Prevalence and risk factors associated with the need for surgical intervention due to necrotizing enterocolitis in very low birth weight infants

INTRODUCTION

Necrotizing enterocolitis (NEC) is one of the most common gastrointestinal emergencies affecting very low birth weight (VLBW) infants with an incidence of 6-15 %. Early recognition is crucial. Mortality is high and variable (30-50 %). Those requiring surgical intervention have a higher mortality rate than those who receive medical treatment.

OBJECTIVES

1) To assess the prevalence of surgical NEC and associated risk factors 2) To compare outcomes based on the type of treatment required 3) To estimate the mortality associated with NEC and surgical NEC.

METHODS

A multicentre retrospective cohort study was designed (level II), including VLBW infants born between 2011 and 2020 in Centers of the Neocosur Network. A multivariate logistic regression analysis was performed to evaluate risk factors associated with the need for surgery.

RESULTS

NEC was diagnosed in 1679 (10.4 %) of 16,131 births in this period. The prevalence of surgery was 25 % (95 % CI 23-27 %). In multivariable analysis, variables associated with an increased risk of surgery requirement were birth weight <750 g (aOR 1.73-95%CI 1.2-2.5) and receiving antenatal antibiotics (aOR 1.54-95%CI 1.09-2.74). Those requiring surgery had significantly higher morbidity and mortality than the ones receiving medical treatment.

CONCLUSION

In VLBW infants with NEC, lower birth weight and antenatal antibiotics administration were independently associated with the need for surgical intervention.

A novel model to predict severe COVID-19 and mortality using an artificial intelligence algorithm to interpret chest X-Rays and clinical variables

Background

Patients with coronavirus disease 2019 (COVID-19) could develop severe disease requiring admission to the intensive care unit (ICU). This article presents a novel method that predicts whether a patient will need admission to the ICU and assesses the risk of in-hospital mortality by training a deep-learning model that combines a set of clinical variables and features in chest radiographs.

Methods

This was a prospective diagnostic test study. Patients with confirmed severe acute respiratory syndrome coronavirus 2 infection between March 2020 and January 2021 were included. This study was designed to build predictive models obtained by training convolutional neural networks for chest radiograph images using an artificial intelligence (AI) tool and a random forest analysis to identify critical clinical variables. Then, both architectures were connected and fine-tuned to provide combined models.

Results

2552 patients were included in the clinical cohort. The variables independently associated with ICU admission were age, fraction of inspired oxygen (F_iO2) on admission, dyspnoea on admission and obesity. Moreover, the variables associated with hospital mortality were age, F_iO2 on admission and dyspnoea. When implementing the AI model to interpret the chest radiographs and the clinical variables identified by random forest, we developed a model that accurately predicts ICU admission (area under the curve (AUC) 0.92±0.04) and hospital mortality (AUC 0.81±0.06) in patients with confirmed COVID-19.

Conclusions

This automated chest radiograph interpretation algorithm, along with clinical variables, is a reliable alternative to identify patients at risk of developing severe COVID-19 who might require admission to the ICU.

In patients with #COVID19, an automated chest radiograph interpretation algorithm, along with clinical variables, is a reliable alternative to identify patients at risk of developing severe COVID-19, who might require admission to the intensive care unithttps://bit.ly/3Kf61TK

Bronchopulmonary dysplasia: risk prediction models for very-low- birth-weight infants

OBJECTIVE

Our objective is to develop risk prediction models for moderate/severe bronchopulmonary dysplasia (BPD) and BPD and/or death in very-low-birth-weight infants (VLBWI) at birth, 3, 7, and 14 postnatal days.

STUDY DESIGN

It is a multicenter study including 16,407 infants weighing 500-1500 g (2001-2015) from the Neocosur Network. BPD was defined as oxygen dependency at 36 weeks. Variables were selected using forward logistic regression models. Predictive values were evaluated using the ROC curve.

RESULTS

In total, 2580 (15.7%) presented BPD and 6121 (37.3%) BPD/death. The AUC values for the BPD models were 0.788, 0.818, 0.827, and 0.894 respectively. For BPD/death, the AUC values were 0.860, 0.869, 0.867, and 0.906. BW and gestational age had higher contribution at birth; at later ages, the length of oxygen therapy and ventilation had the highest contribution. All AUC values were statistically significant when compared with a neutral value of 0.5 (p-value < 0.001).

CONCLUSIONS

We developed high predictive power models for moderate/severe BPD and BPD/death at four postnatal ages.