A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis

Jun Ji, Xuefeng B. Ling, Yingzhen Zhao, Zhongkai Hu, Xiaolin Zheng, Zhening Xu, Qiaojun Wen, Zachary J. Kastenberg, Ping Li, Fizan Abdullah, Mary L. Brandt, Richard A. Ehrenkranz, Mary Catherine Harris, Timothy C. Lee, B. Joyce Simpson, Corinna Bowers, R. Lawrence Moss, Karl G. Sylvester

Research output: Contribution to journalArticle

Abstract

Background: Necrotizing enterocolitis (NEC) is a major source of neonatal morbidity and mortality. Since there is no specific diagnostic test or risk of progression model available for NEC, the diagnosis and outcome prediction of NEC is made on clinical grounds. The objective in this study was to develop and validate new NEC scoring systems for automated staging and prognostic forecasting. Study design: A six-center consortium of university based pediatric teaching hospitals prospectively collected data on infants under suspicion of having NEC over a 7-year period. A database comprised of 520 infants was utilized to develop the NEC diagnostic and prognostic models by dividing the entire dataset into training and testing cohorts of demographically matched subjects. Developed on the training cohort and validated on the blind testing cohort, our multivariate analyses led to NEC scoring metrics integrating clinical data. Results: Machine learning using clinical and laboratory results at the time of clinical presentation led to two NEC models: (1) an automated diagnostic classification scheme; (2) a dynamic prognostic method for risk-stratifying patients into low, intermediate and high NEC scores to determine the risk for disease progression. We submit that dynamic risk stratification of infants with NEC will assist clinicians in determining the need for additional diagnostic testing and guide potential therapies in a dynamic manner. Algorithm availability: http://translationalmedicine.stanford. edu/cgi-bin/NEC/index.pl and smartphone application upon request.

Original languageEnglish (US)
Article numbere89860
JournalPLoS One
Volume9
Issue number2
DOIs
StatePublished - Feb 28 2014

Fingerprint

enterocolitis
Necrotizing Enterocolitis
Clinical Laboratory Techniques
prognosis
Testing
Pediatrics
Smartphones
Bins
Learning systems
Teaching
Availability
Pediatric Hospitals
artificial intelligence
testing
Infant Mortality
Routine Diagnostic Tests
disease course
Teaching Hospitals
diagnostic techniques
morbidity

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis. / Ji, Jun; Ling, Xuefeng B.; Zhao, Yingzhen; Hu, Zhongkai; Zheng, Xiaolin; Xu, Zhening; Wen, Qiaojun; Kastenberg, Zachary J.; Li, Ping; Abdullah, Fizan; Brandt, Mary L.; Ehrenkranz, Richard A.; Harris, Mary Catherine; Lee, Timothy C.; Simpson, B. Joyce; Bowers, Corinna; Moss, R. Lawrence; Sylvester, Karl G.

In: PLoS One, Vol. 9, No. 2, e89860, 28.02.2014.

Research output: Contribution to journalArticle

Ji, J, Ling, XB, Zhao, Y, Hu, Z, Zheng, X, Xu, Z, Wen, Q, Kastenberg, ZJ, Li, P, Abdullah, F, Brandt, ML, Ehrenkranz, RA, Harris, MC, Lee, TC, Simpson, BJ, Bowers, C, Moss, RL & Sylvester, KG 2014, 'A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis', PLoS One, vol. 9, no. 2, e89860. https://doi.org/10.1371/journal.pone.0089860
Ji, Jun ; Ling, Xuefeng B. ; Zhao, Yingzhen ; Hu, Zhongkai ; Zheng, Xiaolin ; Xu, Zhening ; Wen, Qiaojun ; Kastenberg, Zachary J. ; Li, Ping ; Abdullah, Fizan ; Brandt, Mary L. ; Ehrenkranz, Richard A. ; Harris, Mary Catherine ; Lee, Timothy C. ; Simpson, B. Joyce ; Bowers, Corinna ; Moss, R. Lawrence ; Sylvester, Karl G. / A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis. In: PLoS One. 2014 ; Vol. 9, No. 2.
@article{1788c13fa5684b63a0e5802f2309342a,
title = "A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis",
abstract = "Background: Necrotizing enterocolitis (NEC) is a major source of neonatal morbidity and mortality. Since there is no specific diagnostic test or risk of progression model available for NEC, the diagnosis and outcome prediction of NEC is made on clinical grounds. The objective in this study was to develop and validate new NEC scoring systems for automated staging and prognostic forecasting. Study design: A six-center consortium of university based pediatric teaching hospitals prospectively collected data on infants under suspicion of having NEC over a 7-year period. A database comprised of 520 infants was utilized to develop the NEC diagnostic and prognostic models by dividing the entire dataset into training and testing cohorts of demographically matched subjects. Developed on the training cohort and validated on the blind testing cohort, our multivariate analyses led to NEC scoring metrics integrating clinical data. Results: Machine learning using clinical and laboratory results at the time of clinical presentation led to two NEC models: (1) an automated diagnostic classification scheme; (2) a dynamic prognostic method for risk-stratifying patients into low, intermediate and high NEC scores to determine the risk for disease progression. We submit that dynamic risk stratification of infants with NEC will assist clinicians in determining the need for additional diagnostic testing and guide potential therapies in a dynamic manner. Algorithm availability: http://translationalmedicine.stanford. edu/cgi-bin/NEC/index.pl and smartphone application upon request.",
author = "Jun Ji and Ling, {Xuefeng B.} and Yingzhen Zhao and Zhongkai Hu and Xiaolin Zheng and Zhening Xu and Qiaojun Wen and Kastenberg, {Zachary J.} and Ping Li and Fizan Abdullah and Brandt, {Mary L.} and Ehrenkranz, {Richard A.} and Harris, {Mary Catherine} and Lee, {Timothy C.} and Simpson, {B. Joyce} and Corinna Bowers and Moss, {R. Lawrence} and Sylvester, {Karl G.}",
year = "2014",
month = "2",
day = "28",
doi = "10.1371/journal.pone.0089860",
language = "English (US)",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

