Literature DB >> 29229144

Postoperative neonatal mortality prediction using superlearning.

Jennifer N Cooper1, Peter C Minneci2, Katherine J Deans2.   

Abstract

BACKGROUND: The variable risks associated with neonatal surgery present a challenge to accurate mortality prediction. We aimed to apply superlearning, an ensemble machine learning method, to the prediction of 30-day neonatal postoperative mortality.
MATERIALS AND METHODS: We included neonates in the 2012-2014 National Surgical Quality Improvement Program Pediatric. Patients treated in 2012-13 were used in model development (n = 6499), and patients treated in 2014 formed the validation sample (n = 3552). Our superlearner algorithm included 14 regression and machine learning algorithms and included all preoperative patient demographic and clinical characteristics, including indicator variables for surgical procedures. Performance was evaluated using mean squared error and measures of discrimination and calibration.
RESULTS: The superlearner out-performed all individual algorithms with regard to cross-validated mean squared error. It showed excellent discrimination, with an area under the receiver-operating characteristic curve of 0.91 in development and 0.87 in validation. The superlearner showed good calibration in development but not in validation (Cox calibration test P = 0.06 and P < 0.001, respectively). Performance was improved when the superlearner was fit using only variables strongly associated with mortality in bivariate analysis (area under the receiver-operating characteristic curve 0.89, calibration test P = 0.63 in validation).
CONCLUSIONS: Superlearning provided improved or equivalent performance compared with individual regression and machine learning algorithms for predicting neonatal surgical mortality. This method should be considered for prediction in large data sets whenever complex mechanisms make parametric modeling assumptions unrealistic.
Copyright © 2017 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Neonates; Postoperative mortality; Prediction; Superlearning

Mesh:

Year:  2018        PMID: 29229144     DOI: 10.1016/j.jss.2017.09.002

Source DB:  PubMed          Journal:  J Surg Res        ISSN: 0022-4804            Impact factor:   2.192


  6 in total

1.  An analysis of neonatal mortality following gastro-intestinal and/or abdominal surgery in a tertiary hospital in South Africa.

Authors:  Thozama Siyotula; Marion Arnold
Journal:  Pediatr Surg Int       Date:  2022-03-02       Impact factor: 1.827

2.  Prediction of Incident Atrial Fibrillation in Chronic Kidney Disease: The Chronic Renal Insufficiency Cohort Study.

Authors:  Leila R Zelnick; Michael G Shlipak; Elsayed Z Soliman; Amanda Anderson; Robert Christenson; James Lash; Rajat Deo; Panduranga Rao; Farsad Afshinnia; Jing Chen; Jiang He; Stephen Seliger; Raymond Townsend; Debbie L Cohen; Alan Go; Nisha Bansal
Journal:  Clin J Am Soc Nephrol       Date:  2021-07-12       Impact factor: 10.614

3.  Prediction of neonatal deaths in NICUs: development and validation of machine learning models.

Authors:  Abbas Sheikhtaheri; Mohammad Reza Zarkesh; Raheleh Moradi; Farzaneh Kermani
Journal:  BMC Med Inform Decis Mak       Date:  2021-04-19       Impact factor: 2.796

4.  A maChine and deep Learning Approach to predict pulmoNary hyperteNsIon in newbornS with congenital diaphragmatic Hernia (CLANNISH): Protocol for a retrospective study.

Authors:  Ilaria Amodeo; Giorgio De Nunzio; Genny Raffaeli; Irene Borzani; Alice Griggio; Luana Conte; Francesco Macchini; Valentina Condò; Nicola Persico; Isabella Fabietti; Stefano Ghirardello; Maria Pierro; Benedetta Tafuri; Giuseppe Como; Donato Cascio; Mariarosa Colnaghi; Fabio Mosca; Giacomo Cavallaro
Journal:  PLoS One       Date:  2021-11-09       Impact factor: 3.240

5.  Explainable Artificial Intelligence for Predicting Hospital-Acquired Pressure Injuries in COVID-19-Positive Critical Care Patients.

Authors:  Jenny Alderden; Susan M Kennerly; Andrew Wilson; Jonathan Dimas; Casey McFarland; David Y Yap; Lucy Zhao; Tracey L Yap
Journal:  Comput Inform Nurs       Date:  2022-10-01       Impact factor: 2.146

6.  Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network.

Authors:  Hyun Jeong Do; Kyoung Min Moon; Hyun-Seung Jin
Journal:  Diagnostics (Basel)       Date:  2022-03-03
  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.