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

• Published in: PloS one Vol. 15; no. 1; p. e0227419
• Main Authors: Turova, Varvara, Sidorenko, Irina, Eckardt, Laura, Rieger-Fackeldey, Esther, Felderhoff-Müser, Ursula, Alves-Pinto, Ana, Lampe, Renée
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.01.2020; Public Library of Science (PLoS)
• Subjects: Age; Biology and Life Sciences; Birth weight; Bleeding; Brain damage; Brain injury; Brain research; Cerebral Hemorrhage - diagnosis; Cerebral Hemorrhage - physiopathology; Cerebral palsy; Coagulation; Computer and Information Sciences; Departments; Ethics; Female; Forest management; Gestation; Hemorrhage; Humans; Identification methods; Infant, Extremely Premature; Infant, Newborn; Infants; Learning algorithms; Machine Learning; Male; Medical prognosis; Medicine and Health Sciences; Model accuracy; Models, Cardiovascular; Newborn babies; Obstetrics; Paralysis; Pathogenesis; Pediatrics; Physical Sciences; Premature babies; Research and Analysis Methods; Retrospective Studies; Risk analysis; Risk Factors; Risk reduction; Software; Ultrasonic imaging; Germany
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0227419

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.