TY - JOUR
T1 - Neonatal Sepsis Diagnosis Decision-Making Based on Artificial Neural Networks
AU - Helguera-Repetto, Addy Cecilia
AU - Soto-Ramírez, María Dolores
AU - Villavicencio-Carrisoza, Oscar
AU - Yong-Mendoza, Samantha
AU - Yong-Mendoza, Angélica
AU - León-Juárez, Moisés
AU - González-y-Merchand, Jorge A.
AU - Zaga-Clavellina, Verónica
AU - Irles, Claudine
N1 - Publisher Copyright:
© Copyright © 2020 Helguera-Repetto, Soto-Ramírez, Villavicencio-Carrisoza, Yong-Mendoza, Yong-Mendoza, León-Juárez, González-y-Merchand, Zaga-Clavellina and Irles.
PY - 2020/9/11
Y1 - 2020/9/11
N2 - Neonatal sepsis remains difficult to diagnose due to its non-specific signs and symptoms. Traditional scoring systems help to discriminate between septic or not patients, but they do not consider every single patient particularity. Thus, the purpose of this study was to develop an early- and late-onset neonatal sepsis diagnosis model, based on clinical maternal and neonatal data from electronic records, at the time of clinical suspicion. A predictive model was obtained by training and validating an artificial Neural Networks (ANN) algorithm with a balanced dataset consisting of preterm and term non-septic or septic neonates (early- and late-onset), with negative and positive culture results, respectively, using 25 maternal and neonatal features. The outcome of the model was sepsis or not. The performance measures of the model, evaluated with an independent dataset, outperformed physician's diagnosis using the same features based on traditional scoring systems, with a 93.3% sensitivity, an 80.0% specificity, a 94.4% AUROC, and a regression coefficient of 0.974 between actual and simulated results. The model also performed well-relative to the state-of-the-art methods using similar maternal/neonatal variables. The top 10 factors estimating sepsis were maternal age, cervicovaginitis and neonatal: fever, apneas, platelet counts, gender, bradypnea, band cells, catheter use, and birth weight.
AB - Neonatal sepsis remains difficult to diagnose due to its non-specific signs and symptoms. Traditional scoring systems help to discriminate between septic or not patients, but they do not consider every single patient particularity. Thus, the purpose of this study was to develop an early- and late-onset neonatal sepsis diagnosis model, based on clinical maternal and neonatal data from electronic records, at the time of clinical suspicion. A predictive model was obtained by training and validating an artificial Neural Networks (ANN) algorithm with a balanced dataset consisting of preterm and term non-septic or septic neonates (early- and late-onset), with negative and positive culture results, respectively, using 25 maternal and neonatal features. The outcome of the model was sepsis or not. The performance measures of the model, evaluated with an independent dataset, outperformed physician's diagnosis using the same features based on traditional scoring systems, with a 93.3% sensitivity, an 80.0% specificity, a 94.4% AUROC, and a regression coefficient of 0.974 between actual and simulated results. The model also performed well-relative to the state-of-the-art methods using similar maternal/neonatal variables. The top 10 factors estimating sepsis were maternal age, cervicovaginitis and neonatal: fever, apneas, platelet counts, gender, bradypnea, band cells, catheter use, and birth weight.
KW - machine learning
KW - neural network
KW - newborn
KW - prematurity
KW - sepsis
UR - http://www.scopus.com/inward/record.url?scp=85091573242&partnerID=8YFLogxK
U2 - 10.3389/fped.2020.00525
DO - 10.3389/fped.2020.00525
M3 - Artículo
AN - SCOPUS:85091573242
SN - 2296-2360
VL - 8
JO - Frontiers in Pediatrics
JF - Frontiers in Pediatrics
M1 - 525
ER -