AI Science Tracker
EN

Adelaide University

1 discovery from 2026

Discoveries

Neural mortality prediction matches simpler models after emergency laparotomy

Source check: Source checked. Not independent scientific confirmation.

Finding: A multilayer perceptron predicted 30-day mortality using 8,293 emergency laparotomy operations in an Australasian audit. Internal test AUROC was 0.817, without a significant advantage over logistic regression or the NELA score. Imputation before splitting could leak information, although complete-case sensitivity analysis gave similar discrimination. This retrospective result does not establish improved surgical decisions or patient outcomes.

Technology: Multilayer perceptron; radial-basis-function neural network

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Neural networks learn relationships between preoperative audit variables and recorded 30-day mortality.
Test and result
Retrospective internal 80:20 operation-level split, comparison with logistic regression and NELA, and complete-case sensitivity analysis.
Limitation / still unknown
External clinical utility remains unestablished; pre-split imputation and selection among repeated model runs may inflate performance, and the denominator is operations rather than established unique patients.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13529842/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 21 Nov 2026. Review scope: Primary relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships checked..

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 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.