Predicting Pediatric Sepsis and Mortality Using Wearable Device Data and Machine Learning in Bangladesh
Bibliographic record
Abstract
Sepsis disproportionately impacts children in low-resource settings, where diagnostic tools like the Phoenix Sepsis Score (PSS) are constrained by reliance on laboratory testing. The objective of this research was to evaluate the use of continuous physiological data from low-cost wearable biosensors and machine learning models to predict pediatric sepsis, septic shock, and mortality in a low-resource, intensive care setting. This prospective observational single-site study analyzed 96 pediatric intensive care unit patients with suspected sepsis in Dhaka, Bangladesh. Physiological data were collected using a wearable biosensor patch, whereas clinical exams, laboratory tests, and PSS criteria identified sepsis, septic shock, and mortality. Least absolute shrinkage and selection operator (LASSO) regression models were developed and validated through leave-one-group-out cross-validation (LOGO-CV) using biosensor data. Our clinical diagnostic model for sepsis using biosensor-only features demonstrated an area under the receiver operating characteristic curve (AUROC) of 0.78 (null AUROC = 0.58). For septic shock, the model demonstrated an AUROC of 0.85 (null AUROC = 0.61). The mortality model demonstrated an AUROC of 0.87 (null AUROC = 0.64). Sensitivity analyses showed improvement of AUROC to 0.89 for prediction of sepsis with manual recorded oxygen saturation (SpO2) included. Although models were trained and tested retrospectively with internal validation, findings demonstrate the potential of wearable biosensors to support pediatric sepsis diagnosis without reliance on advanced diagnostics. These results encourage further external validation with larger, multisite cohorts and real-time mobile health (mHealth) integration to support clinical use in low-resource settings.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 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".