Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 17, 2025

DeepSurv: A machine learning model for predicting mortality in very-low-birth-weight infants treated in intensive care units

View Full Paper
Ask AI
Bookmark
Share

Authors

NBNishankul BozhbanbayevaKazakh National Medical UniversityAAArailym AbilbayevaKazakh National Medical UniversityATAnel TarabayevaKazakh National Medical University

Discussion

Loading...

Member takes

Implication

Retrospective analysis identified DeepSurv as superior in predicting mortality in very-low-birth-weight neonates, suggesting improved risk stratification in neonatal care.

Key Points

  • DeepSurv achieved an overall AUC of 0.95, demonstrating significant superiority over random survival forest and Cox proportional hazards models.
  • The study evaluated 958 very-low-birth-weight neonates in the ICU from January 2021 to May 2025, providing a robust dataset for analysis.
  • Calibration curves indicated high predictive accuracy across all models, with DeepSurv recording the lowest Brier scores during the follow-up period.
  • Decision curve analysis revealed DeepSurv's excellent clinical utility at key timepoints, emphasizing its role in enhancing neonatal mortality prediction.

Cite This Study

Bozhbanbayeva et al. (2025) studied this question.

synapsesocial.com/papers/68a36f840a429f797333238fhttps://doi.org/10.21203/rs.3.rs-7126001/v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Evidence-based interventions to reduce mortality among preterm and low-birthweight neonates in low-income and middle-income countries: a systematic review and meta-analysis2021 · 66 citations
  2. 2Prevalence, mortality and risk factors associated with very low birth weight preterm infants: an analysis of 33 years2018 · 68 citations
  3. 3Feature Selection with the Boruta Package2010 · 5,814 citations