The Prediction of Body Mass Index from Negative Affectivity through Machine Learning: A Confirmatory Study

This study investigates on the relationship between affect-related psychological variables and Body Mass Index (BMI). We have utilized a novel method based on machine learning (ML) algorithms that forecast unobserved BMI values based on psychological variables, like depression, as predictors. We have employed various machine learning algorithms, including gradient boosting and random forest, with psychological variables relative to 221 subjects to predict both the BMI values and the BMI status (normal, overweight, and obese) of those subjects. We have found that the psychological variables in use allow one to predict both the BMI values (with a mean absolute error of 5.27–5.50) and the BMI status with an accuracy of over 80% (metric: F1-score). Further, our study has also confirmed the particular efficacy of psychological variables of negative type, such as depression for example, compared to positive ones, to achieve excellent predictive BMI values.

[1]  Dimitrios Tzovaras,et al.  Computerized decision support and machine learning applications for the prevention and treatment of childhood obesity: A systematic review of the literature , 2020, Artif. Intell. Medicine.

[2]  Felipe A. Tobar,et al.  Predicting nationwide obesity from food sales using machine learning , 2020, Health Informatics J..

[3]  Zlatan Car,et al.  Using multi-layer perceptron with Laplacian edge detector for bladder cancer diagnosis , 2020, Artif. Intell. Medicine.

[4]  U. Carraro,et al.  Machine Learning Algorithms Predict Body Mass Index Using Nonlinear Trimodal Regression Analysis from Computed Tomography Scans , 2019, IFMBE Proceedings.

[5]  Min Jiang,et al.  On visual BMI analysis from facial images , 2019, Image Vis. Comput..

[6]  Luca Foschini,et al.  Reproducibility in Machine Learning for Health , 2019, RML@ICLR.

[7]  Leo Anthony Celi,et al.  The reproducibility crisis in the age of digital medicine , 2019, npj Digital Medicine.

[8]  Philipp Probst,et al.  Hyperparameters and tuning strategies for random forest , 2018, WIREs Data Mining Knowl. Discov..

[9]  Aakanksha Sharaff,et al.  Extra-Tree Classifier with Metaheuristics Approach for Email Classification , 2019, Advances in Intelligent Systems and Computing.

[10]  Giacomo Mancini,et al.  Emotional intelligence, emotion regulation and affectivity in adults seeking treatment for obesity , 2018, Psychiatry Research.

[11]  J. Ranstam,et al.  LASSO regression , 2018, The British journal of surgery.

[12]  Antitza Dantcheva,et al.  Show me your face and I will tell you your height, weight and body mass index , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[13]  Carlos Dias Maciel,et al.  Dependence between cognitive impairment and metabolic syndrome applied to a Brazilian elderly dataset , 2018, Artif. Intell. Medicine.

[14]  Arielle S. Selya,et al.  Machine Learning for the Classification of Obesity from Dietary and Physical Activity Patterns , 2018 .

[15]  Chee Peng Lim,et al.  Credit Card Fraud Detection Using AdaBoost and Majority Voting , 2019, IEEE Access.

[16]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[17]  Okfalisa,et al.  Comparative analysis of k-nearest neighbor and modified k-nearest neighbor algorithm for data classification , 2017, 2017 2nd International conferences on Information Technology, Information Systems and Electrical Engineering (ICITISEE).

[18]  F. Cabitza,et al.  Unintended Consequences of Machine Learning in Medicine , 2017, JAMA.

[19]  Jonathan H. Chen,et al.  Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations. , 2017, The New England journal of medicine.

[20]  B. Pradhan,et al.  A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility , 2017 .

[21]  Ling Shao,et al.  Discriminative Elastic-Net Regularized Linear Regression , 2017, IEEE Transactions on Image Processing.

[22]  Stephen R. Piccolo,et al.  Tools and techniques for computational reproducibility , 2015, bioRxiv.

[23]  Huiling Chen,et al.  Using Blood Indexes to Predict Overweight Statuses: An Extreme Learning Machine-Based Approach , 2015, PloS one.

[24]  Chih-Hua Tai,et al.  A Framework for Healthcare Everywhere: BMI Prediction Using Kinect and Data Mining Techniques on Mobiles , 2015, 2015 16th IEEE International Conference on Mobile Data Management.

[25]  F. Nuttall,et al.  Body Mass Index , 2020, Definitions.

[26]  M. Cotterchio,et al.  Associations between Anxiety, Depression, Antidepressant Medication, Obesity and Weight Gain among Canadian Women , 2014, PloS one.

[27]  G. Bray,et al.  Handbook of Obesity - Volume 2 : Clinical Applications, Fourth Edition , 2014 .

[28]  Keun Ho Kim,et al.  Prediction of body mass index status from voice signals based on machine learning for automated medical applications , 2013, Artif. Intell. Medicine.

[29]  Victoria Stodden,et al.  Best Practices for Computational Science: Software Infrastructure and Environments for Reproducible and Extensible Research , 2014 .

[30]  Prevention of Obesity using Artificial Intelligence Techniques , 2012 .

[31]  J. Dixon,et al.  The effect of obesity on health outcomes , 2010, Molecular and Cellular Endocrinology.

[32]  D. Nitka,et al.  The association between obesity and anxiety disorders in the population: a systematic review and meta-analysis , 2010, International Journal of Obesity.

[33]  Theo Stijnen,et al.  Overweight, obesity, and depression: a systematic review and meta-analysis of longitudinal studies. , 2010, Archives of general psychiatry.

[34]  William Stafford Noble,et al.  Support vector machine , 2013 .

[35]  Adrian Furnham,et al.  The Role of Trait Emotional Intelligence in a Gender‐Specific Model of Organizational Variables , 2006 .

[36]  J. Seidell,et al.  Epidemiology of obesity. , 2002, Seminars in vascular medicine.

[37]  O. John,et al.  Individual differences in two emotion regulation processes: implications for affect, relationships, and well-being. , 2003, Journal of personality and social psychology.

[38]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[39]  E. Stice.  Risk and maintenance factors for eating pathology: a meta-analytic review. , 2002, Psychological bulletin.

[40]  John R. Koza,et al.  Automated Design of Both the Topology and Sizing of Analog Electrical Circuits Using Genetic Programming , 1996 .

[41]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[42]  M. Argyle,et al.  Happiness as a function of personality and social encounters. , 1989 .

[43]  John Gormally,et al.  The assessment of binge eating severity among obese persons. , 1982, Addictive behaviors.

[44]  C. Spielberger,et al.  Manual for the State-Trait Anxiety Inventory , 1970 .

[45]  J. R. Beaton,et al.  Energy balance and obesity. , 1967, Canadian journal of public health = Revue canadienne de sante publique.