Author/Authors :
Zhang ، Ying Department of Neonatal - Tianjin Children’s Hospital - Tianjin University , Zhang ، Cheng Department of Neonatal - Tianjin Children’s Hospital - Tianjin University , Shu ، Jianbo Institute of Pediatrics, The Children s Hospital of Tianjin - Tianjin University , Zhang ، Fang Department of Neonatal - Tianjin Children’s Hospital - Tianjin University
Abstract :
Background: We aimed to establish and validate diagnostic models for distinguishing bacterial/viral infections among sepsis neonates and also a model for prognostic evaluation. Methods: Training data sets (cohorts) of neonatal sepsis patients were derived retrospectively from 2017 to 2019, and the verifying sets were followed up from 2019 to 2021. The backward elimination method of logistic regression was used in identifying the optimum feature combination by adding all potential factors to the regression equation. Results: The current study established 3 models. For distinguishing bacterial sepsis patients and bacterial culture-negative patients, we found Y = 1.930+0.105X 1+0.891X 2-1.389X 3-0.774X 4(Y symbolizes the status of bacterial infectious sepsis, X 1is age increase, X 2is intra-amniotic infection (mother), X 3is vomiting sign, and X 4is cough sign). Similarly, for distinguishing bacterial infectious sepsis patients and bacterial/viral double-positive patients, we found Y = 2.918+1.568X 1+1.882X 2-0.113X 3-2.214X 4-2.255X 5-2.312X 6(Y means the bacterial/viral double-positive status, X 1is IL-6 increase, X 2means CRP increase, X 3means age increase, X 4means high fever sign, X 5is cyanotic sign, and X 6is HGB increase). For predicting hospital days as one of the prognoses, we found Y = -1.993+0.073X 1+1.963X 2+0.466X 3-0.791X 4-0.633X 5(Y means worse prognosis, which is hospital days longer than 7 days, X 1means age increase, X 2means intra-amniotic infection (mother), X 3is IL-6 increase, X 4is convulsion with unconsciousness, and X 5is cough sign). Then, the ROC curves of the models from the verifying cohort indicated that all of the 3 models had good performance among sepsis children. Conclusions: Two diagnostic models and one prognostic model were established for clinical reference from the current first-step analysis with excellent model performance, which could be suggested as new useful diagnostic tools and a therapeutic strategy guiding marker for neonatal sepsis in the future.
Keywords :
Neonatal Sepsis , ROC , Prognosis , Logistic Regression , Diagnosis Model
