The utility of lung ultrasound score as a predictor for extubation success in ventilated neonates

Background Weaning from mechanical ventilation is a challenging decision, as weaning failure can lead to complications. Because of its non-invasive, convenient, and real-time features, ultrasound has great potential for bedside assessment of critically ill ventilated neonates. Aim of the work This study aimed to evaluate the accuracy of the lung ultrasound severity score (LUSS) as a predictor of extubation outcome in ventilated newborns. As a secondary exploratory objective, we evaluated whether combining LUSS with oxygenation parameters (OI and S/F ratio) provides additional discriminatory value. Study design A prospective observational cohort study was conducted at the NICU of Kafrelsheikh University Hospital. Neonates who were mechanically ventilated for more than 48 h and ready for weaning were included in the study. Lung ultrasound was performed 1 h before planned extubation to assess the predictive value of LUSS for extubation outcome and again 48 h after extubation to assess subsequent changes in lung aeration. The included infants were then categorized into two groups: success group and failure group based on extubation outcome. Results A total of 60 newborns were included, of whom 53 (88.3%) were successfully extubated and 7 (11.7%) failed. The success group had significantly lower pre-extubation LUSS than the failure group. The AUC for pre-extubation LUSS was 0.906 (BCa bootstrap 95% CI: 0.774–0.966; p < 0.001). Among the evaluated thresholds, ≤ 2 yielded the highest Youden index (0.698), with a sensitivity of 69.81% and specificity of 100%. However, a cutoff of ≤ 3 was considered the preferred pragmatic threshold, providing a more balanced sensitivity (81.13%) and specificity (85.71%), with a Youden index of 0.668. In exploratory unvalidated analyses, the combined model including LUSS, OI, and S/F ratio showed an apparent AUC of 0.946; however, this finding should be interpreted cautiously because of the small number of extubation-failure events and absence of internal validation or calibration. Conclusion Pre-extubation LUSS was significantly associated with extubation outcomes in mechanically ventilated neonates. A cutoff of ≤ 3 provided a balanced diagnostic performance in our cohort. However, the additional predictive value of combined models remains uncertain and requires validation in larger studies.

Authors

Institutions

Publication Details

Journal
Egyptian Journal of Bronchology
Published
2026-11-18
DOI
https://doi.org/10.1186/s43168-026-00728-8
Primary Topic
Neonatal Respiratory Health Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

The utility of lung ultrasound score as a predictor for extubation success in ventilated neonates

Osama A. Elagamy, Marwa Eldegwi, Abeer Salama, Eman khamis
3 links
Egyptian Journal of Bronchology
Neonatal Respiratory Health Research
article

The utility of lung ultrasound score as a predictor for extubation success in ventilated neonates

Osama A. Elagamy, Marwa Eldegwi, Abeer Salama, Eman khamis
article en

Abstract

Background Weaning from mechanical ventilation is a challenging decision, as weaning failure can lead to complications. Because of its non-invasive, convenient, and real-time features, ultrasound has great potential for bedside assessment of critically ill ventilated neonates. Aim of the work This study aimed to evaluate the accuracy of the lung ultrasound severity score (LUSS) as a predictor of extubation outcome in ventilated newborns. As a secondary exploratory objective, we evaluated whether combining LUSS with oxygenation parameters (OI and S/F ratio) provides additional discriminatory value. Study design A prospective observational cohort study was conducted at the NICU of Kafrelsheikh University Hospital. Neonates who were mechanically ventilated for more than 48 h and ready for weaning were included in the study. Lung ultrasound was performed 1 h before planned extubation to assess the predictive value of LUSS for extubation outcome and again 48 h after extubation to assess subsequent changes in lung aeration. The included infants were then categorized into two groups: success group and failure group based on extubation outcome. Results A total of 60 newborns were included, of whom 53 (88.3%) were successfully extubated and 7 (11.7%) failed. The success group had significantly lower pre-extubation LUSS than the failure group. The AUC for pre-extubation LUSS was 0.906 (BCa bootstrap 95% CI: 0.774–0.966; p < 0.001). Among the evaluated thresholds, ≤ 2 yielded the highest Youden index (0.698), with a sensitivity of 69.81% and specificity of 100%. However, a cutoff of ≤ 3 was considered the preferred pragmatic threshold, providing a more balanced sensitivity (81.13%) and specificity (85.71%), with a Youden index of 0.668. In exploratory unvalidated analyses, the combined model including LUSS, OI, and S/F ratio showed an apparent AUC of 0.946; however, this finding should be interpreted cautiously because of the small number of extubation-failure events and absence of internal validation or calibration. Conclusion Pre-extubation LUSS was significantly associated with extubation outcomes in mechanically ventilated neonates. A cutoff of ≤ 3 provided a balanced diagnostic performance in our cohort. However, the additional predictive value of combined models remains uncertain and requires validation in larger studies.

Egyptian Journal of BronchologyVol. 20(1)
Kafrelsheikh University (EG)
Good health and well-being
Neonatal Respiratory Health Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon