A Data-analytical System to Predict Therapy Success for Obese Children

Childhood obesity is an increasingly pervasive problem. Traditional therapy programs are timeand cost-intensive. Furthermore, success of therapy is often not guaranteed. Typically, success of therapies is determined by comparison of body mass index (BMI) before and after a therapy. In this paper, we present a Data-analytical Information Systems (DAIS) that provides predictions of future BMI changes before conducting a therapy. The DAIS considers current parameters like age as well as heart rate during a standardized exercise. By predicting outcomes of a therapy, healthcare practitioners could personalize standard therapies and improve the outcome. We collected data from randomized clinical trial and trained Machine Learning models to estimate whether BMI will decrease after therapy with 85% accuracy. Accuracy of predictions is compared with domain experts’ predictions. Further, we present empirical results of the domain experts' perception regarding the proposed DAIS. Our DAIS provides positive evidence as a tool for personalized medicine.

[1]  Randal S. Olson,et al.  PMLB: a large benchmark suite for machine learning evaluation and comparison , 2017, BioData Mining.

[2]  R. Dalle Grave,et al.  Long-term weight loss maintenance for obesity: a multidisciplinary approach , 2016, Diabetes, metabolic syndrome and obesity : targets and therapy.

[3]  N. Ntoumanis,et al.  Intrinsic motivation in two exercise interventions: Associations with fitness and body composition. , 2016, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[4]  Kelsey Higginson.  Distraction, Enjoyment, and Motivation During an Indoor Cycling Unit of High School Physical Education , 2016 .

[5]  T M Dugan,et al.  Machine Learning Techniques for Prediction of Early Childhood Obesity. , 2015, Applied clinical informatics.

[6]  Anthony Scime.  Expert Knowledge in Data Mining , 2015 .

[7]  G. Bray,et al.  American association of clinical endocrinologists and american college of endocrinology consensus conference on obesity: building an evidence base for comprehensive action. , 2014, Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists.

[8]  C. Apovian,et al.  Guidelines (2013) for managing overweight and obesity in adults , 2014 .

[9]  Ljubomir J. Buturovic,et al.  Cross-validation pitfalls when selecting and assessing regression and classification models , 2014, Journal of Cheminformatics.

[10]  Christopher P. Cerasoli,et al.  Intrinsic motivation and extrinsic incentives jointly predict performance: a 40-year meta-analysis. , 2014, Psychological bulletin.

[11]  K. Tierney,et al.  Zebrafish (Danio rerio) as a model for the study of aging and exercise: Physical ability and trainability decrease with age , 2014, Experimental Gerontology.

[12]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[13]  J. McGill,et al.  American Association of Clinical Endocrinologists’ Comprehensive Diabetes Management Algorithm 2013 Consensus Statement , 2013 .

[14]  C. Dixon,et al.  The effect of a meal on measures of impedance and percent body fat estimated using contact-electrode bioelectrical impedance technology , 2013, European Journal of Clinical Nutrition.

[15]  S. Simon,et al.  Evaluating the impact of point‐ of‐care decision support tools in improving diagnosis of obese children in primary care , 2013, Obesity.

[16]  Wolfgang Maass,et al.  Applying Situation-Service Fit to Physical Environments Enhanced by Ubiquitous Information Systems , 2012, ECIS.

[17]  Nur'Aini Abdul Rashid,et al.  A hybrid approach using Naïve Bayes and Genetic Algorithm for childhood obesity prediction , 2012, 2012 International Conference on Computer & Information Science (ICCIS).

[18]  G. Chock,et al.  A Report on the development of the Hawai'i Pediatric Weight Management Toolkit. , 2011, Hawaii medical journal.

[19]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[20]  Galit Shmueli,et al.  Predictive Analytics in Information Systems Research , 2010, MIS Q..

[21]  Klaus Krippendorff,et al.  Computing Krippendorff's Alpha-Reliability , 2011 .

[22]  S. Blair,et al.  Mortality trends in the general population: the importance of cardiorespiratory fitness , 2010, Journal of psychopharmacology.

[23]  Gavin C. Cawley,et al.  On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation , 2010, J. Mach. Learn. Res..

[24]  Angelo M. Sabatini,et al.  Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers , 2010, Sensors.

[25]  Gemma C. Garriga,et al.  Permutation Tests for Studying Classifier Performance , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[26]  J. Mota,et al.  Cardiorespiratory fitness status and body mass index change over time: a 2-year longitudinal study in elementary school children. , 2009, International journal of pediatric obesity : IJPO : an official journal of the International Association for the Study of Obesity.

[27]  Hong Qiao,et al.  Comparing data mining methods with logistic regression in childhood obesity prediction , 2009, Inf. Syst. Frontiers.

[28]  K. Rattay,et al.  Use of an Electronic Medical Record System to Support Primary Care Recommendations to Prevent, Identify, and Manage Childhood Obesity , 2009, Pediatrics.

[29]  Cristine Mermier,et al.  POST-EXERCISE HEART RATE RECOVERY : AN INDEX OF CARDIOVASCULAR FITNESS , 2009 .

[30]  Nicole L. Nollen,et al.  Motivational interviewing fails to improve outcomes of a behavioral weight loss program for obese African American women: a pilot randomized trial , 2008, Journal of Behavioral Medicine.

[31]  Kimberlee Gauvreau,et al.  Determinants of heart rate recovery following exercise in children. , 2008, Medicine and science in sports and exercise.

[32]  S. Barlow,et al.  Expert committee recommendations regarding the prevention, assessment, and treatment of child and adolescent overweight and obesity: summary report. , 2007, Pediatrics.

[33]  Richard Simon,et al.  Bias in error estimation when using cross-validation for model selection , 2006, BMC Bioinformatics.

[34]  S. Tiukinhoy.  HEART RATE PROFILE DURING EXERCISE AS A PREDICTOR OF SUDDEN DEATH , 2005 .

[35]  Barbara H Wixom,et al.  A Theoretical Integration of User Satisfaction and Technology Acceptance , 2005, Inf. Syst. Res..

[36]  Ian G. Harnik.  Heart-rate profile during exercise as a predictor of sudden death. , 2005, The New England journal of medicine.

[37]  Laura Kann,et al.  Methodology of the youth risk behavior surveillance system. , 2004, MMWR. Recommendations and reports : Morbidity and mortality weekly report. Recommendations and reports.

[38]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[39]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[40]  M. Kersting,et al.  Predictors to success in outpatient training in obese children and adolescents , 2003, International Journal of Obesity.

[41]  J. Friedman.  Stochastic gradient boosting , 2002 .

[42]  Trevor Hastie,et al.  Overview of Supervised Learning , 2001 .

[43]  G. Bellon,et al.  [Personal sports training in the management of obese boys aged 12 to 16 years]. , 2000, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[44]  D R Bassett,et al.  Limiting factors for maximum oxygen uptake and determinants of endurance performance. , 2000, Medicine and science in sports and exercise.

[45]  K. Teo,et al.  Reliability and Validity of Measures of Cardiac Output During Incremental to Maximal Aerobic Exercise , 1999, Sports medicine.

[46]  M. Meuser,et al.  Expertenwissen und Experteninterview , 1994 .

[47]  P. Marshall,et al.  Influence of plasma catecholamines on the lactate threshold during graded exercise. , 1989, Journal of applied physiology.

[48]  Peter J. Rousseeuw,et al.  Robust Regression and Outlier Detection , 2005, Wiley Series in Probability and Statistics.