Publication
Title
Clinical decision support for improved neonatal care : the development of a machine learning model for the prediction of late-onset sepsis and necrotizing enterocolitis
Author
Abstract
Objective To develop an artificial intelligence (AI)-based software system for predicting late-onset sepsis (LOS) and necrotizing enterocolitis (NEC) in infants admitted to the neonatal intensive care unit (NICU). Study Design Single-center, retrospective cohort study, conducted in the neonatal intensive care unit (NICU) of the Antwerp University Hospital. Continuous monitoring data of 865 preterm infants born below 32 weeks of gestational age, admitted to the NICU in the first week of life, were used to train an XGBoost machine learning (ML) algorithm for LOS and NEC prediction in a cross-validated setup. Afterwards, the model’s performance was assessed on an independent test-set of 148 patients (internal validation). Results The ML model delivered hourly risk predictions with an overall sensitivity of 69% (142/206) for all LOS/NEC episodes and 81% (67/83) for severe LOS/NEC episodes. The model showed a median time gain up to 10 (3.1-21.0) hours, compared to historical clinical diagnosis. On the complete retrospective dataset, the ML model made 721,069 predictions, of which 9,805 (1.3 %) depicted a LOS/NEC probability of ≥ 0.15, resulting in a total alarm rate of less than 1 patient alarm day per week. The model reached a similar performance on the internal validation set. Conclusions AI technology can assist clinicians in the early detection of LOS and NEC in neonatal intensive care which potentially can result in clinical and socio-economic benefits. Additional studies are required to quantify further the effect of combining artificial and human intelligence on patient outcomes in the NICU.
Language
English
Source (journal)
The journal of pediatrics. - St.Louis, Mo.
Publication
St.Louis, Mo. : 2024
ISSN
0022-3476
DOI
10.1016/J.JPEDS.2023.113869
Volume/pages
266 (2024) , p. 1-10
Article Reference
113869
ISI
001159147200001
Pubmed ID
38065281
Full text (Publisher's DOI)
Full text (publisher's version - intranet only)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identifier
Creation 21.12.2023
Last edited 11.04.2024
To cite this reference