MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1038/s41390-026-05409-2

Медицинская библиотека · Pediatric research · 2026

Development of a machine-learning risk stratification tool for vasoactive medication need after two-bolus fluid resuscitation in pediatric suspected sepsis.

Velez Tom, Badaki-Makun Oluwakemi, Mercurio Danielle Claire, Hirsch Danielle, Depinet Holly, Dewan Maya, Kamaleswaran Rishikesan, Grunwell Jocelyn, Vong Tyrus, Cross Cody, Triantafyllou Maria, Wolff Nora, Abdelrahman Fehima, Macias Charles, Koutroulis Ioannis

СтатьяПеревод в очереди

Аннотация

BACKGROUND

Timely vasopressor initiation is critical in fluid-refractory pediatric septic shock, yet clinicians lack objective tools to identify children requiring early hemodynamic escalation after fluid resuscitation.

METHODS

We performed a retrospective multicenter study using electronic health record data from five pediatric emergency departments (March 2022-February 2025). Children aged 3 months-17 years screened for sepsis who received ≥2 fluid boluses and were vasopressor-naïve at the second bolus were included. The analytic cohort required abnormal age-adjusted vital signs before the first bolus and documented vital signs after the second bolus. Eight predictors were selected from 41 candidate variables via recursive feature elimination to develop a model predicting subsequent vasopressor administration. A super learner framework evaluated 13 algorithms.

RESULTS

Among 645 eligible patients, 341 met analytic criteria and 88 (25.8%) received vasopressors. Random Forest demonstrated optimal performance (AUROC 0.827 [95% CI 0.777-0.876], AUPRC 0.661). Post-second-bolus mean arterial pressure and baseline MAP severity were the strongest predictors, while blood urea nitrogen was the only retained laboratory variable. Four risk tiers showed vasopressor rates ranging from 6.6% to 63.6%.

CONCLUSION

Machine learning accurately identified children at risk for fluid-refractory septic shock and may support timely vasopressor initiation.

IMPACT: A machine-learning model using eight routinely available clinical variables accurately predicts vasoactive medication need after two fluid boluses in pediatric suspected sepsis. The model stratifies patients into four calibrated risk tiers with a 9.6-fold gradient in vasoactive medication rates, identifying children at risk for fluid-refractory septic shock. This work addresses a critical clinical decision point, whether to continue fluids or escalate to vasoactive medications, where current guidelines offer limited objective guidance. The tool has potential to support earlier recognition of fluid-refractory shock and optimize resuscitation strategies in pediatric emergency care.

Для цитирования: Velez Tom, Badaki-Makun Oluwakemi, Mercurio Danielle Claire, Hirsch Danielle, Depinet Holly, Dewan Maya, Kamaleswaran Rishikesan, Grunwell Jocelyn, Vong Tyrus, Cross Cody, Triantafyllou Maria, Wolff Nora, Abdelrahman Fehima, Macias Charles, Koutroulis Ioannis. Development of a machine-learning risk stratification tool for vasoactive medication need after two-bolus fluid resuscitation in pediatric suspected sepsis.. Pediatric research. 2026. DOI: 10.1038/s41390-026-05409-2.
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.