Predicting mortality risk for preterm infants using random forest

Jennifer Lee, Jinjin Cai, Fuhai Li, Zachary A. Vesoulis

Research output: Contribution to journalArticlepeer-review

Abstract

Mortality is an unfortunately common outcome of extremely and very preterm birth. Existing clinical prediction models capture mortality risk at birth but fail to account for the remainder of the hospital course. Infants born < 32 weeks gestation with complete physiologic and clinical data were included in this retrospective study. Mortality risk was quantified by conventional means (clinical factors) using the CRIB-II score and the optimal logistic regression model. A random forest (RF) model was trained using a subset of the cohort, labeling data within 6 h of death as “worry.” The model was then tested using the remaining infants. A total of 275 infants were included in the study with a mean gestational age of 27 weeks, mean birth weight of 929 g, 49% female, and a mortality rate of 21%. The CRIB-II and logistic regression models had acceptable performance with sensitivities of 71% and 80% AUC scores of 0.78 and 0.84, respectively. The RF model had superior performance with a sensitivity of 88% and an AUC of 0.93. A random forest model which incorporates fixed clinical factors with the influence of aberrancies in subsequent physiology has superior performance for mortality prediction compared to conventional models.

Original languageEnglish
Article number7308
JournalScientific reports
Volume11
Issue number1
DOIs
StatePublished - Dec 2021

Fingerprint

Dive into the research topics of 'Predicting mortality risk for preterm infants using random forest'. Together they form a unique fingerprint.

Cite this