Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Feb 17, 2026

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators
09:51

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators

Published on: March 21, 2018

20.5K

Postoperative neonatal mortality prediction using superlearning.

Jennifer N Cooper1, Peter C Minneci2, Katherine J Deans2

  • 1Center for Surgical Outcomes Research and Center for Innovation in Pediatric Practice, The Research Institute at Nationwide Children's Hospital, Columbus, Ohio.

The Journal of Surgical Research
|December 13, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Further Considerations in Pediatric Appendicitis.

JAMA pediatrics·2026
Same author

Is Appendiceal Cancer a Risk of Nonoperative Management of Pediatric Uncomplicated Appendicitis?

The Journal of surgical research·2025
Same author

Identifying Predictors of Recurrent Pilonidal Disease in Adolescents and Young Adults: A Secondary Analysis of a Randomized Controlled Trial.

The Journal of surgical research·2025
Same author

Evaluating Outcomes in Adolescents With Pilonidal Disease Treated With Pilonidal Sinus Trephination.

The Journal of surgical research·2025
Same author

Real-world Multi-institutional Data From the Midwest Pediatric Surgery Consortium (MWPSC) to Assess the Effect of Delayed Kasai Procedure on Biliary Drainage in Patients With Biliary Atresia.

Journal of pediatric surgery·2025
Same author

Prevalence of psychosocial interventions for pediatric dog bite injury: Is the bark actually worse than the bite?

Journal of child & adolescent trauma·2024
Same journal

The Price of Progress: Cost Considerations in Hepatocellular Carcinoma Clinical Trials.

The Journal of surgical research·2026
Same journal

Sex Differences in Thrombin Generation Using Calibrated Automated Thrombogram in Patients With Peripheral Artery Disease.

The Journal of surgical research·2026
Same journal

Beyond the Ventilator: Risk Factors for "Trauma-Associated" Pneumonia in the Trauma Intensive Care Unit.

The Journal of surgical research·2026
Same journal

Impact of In-Network Versus Out-of-Network Fragmentation of Care on Long-Term Outcomes After Trauma.

The Journal of surgical research·2026
Same journal

A Mixed-Methods Study of the Variation in Routine Preoperative Clinic Utilization.

The Journal of surgical research·2026
Same journal

Impact of Social Support on Patient-Reported Outcomes in Cardiothoracic Surgery: A Systematic Review.

The Journal of surgical research·2026
See all related articles

Superlearning, an ensemble machine learning method, accurately predicts 30-day neonatal surgical mortality. This advanced technique offers improved performance over individual algorithms for complex datasets.

Area of Science:

  • Medical informatics
  • Machine learning in healthcare
  • Pediatric surgery outcomes

Background:

  • Neonatal surgery carries variable risks, complicating accurate mortality prediction.
  • Developing precise predictive models for 30-day postoperative mortality in neonates is crucial.

Purpose of the Study:

  • To apply superlearning, an ensemble machine learning approach, for predicting 30-day mortality in neonates undergoing surgery.
  • To evaluate the performance of superlearning against individual algorithms in this prediction task.

Main Methods:

  • Utilized data from the 2012-2014 National Surgical Quality Improvement Program Pediatric database.
  • Developed a superlearner model using 14 regression and machine learning algorithms on 6,499 neonates (2012-13) and validated on 3,552 neonates (2014).
Keywords:
NeonatesPostoperative mortalityPredictionSuperlearning

Related Experiment Videos

Last Updated: Feb 17, 2026

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators
09:51

Model Surgical Training: Skills Acquisition in Fetoscopic Laser Photocoagulation of Monochorionic Diamniotic Twin Placenta Using Realistic Simulators

Published on: March 21, 2018

20.5K
  • Included preoperative demographic and clinical characteristics, and surgical procedure variables; performance assessed by mean squared error, discrimination, and calibration.

    • Main Results:

    • The superlearner model outperformed individual algorithms in cross-validated mean squared error.
    • Achieved excellent discrimination with an area under the receiver-operating characteristic curve of 0.91 (development) and 0.87 (validation).
    • Demonstrated good calibration in development (P=0.06) but not in validation (P<0.001); performance improved with selected variables (AUC 0.89, P=0.63 in validation).

    Conclusions:

    • Superlearning offers improved or equivalent performance for predicting neonatal surgical mortality compared to individual algorithms.
    • This ensemble method is recommended for large datasets with complex mechanisms where parametric modeling is unsuitable.