Machine learning models for identifying preterm infants at risk of cerebral hemorrhage

被引：28

作者：

Turova, Varvara ^{[1
]}

Sidorenko, Irina ^{[2
]}

Eckardt, Laura ^{[3
,4
]}

Rieger-Fackeldey, Esther ^{[5
]}

Felderhoff-Mueser, Ursula ^{[3
,4
]}

Alves-Pinto, Ana ^{[1
]}

Lampe, Renee ^{[1
]}

机构：

[1] Tech Univ Munich, Res Unit Pediat Neuroorthoped & Cerebral Palsy, Orthoped Dept, Klinikum Rechts Isar,Buhl Strohmaier Fdn, Munich, Germany

[2] Tech Univ Munich, Math Fac, Chair Math Modelling, Garching, Germany

[3] Univ Duisburg Essen, Univ Hosp Essen, Dept Pediat, Essen, Germany

[4] Univ Duisburg Essen, Univ Hosp Essen, Dept Neonatol, Essen, Germany

[5] Tech Univ Munich, Dept Pediat, Klinikum Rechts Isar, Neonatol, Munich, Germany

来源：

PLOS ONE | 2020年 / 15卷 / 01期

关键词：

INTRAVENTRICULAR HEMORRHAGE; PRESSURE-PASSIVITY; RATES; FLOW;

D O I：

10.1371/journal.pone.0227419

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Intracerebral hemorrhage in preterm infants is a major cause of brain damage and cerebral palsy. The pathogenesis of cerebral hemorrhage is multifactorial. Among the risk factors are impaired cerebral autoregulation, infections, and coagulation disorders. Machine learning methods allow the identification of combinations of clinical factors to best differentiate preterm infants with intra-cerebral bleeding and the development of models for patients at risk of cerebral hemorrhage. In the current study, a Random Forest approach is applied to develop such models for extremely and very preterm infants (23-30 weeks gestation) based on data collected from a cohort of 229 individuals. The constructed models exhibit good prediction accuracy and might be used in clinical practice to reduce the risk of cerebral bleeding in prematurity.

引用

页数：14

共 36 条

[1] Neonatal seizures: Predictors of adverse outcome [J].