m+Medelevator.RU
← Поиск публикаций
Studies in health technology and informatics · 2026

Early Postoperative AKI Risk Factors After Pediatric Cardiac Surgery: A Literature-Informed Analysis of Integrated Routine Clinical Data.

СтатьяНазвание и аннотация: Перевод в очереди
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.

Ali-Sadeh Fatemeh, Schack Marcel, Apfel-Starke Johanna Natalie

Аннотация

INTRODUCTION: Acute kidney injury (AKI) is a frequent complication after pediatric cardiac surgery. This study aimed to identify literature-informed perioperative variables associated with AKI within 0-7 days after surgery and to assess whether the resulting risk profile remained visible in an extended routine-data feature set.

METHODS: We performed a retrospective secondary analysis of anonymized routine clinical data comprising 1,354 surgery episodes from 1,135 patients. Feature selection was informed by a structured literature review and resulted in two analytical datasets from the same cohort: Dataset A, a 26-feature core set, and Dataset B, a broader 72-variable feature space used for domain-level robustness analysis. The primary endpoint was AKI within 0-7 days after surgery.

RESULTS: AKI within 0-7 days occurred in 530 of 1,354 episodes (39.14%), and overall postoperative AKI occurred in 566 episodes (41.8%). Episodes with AKI showed longer procedure, cardiopulmonary bypass (CPB), and aortic cross-clamp times and higher mean Vasoactive Inotropic Score (VIS) during the first 24 postoperative hours. The median time from surgery end to the first linked rule-based AKI event was 7.2 hours; 395 of 530 events (74.5%) occurred within 24 hours and 462 (87.2%) within 48 hours.

CONCLUSION: The findings identify a clinically relevant early postoperative risk window characterized by patient vulnerability, intraoperative burden, and early hemodynamic/perfusion instability. Dataset B provided domain-level robustness support, while ehrapy and AnnData enabled reproducible data representation and exploration.

Предметные рубрики MeSH

ИП Урсолов Владлен Сергеевич

ИНН 500118482352 · ОГРНИП 314500117700049

Реквизиты и контакты