Literature DB >> 25528697

Pre-operative prediction of surgical morbidity in children: comparison of five statistical models.

Jennifer N Cooper1, Lai Wei2, Soledad A Fernandez3, Peter C Minneci4, Katherine J Deans5.   

Abstract

BACKGROUND: The accurate prediction of surgical risk is important to patients and physicians. Logistic regression (LR) models are typically used to estimate these risks. However, in the fields of data mining and machine-learning, many alternative classification and prediction algorithms have been developed. This study aimed to compare the performance of LR to several data mining algorithms for predicting 30-day surgical morbidity in children.
METHODS: We used the 2012 National Surgical Quality Improvement Program-Pediatric dataset to compare the performance of (1) a LR model that assumed linearity and additivity (simple LR model) (2) a LR model incorporating restricted cubic splines and interactions (flexible LR model) (3) a support vector machine, (4) a random forest and (5) boosted classification trees for predicting surgical morbidity.
RESULTS: The ensemble-based methods showed significantly higher accuracy, sensitivity, specificity, PPV, and NPV than the simple LR model. However, none of the models performed better than the flexible LR model in terms of the aforementioned measures or in model calibration or discrimination.
CONCLUSION: Support vector machines, random forests, and boosted classification trees do not show better performance than LR for predicting pediatric surgical morbidity. After further validation, the flexible LR model derived in this study could be used to assist with clinical decision-making based on patient-specific surgical risks.
Copyright © 2014 Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Boosting; Data mining; Logistic regression; Machine learning; Pediatrics; Prediction; Random forests; Support vector machines; Surgical morbidity

Mesh:

Year:  2014        PMID: 25528697      PMCID: PMC4306609          DOI: 10.1016/j.compbiomed.2014.11.009

Source DB:  PubMed          Journal:  Comput Biol Med        ISSN: 0010-4825            Impact factor:   4.589


  34 in total

1.  Comparisons of predictive values of binary medical diagnostic tests for paired designs.

Authors:  W Leisenring; T Alonzo; M S Pepe
Journal:  Biometrics       Date:  2000-06       Impact factor: 2.571

2.  Stratification of adverse outcomes by preoperative risk factors in coronary artery bypass graft patients: an artificial neural network prediction model.

Authors:  Chee-Fah Chong; Yu-Chuan Li; Tzong-Luen Wang; Hang Chang
Journal:  AMIA Annu Symp Proc       Date:  2003

Review 3.  Presentation of multivariate data for clinical use: The Framingham Study risk score functions.

Authors:  Lisa M Sullivan; Joseph M Massaro; Ralph B D'Agostino
Journal:  Stat Med       Date:  2004-05-30       Impact factor: 2.373

4.  Classifying highly imbalanced ICU data.

Authors:  Yazan F Roumani; Jerrold H May; David P Strum; Luis G Vargas
Journal:  Health Care Manag Sci       Date:  2012-11-07

5.  Clostridium difficile colitis in the United States: a decade of trends, outcomes, risk factors for colectomy, and mortality after colectomy.

Authors:  Wissam J Halabi; Vinh Q Nguyen; Joseph C Carmichael; Alessio Pigazzi; Michael J Stamos; Steven Mills
Journal:  J Am Coll Surg       Date:  2013-09-04       Impact factor: 6.113

6.  Development and evaluation of the universal ACS NSQIP surgical risk calculator: a decision aid and informed consent tool for patients and surgeons.

Authors:  Karl Y Bilimoria; Yaoming Liu; Jennifer L Paruch; Lynn Zhou; Thomas E Kmiecik; Clifford Y Ko; Mark E Cohen
Journal:  J Am Coll Surg       Date:  2013-09-18       Impact factor: 6.113

7.  Development of a model for prediction of survival in pediatric trauma patients: comparison of artificial neural networks and logistic regression.

Authors:  Stephen M DiRusso; A Alfred Chahine; Thomas Sullivan; Donald Risucci; Peter Nealon; Sara Cuff; John Savino; Michel Slim
Journal:  J Pediatr Surg       Date:  2002-07       Impact factor: 2.545

8.  A novel tool for reliable and accurate prediction of renal complications in patients undergoing percutaneous coronary intervention.

Authors:  Hitinder S Gurm; Milan Seth; Judith Kooiman; David Share
Journal:  J Am Coll Cardiol       Date:  2013-06-04       Impact factor: 24.094

9.  Artificial neural networks--a method for prediction of survival following liver resection for colorectal cancer metastases.

Authors:  L Spelt; J Nilsson; R Andersson; B Andersson
Journal:  Eur J Surg Oncol       Date:  2013-03-17       Impact factor: 4.424

10.  A plea for neutral comparison studies in computational sciences.

Authors:  Anne-Laure Boulesteix; Sabine Lauer; Manuel J A Eugster
Journal:  PLoS One       Date:  2013-04-24       Impact factor: 3.240

View more
  4 in total

1.  Ensemble machine learning for the prediction of patient-level outcomes following thyroidectomy.

Authors:  Carolyn D Seib; James P Roose; Alan E Hubbard; Insoo Suh
Journal:  Am J Surg       Date:  2020-12-03       Impact factor: 3.125

2.  A novel risk classification system for 30-day mortality in children undergoing surgery.

Authors:  Oguz Akbilgic; Max R Langham; Arianne I Walter; Tamekia L Jones; Eunice Y Huang; Robert L Davis
Journal:  PLoS One       Date:  2018-01-19       Impact factor: 3.240

3.  Predicting congenital heart defects: A comparison of three data mining methods.

Authors:  Yanhong Luo; Zhi Li; Husheng Guo; Hongyan Cao; Chunying Song; Xingping Guo; Yanbo Zhang
Journal:  PLoS One       Date:  2017-05-24       Impact factor: 3.240

4.  An Exome-wide Association Study for Type 2 Diabetes-Attributed End-Stage Kidney Disease in African Americans.

Authors:  Meijian Guan; Jacob M Keaton; Latchezar Dimitrov; Pamela J Hicks; Jianzhao Xu; Nicholette D Palmer; James G Wilson; Barry I Freedman; Donald W Bowden; Maggie C Y Ng
Journal:  Kidney Int Rep       Date:  2018-03-14
  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.