Risk factors for prolonged respiratory support in late preterm infants: a LASSO-Cox regression analysis - Scorecard - MDSpire

Risk factors for prolonged respiratory support in late preterm infants: a LASSO-Cox regression analysis

  • By

  • Yu Huang

  • Xiao-Shuang Bao

  • Na Sun

  • Kai Li

  • Cheng-Cheng Huang

  • Shi-Fai Zhang

  • June 10, 2026

  • 0 min

Share

Clinical Scorecard: Identifying Factors Influencing Extended Respiratory Support in Late Preterm Infants: A LASSO-Cox Regression Study

At a Glance

CategoryDetail
ConditionRespiratory support duration in late preterm infants
Key MechanismsLASSO-Cox regression for variable selection and prediction modeling
Target PopulationLate preterm infants (gestational age 34 + 0–36 + 6 weeks)
Care SettingNeonatal Intensive Care Unit (NICU)

Key Highlights

  • Study enrolled 365 late preterm infants to assess respiratory support duration.
  • Key risk factors identified include multiple pregnancy and elevated superoxide dismutase (SOD).
  • Protective factors include nasal continuous positive airway pressure (NCPAP) and lymphocyte percentage.
  • Model achieved a C-index of 0.677 and time-dependent AUC values indicating moderate-to-good discrimination.
  • SHAP analysis highlighted SOD, NCPAP, and lymphocyte percentage as primary drivers.

Guideline-Based Recommendations

Diagnosis

  • Assess respiratory support needs based on gestational age and clinical indicators.

Management

  • Utilize NCPAP early to potentially shorten respiratory support duration.

Monitoring & Follow-up

  • Monitor superoxide dismutase levels and lymphocyte percentage as part of respiratory support management.

Risks

  • Be aware of increased risk of prolonged respiratory support in cases of multiple pregnancies and elevated SOD.

Patient & Prescribing Data

Late preterm infants requiring respiratory support within 24 hours of birth.

NCPAP is associated with reduced duration of respiratory support.

Clinical Best Practices

  • Implement LASSO-Cox regression models for individualized weaning assessments.
  • Utilize SHAP analysis for transparent interpretation of weaning risk factors.

Related Resources & Content

Original Source(s)

Related Content