PP153 Topic: AS14–Infections: Sepsis and Septic Shock/Antimicrobial Stewardship/Tropical and Parasite Infections/Other: IMPROVED PREDICTION OF POST-DISCHARGE MORTALITY INCORPORATING BOTH THE ADMISSION & DISCHARGE CHARACTERISTICS FOR CHILDREN UNDER 5.
Bibliographic record
Abstract
Aims & Objectives: In resource-limited settings, children with suspected sepsis face significant post-discharge mortality risk. We have previously developed a risk prediction model to allow health workers to assess the risk of death at admission. The Smart Discharges program in Uganda employs this model for comprehensive care during admission, discharge and the post-discharge period. This study assesses the added prediction value of incorporating discharge variables to identify children at risk of post-discharge mortality. Methods: This study used a dataset from four multisite prospective studies (2012-2021) of 8,179 children with suspected sepsis in Uganda. We employed elastic net regression integrating admission variables and previously unused discharge data. Models were validated by 10-fold cross-validation. Variable importance was calculated to identify the top 10 contributing variables. Missingness was addressed through multiple imputations. Results: The original clinical variable model had an AUROC of 0.77 and 0.75 for the age groups under 6 and 6-60m, respectively. The enhanced model using discharge variables showed a significant improvement in AUROC of 0.82 (95% CI 0.79-0.80) and 0.79 (95% CI 0.75-0.82). Calibration across risk strata was excellent, with Brier scores of 0.06 and 0.04. The discharge variables with the highest importance included discharge status for both age groups, feeding status for those under six months, and oxygen saturation for the 6-60 months age group. Conclusions: Inclusion of discharge variables significantly improved identification of children at high risk of post-discharge mortality. The enhanced model empowers healthcare professionals by providing updated guidance at discharge, improving care efficiency and sensitivity in identifying at-risk children for follow-up. Keywords: Post-discharge Mortality, Resource-limited settings, Improved Prediction, children under 5, discharge characteristics
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.068 | 0.014 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".