Machine Learning-based Mortality Prediction for Pediatric Fulminant Myocarditis Using Cytokine Profiles
Bibliographic record
Abstract
Abstract Background Fulminant myocarditis (FM) is a rare but life-threatening pediatric condition that rapidly progresses to cardiogenic shock and fatal arrhythmias. Early identification of prognostic biomarkers is vital for timely intervention and better outcomes. Although inflammatory cytokines contribute to FM pathogenesis, their prognostic value remains unclear. This study aimed to identify mortality-associated markers by integrating cytokine profiles and clinical variables through a machine learning approach. Methods We retrospectively analyzed 21 pediatric FM cases from two tertiary centers (2012–2022). At admission, 37 cytokines and 14 clinical parameters were assessed. Partial least squares discriminant analysis was employed to identify prognostic features, with variable importance in projection scores quantifying their contribution. Model performance was evaluated using leave-one-out cross-validation. Statistical significance was determined via the Benjamini-Hochberg method at a false discovery rate of 0.05. Results Of the 51 features analyzed, 23 emerged as key predictors with variable importance in projection scores above 1.0, including 20 cytokines and three clinical parameters. Six cytokines (TNF-α, M-CSF, MIP-1α, IL-8, IL-6, and IL-15) were both statistically significant and highly important. Elevated CK-MB and lactate levels and lower pH were also linked to poor outcomes. The model performed robustly, with an AUC of 0.92, 85.7% accuracy, 92.9% sensitivity, and 71.4% specificity. Conclusions TNF-α emerged as a key cytokine linked to mortality in pediatric FM, supporting its role as a prognostic biomarker and potential therapeutic target.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 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".