T M Dugan1, S Mukhopadhyay2, A Carroll3, S Downs3. 1. Indiana University , Children's Health Services Research, Indianapolis, IN, United States ; Indiana University Purdue University Indianapolis , Computer Science, Indianapolis, IN, United States. 2. Indiana University Purdue University Indianapolis , Computer Science, Indianapolis, IN, United States. 3. Indiana University , Children's Health Services Research, Indianapolis, IN, United States.
Abstract
OBJECTIVES: This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. METHODS: Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. RESULTS: Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. CONCLUSIONS: This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two.
OBJECTIVES: This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. METHODS: Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. RESULTS: Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. CONCLUSIONS: This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two.
Authors: Catherine L Davis; Norman K Pollock; Jennifer L Waller; Jerry D Allison; B Adam Dennis; Reda Bassali; Agustín Meléndez; Colleen A Boyle; Barbara A Gower Journal: JAMA Date: 2012-09-19 Impact factor: 56.272
Authors: Rena R Wing; Paula Bolin; Frederick L Brancati; George A Bray; Jeanne M Clark; Mace Coday; Richard S Crow; Jeffrey M Curtis; Caitlin M Egan; Mark A Espeland; Mary Evans; John P Foreyt; Siran Ghazarian; Edward W Gregg; Barbara Harrison; Helen P Hazuda; James O Hill; Edward S Horton; Van S Hubbard; John M Jakicic; Robert W Jeffery; Karen C Johnson; Steven E Kahn; Abbas E Kitabchi; William C Knowler; Cora E Lewis; Barbara J Maschak-Carey; Maria G Montez; Anne Murillo; David M Nathan; Jennifer Patricio; Anne Peters; Xavier Pi-Sunyer; Henry Pownall; David Reboussin; Judith G Regensteiner; Amy D Rickman; Donna H Ryan; Monika Safford; Thomas A Wadden; Lynne E Wagenknecht; Delia S West; David F Williamson; Susan Z Yanovski Journal: N Engl J Med Date: 2013-06-24 Impact factor: 91.245
Authors: Thomas A Wadden; Sheri Volger; David B Sarwer; Marion L Vetter; Adam G Tsai; Robert I Berkowitz; Shiriki Kumanyika; Kathryn H Schmitz; Lisa K Diewald; Ronald Barg; Jesse Chittams; Reneé H Moore Journal: N Engl J Med Date: 2011-11-14 Impact factor: 91.245
Authors: Anita Morandi; David Meyre; Stéphane Lobbens; Ken Kleinman; Marika Kaakinen; Sheryl L Rifas-Shiman; Vincent Vatin; Stefan Gaget; Anneli Pouta; Anna-Liisa Hartikainen; Jaana Laitinen; Aimo Ruokonen; Shikta Das; Anokhi Ali Khan; Paul Elliott; Claudio Maffeis; Matthew W Gillman; Marjo-Riitta Järvelin; Philippe Froguel Journal: PLoS One Date: 2012-11-28 Impact factor: 3.240
Authors: K W DeGregory; P Kuiper; T DeSilvio; J D Pleuss; R Miller; J W Roginski; C B Fisher; D Harness; S Viswanath; S B Heymsfield; I Dungan; D M Thomas Journal: Obes Rev Date: 2018-02-09 Impact factor: 9.213
Authors: Felipe Yu Matsushita; Vera Lucia Jornada Krebs; Werther Brunow de Carvalho Journal: Rev Assoc Med Bras (1992) Date: 2022-06-24 Impact factor: 1.712
Authors: Christina Vogel; Stephen Zwolinsky; Claire Griffiths; Matthew Hobbs; Emily Henderson; Emma Wilkins Journal: Int J Obes (Lond) Date: 2019-01-17 Impact factor: 5.095