Derivation and validation of a novel risk assessment tool to identify children aged 2–59 months at risk of hospitalised pneumonia-related mortality in 20 countries
Bibliographic record
Abstract
INTRODUCTION: Existing risk assessment tools to identify children at risk of hospitalised pneumonia-related mortality have shown suboptimal discriminatory value during external validation. Our objective was to derive and validate a novel risk assessment tool to identify children aged 2-59 months at risk of hospitalised pneumonia-related mortality across various settings. METHODS: We used primary, baseline, patient-level data from 11 studies, including children evaluated for pneumonia in 20 low-income and middle-income countries. Patients with complete data were included in a logistic regression model to assess the association of candidate variables with the outcome hospitalised pneumonia-related mortality. Adjusted log coefficients were calculated for each candidate variable and assigned weighted points to derive the Pneumonia Research Partnership to Assess WHO Recommendations (PREPARE) risk assessment tool. We used bootstrapped selection with 200 repetitions to internally validate the PREPARE risk assessment tool. RESULTS: A total of 27 388 children were included in the analysis (mean age 14.0 months, pneumonia-related case fatality ratio 3.1%). The PREPARE risk assessment tool included patient age, sex, weight-for-age z-score, body temperature, respiratory rate, unconsciousness or decreased level of consciousness, convulsions, cyanosis and hypoxaemia at baseline. The PREPARE risk assessment tool had good discriminatory value when internally validated (area under the curve 0.83, 95% CI 0.81 to 0.84). CONCLUSIONS: The PREPARE risk assessment tool had good discriminatory ability for identifying children at risk of hospitalised pneumonia-related mortality in a large, geographically diverse dataset. After external validation, this tool may be implemented in various settings to identify children at risk of hospitalised pneumonia-related mortality.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".