Derivation of four computable 24-hour pediatric sepsis phenotypes to facilitate personalized enrollment in early precise anti-inflammatory clinical trials
Bibliographic record
Abstract
ABSTRACT Objective Thrombotic microangiopathy induced Thrombocytopenia Associated Multiple Organ Failure and hyperinflammatory Macrophage Activation Syndrome are important causes of late pediatric sepsis mortality that are often missed or have delayed diagnosis. Our objective is to derive computable 24-hour sepsis phenotypes to facilitate enrollment in early precise anti-inflammatory trials targeting mortality from these conditions. Design Machine learning analysis using consensus k-means clustering. Setting Nine pediatric intensive care units. Patients 404 children with severe sepsis. Interventions 24-hour computable phenotypes derived using 25 bedside variables including C-reactive protein and ferritin. Measurements and Main Results Four computable phenotypes (PedSep-A, B, C, and D) are derived. Compared to the overall population mean, PedSep-A has the least inflammation (median C-reactive protein 7.3 mg/dL, ferritin 125 ng/mL), younger age, less chronic illness, and more respiratory failure (n = 135; 2% mortality); PedSep-B (median C-reactive protein 13.2 mg/dL, ferritin 225 ng/ mL) has organ failure with intubated respiratory failure, shock, and Glasgow Coma Scale score < 7 (n = 102, 12% mortality); PedSep-C (median C-reactive protein 15.2 mg/dL, ferritin 405 ng/mL) has elevated ferritin, lymphopenia, more shock, more hepatic failure and less respiratory failure (n = 110; mortality 10%); and, PedSep D (median C-reactive protein 13.1 mg/dL ferritin 610 ng/mL), has hyperferritinemic, thrombocytopenic multiple organ failure with more cardiovascular, respiratory, hepatic, renal, hematologic, and neurologic system failures (n = 56, 34% mortality). PedSep-D has highest likelihood of Thrombocytopenia Associated Multiple Organ Failure (Adj OR 47.51 95% CI [18.83-136.83], p < 0.0001) and Macrophage Activation Syndrome (Adj OR 38.63 95% CI [13.26-137.75], p <0.0001), and an observed survivor interaction with combined methylprednisolone and intravenous immunoglobulin therapies (p < 0.05). CONCLUSIONS AND RELEVANCE Machine learning identifies four computable phenotypes ( www.pedsepsis.pitt.edu ). Membership in PedSep-D appears optimal for enrollment in early anti-inflammatory trials targeting Thrombocytopenia Associated Multiple Organ Failure and Macrophage Activation Syndrome . Author’s Comment Question Can machine learning methods derive 24-hour computable pediatric sepsis phenotypes that facilitate early identification of patients for enrollment in precise anti-inflammatory therapy trials? Findings Four distinct phenotypes (PedSep-A, B, C, and D) were derived by assessing 25 bedside clinical variables in 404 children with sepsis. PedSep-D patients had a thrombotic microangiopathy and hyperinflammatory macrophage activation biomarker response, and improved survival odds associated with combined methylprednisolone plus intravenous immunoglobulin therapy. Meaning Four novel computable 24-hour phenotypes are identifiable ( www.pedsepsis.pitt.edu ) that could potentially facilitate enrollment in early precise anti-inflammatory trials targeting thrombotic microangiopathy and macrophage activation in pediatric sepsis.
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 | 0.010 | 0.039 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".