O054 / #742: BUILDING AND VALIDATING A PREDICTION MODEL FOR POST-DISCHARGE MORTALITY AMONG 6 TO 60-MONTH-OLD CHILDREN ADMITTED WITH A PROVEN OR SUSPECTED INFECTION IN UGANDA
Bibliographic record
Abstract
Aims & Objectives: In low- and middle-income countries, many children die following hospitalization for infections. Data driven tools can help healthcare workers identify the most vulnerable children. Our objective was to develop and validate algorithms for post-discharge mortality. Methods: This was a 4-hospital prospective cohort study of 6-60 month old children in Uganda. We collected clinical, anthropometric, social and demographic indicators from consented subjects on admission with a proven or suspected infection. Children were followed up to 6 months post-discharge. Using clinical variables as predictors, we built an elastic net prediction model for post-discharge mortality. We used 10-fold cross validation to determine internal validation of the model building, and we assessed performance of the model using subsequently collected data not used in model building. Results: A total of 2635 children were enrolled and followed up at four hospitals over two time periods, March 2012 to December 2013 and July 2017 to June 2018. Of these, 127 (4.8%) died post discharge. A total of 13 out of 31 predictors were chosen for the model. Of these 13 predictors, the three most important were MUAC, weight for age z-score, and SpO2. The model had an area under the receiver operating curve (AUROC) of 0.74 and a specificity of 58% to achieve 80% sensitivity. In 1523 subsequently collected cases (June 2018 to March 2019), the model performed similarly (AUROC = 0.75, specificity = 55%, sensitivity = 87%). Conclusions: Our model predicted post-discharge mortality based on frugal information collected on admission and performs well in unseen data from similar populations.
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 | 0.006 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".