International journal of cardiology · 2025
Precision phenomapping of pediatric dilated cardiomyopathy using clustering models based on electronic hospital records.
СтатьяМногоцентровое исследованиеПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод пока не подготовлен
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.
Fu Xihang, Wu Zubo, Shi Jiawei, Han Ling, Wang Lin, Peng Hua, Wu Jing
Аннотация
BACKGROUND: Pediatric dilated cardiomyopathy (PDCM) is a heterogeneous disease, and its clinical management is still considered challenging. This study aimed to establish clinically relevant PDCM subtypes to evaluate prognosis and guide its treatments.
METHODS: Multidimensional data of study participants were derived from electronic hospital records based on a multicenter retrospective cohort in China. Six clustering models for heterogeneous data were adopted to identify PDCM subtypes, and multiple indices were used to select the best model. Multivariable Cox models were adopted to evaluate the association between PDCM subtypes and the risk of adverse clinical events. Finally, a clinical classifier was constructed for clinical application.
RESULTS: A total of 279 idiopathic PDCM cases were included in this study, and two phenotypes developed by the Kamila model were recognized as optimal. Group I was mainly infants and toddlers (median age: 6.32 months) with larger dimensions but mild systolic dysfunction of the left ventricle (LV) while group II was older children (median age: 111.77 months) with severe LV systolic dysfunction, reduced LV wall thickness, and higher prevalence of abnormal valvular regurgitation and arrhythmia. Moreover, group II had a significantly lower event-free survival probability than group I after adjusting for all covariates (HR = 8.096, P = 0.002). The conditional interference tree model with five parameters could accurately distinguish PDCM subtypes.
CONCLUSIONS: PDCM subtypes in our study showed distinct clinical profiles and risks of worse prognosis, and probably have different responses to current standard therapies, which would provide novel directions for precision management and pathological studies of PDCM.
METHODS: Multidimensional data of study participants were derived from electronic hospital records based on a multicenter retrospective cohort in China. Six clustering models for heterogeneous data were adopted to identify PDCM subtypes, and multiple indices were used to select the best model. Multivariable Cox models were adopted to evaluate the association between PDCM subtypes and the risk of adverse clinical events. Finally, a clinical classifier was constructed for clinical application.
RESULTS: A total of 279 idiopathic PDCM cases were included in this study, and two phenotypes developed by the Kamila model were recognized as optimal. Group I was mainly infants and toddlers (median age: 6.32 months) with larger dimensions but mild systolic dysfunction of the left ventricle (LV) while group II was older children (median age: 111.77 months) with severe LV systolic dysfunction, reduced LV wall thickness, and higher prevalence of abnormal valvular regurgitation and arrhythmia. Moreover, group II had a significantly lower event-free survival probability than group I after adjusting for all covariates (HR = 8.096, P = 0.002). The conditional interference tree model with five parameters could accurately distinguish PDCM subtypes.
CONCLUSIONS: PDCM subtypes in our study showed distinct clinical profiles and risks of worse prognosis, and probably have different responses to current standard therapies, which would provide novel directions for precision management and pathological studies of PDCM.