TY - JOUR

T1 - A data-driven algorithm integrating clinical and laboratory features for the diagnosis and prognosis of necrotizing enterocolitis

AU - Ji, Jun

AU - Ling, Xuefeng B.

AU - Zhao, Yingzhen

AU - Hu, Zhongkai

AU - Zheng, Xiaolin

AU - Xu, Zhening

AU - Wen, Qiaojun

AU - Kastenberg, Zachary J.

AU - Li, Ping

AU - Abdullah, Fizan

AU - Brandt, Mary L.

AU - Ehrenkranz, Richard A.

AU - Harris, Mary Catherine

AU - Lee, Timothy C.

AU - Simpson, B. Joyce

AU - Bowers, Corinna

AU - Moss, R. Lawrence

AU - Sylvester, Karl G.

PY - 2014/2/28

Y1 - 2014/2/28

N2 - Background: Necrotizing enterocolitis (NEC) is a major source of neonatal morbidity and mortality. Since there is no specific diagnostic test or risk of progression model available for NEC, the diagnosis and outcome prediction of NEC is made on clinical grounds. The objective in this study was to develop and validate new NEC scoring systems for automated staging and prognostic forecasting. Study design: A six-center consortium of university based pediatric teaching hospitals prospectively collected data on infants under suspicion of having NEC over a 7-year period. A database comprised of 520 infants was utilized to develop the NEC diagnostic and prognostic models by dividing the entire dataset into training and testing cohorts of demographically matched subjects. Developed on the training cohort and validated on the blind testing cohort, our multivariate analyses led to NEC scoring metrics integrating clinical data. Results: Machine learning using clinical and laboratory results at the time of clinical presentation led to two NEC models: (1) an automated diagnostic classification scheme; (2) a dynamic prognostic method for risk-stratifying patients into low, intermediate and high NEC scores to determine the risk for disease progression. We submit that dynamic risk stratification of infants with NEC will assist clinicians in determining the need for additional diagnostic testing and guide potential therapies in a dynamic manner. Algorithm availability: http://translationalmedicine.stanford. edu/cgi-bin/NEC/index.pl and smartphone application upon request.

AB - Background: Necrotizing enterocolitis (NEC) is a major source of neonatal morbidity and mortality. Since there is no specific diagnostic test or risk of progression model available for NEC, the diagnosis and outcome prediction of NEC is made on clinical grounds. The objective in this study was to develop and validate new NEC scoring systems for automated staging and prognostic forecasting. Study design: A six-center consortium of university based pediatric teaching hospitals prospectively collected data on infants under suspicion of having NEC over a 7-year period. A database comprised of 520 infants was utilized to develop the NEC diagnostic and prognostic models by dividing the entire dataset into training and testing cohorts of demographically matched subjects. Developed on the training cohort and validated on the blind testing cohort, our multivariate analyses led to NEC scoring metrics integrating clinical data. Results: Machine learning using clinical and laboratory results at the time of clinical presentation led to two NEC models: (1) an automated diagnostic classification scheme; (2) a dynamic prognostic method for risk-stratifying patients into low, intermediate and high NEC scores to determine the risk for disease progression. We submit that dynamic risk stratification of infants with NEC will assist clinicians in determining the need for additional diagnostic testing and guide potential therapies in a dynamic manner. Algorithm availability: http://translationalmedicine.stanford. edu/cgi-bin/NEC/index.pl and smartphone application upon request.

UR - http://www.scopus.com/inward/record.url?scp=84896541701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896541701&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0089860

DO - 10.1371/journal.pone.0089860

M3 - Article

C2 - 24587080

AN - SCOPUS:84896541701

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

M1 - e89860

ER -