day ICU mortality risk; the paper compared it with severity scores and albumin-derived indices.
- Test and result
- In retrospective derivation and external cohorts, LDAR showed the most consistent prognostic performance among six albumin-derived indices. The LASSO-feature MLP had external AUC 0.762 (95% CI 0.687–0.840); SOFA plus logLDAR had AUC 0.782, with no significant difference (DeLong P=0.512).
- Limitation / still unknown
- Cohort-definition differences may contribute to performance differences. This is prognostic association and risk stratification, not evidence of clinical benefit or causality.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2026.1915095/full
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Original full-text Methods and Results reviewed from the primary paper or preprint; first result-bearing version checked from the supplied source review; author affiliations checked against exact-DOI metadata where available..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.