Diagnosing pediatric pneumonia under low-resource conditions: The predictive value and reporting reproducibility of chest x-rays
Bibliographic record
Abstract
Background: To meet child mortality targets, it is necessary to improve diagnosis and management of pneumonia. Although CXRs are used as a reference gold standard, their predictive value and reporting reproducibility have never been studied under low-resource conditions. Methods: As part of a larger study of pneumonia in India, we enrolled 502 children below 5 yrs, who met WHO criteria for pneumonia. Patients underwent a detailed examination, saturation and CXR. We selected a sub-group of 133 who had digitized radiographs. ER physician and consultant interpreted films as: normal, minor or major patches, hyperinflation, lobar change, pleural effusion. All children were reviewed 4 days later by a pediatrician and given one of four clinical diagnoses: pneumonia, wheezy disease, mixed and non-respiratory. Films were later reviewed by 2 consultant radiologists. Results: The 10% of X rays showing pleural effusions had good reporter agreement and reliably predicted pneumonia and disease severity. For all other CXR findings (90%), there was no correlation between X ray category and clinical diagnosis, or with disease severity (defined by hospital admission). There was also poor agreement between X ray interpretations made by ER physician, pediatrician and radiologist (all kappa <0.4). Conclusions: With the exception of pleural effusions, CXR findings, interpreted by a radiologist, had no power to predict clinical diagnosis, made by a pediatrician or disease severity. Clinical value of CXRs was further reduced by poor inter-observer agreement. When studying tachypneic children under low-resource conditions, CXRs have less clinical value than is commonly assumed.
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 | 0.019 | 0.097 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".