Frontiers in endocrinology · 2025
Causal insights into gestational diabetes mellitus.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
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.
Zahoor Sheresh, Constantinou Anthony C, O'Halloran Fiona, O'Mahony Louise, O'Riordan Mairead, Kgosidialwa Oratile, Culliney Linda, Said Alhajri Mohammed, Hasanuzzaman Mohammed
Аннотация
INTRODUCTION: Gestational diabetes mellitus (GDM), defined by the onset of hyperglycaemia during pregnancy, remains the most prevalent metabolic complication in pregnancy. It is associated with increased risks of adverse maternal, neonatal, and long-term metabolic outcomes. This study aimed to identify potential causal relationships within clinical data on GDM that could support more targeted and effective interventions.
METHODS: A clinically curated dataset of patients diagnosed with GDM at a major Irish maternity hospital was analysed, covering the study periods 2014-2016 and 2020. A knowledge graph was constructed by integrating clinical expertise, established literature, and insights generated using the GPT-4 large language model. To complement this, 20 structure learning algorithms were applied to independently infer Causal Bayesian Networks (CBNs). A model-averaging approach was then used to generate a consensus-based causal structure to account for variability across individual models.
RESULTS: The integrative model produced a more stable representation of underlying relationships and yielded quantifiable insights to support clinical decision-making. Clinicians involved in the study reported improved confidence in patient care strategies due to the ability to quantify these relationships, facilitating more personalised, evidence-based practice. Key findings from the model-averaged CBN highlighted critical pathways in GDM management, such as the influence of birth weight on neonatal intensive care unit (NICU) admissions and the impact of dietary intervention on maternal glucose regulation. Sensitivity analysis confirmed birth weight, gestational age at delivery, and mode of delivery as major determinants of maternal and neonatal outcomes. Non-modifiable factors, including a history of multiple pregnancies and prior GDM, also contributed to risk stratification.
DISCUSSION: This study applied structure learning techniques to observational clinical data to identify clinically relevant relationships. The resulting insights provide a basis for generating hypotheses that could refine intervention strategies and improve patient outcomes in GDM care.
METHODS: A clinically curated dataset of patients diagnosed with GDM at a major Irish maternity hospital was analysed, covering the study periods 2014-2016 and 2020. A knowledge graph was constructed by integrating clinical expertise, established literature, and insights generated using the GPT-4 large language model. To complement this, 20 structure learning algorithms were applied to independently infer Causal Bayesian Networks (CBNs). A model-averaging approach was then used to generate a consensus-based causal structure to account for variability across individual models.
RESULTS: The integrative model produced a more stable representation of underlying relationships and yielded quantifiable insights to support clinical decision-making. Clinicians involved in the study reported improved confidence in patient care strategies due to the ability to quantify these relationships, facilitating more personalised, evidence-based practice. Key findings from the model-averaged CBN highlighted critical pathways in GDM management, such as the influence of birth weight on neonatal intensive care unit (NICU) admissions and the impact of dietary intervention on maternal glucose regulation. Sensitivity analysis confirmed birth weight, gestational age at delivery, and mode of delivery as major determinants of maternal and neonatal outcomes. Non-modifiable factors, including a history of multiple pregnancies and prior GDM, also contributed to risk stratification.
DISCUSSION: This study applied structure learning techniques to observational clinical data to identify clinically relevant relationships. The resulting insights provide a basis for generating hypotheses that could refine intervention strategies and improve patient outcomes in GDM care.