Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults
Abstract
:1. Introduction
2. Materials and Methods
2.1. Data Source
2.2. Classical Machine Learning Algorithms and Predictive Model Based on Cascade Classifier Flow
2.3. Performance Assessing Metrics of the Algorithms
2.4. Ranking of the Predictive Algorithm: Statistical Validation
2.5. Predictive Variables with a Greater Impact on Overweight/Obesity Risk: SHAP Tool
3. Results
3.1. Description of Recruited Population
3.2. Cross-Validation of Classical Machine Learning Algorithms
3.3. Results of the Cascade Classifier Model
- -
- Gradient boosting was used as the first-level classifier. This model focused on performing the largest individual classification between the high risk of overweight/obesity or normal weight groups. In this case, an accuracy of 80% was obtained out of a total of 135/295 classified individuals. The false-negative value was low (18), indicating that the recall of the overweight/obese class was 89% since there were hardly any cases of individuals suffering from overweight/obesity. Unclassified subjects were passed to the classification model of the following level.
- -
- Random forest was used as the second-level classifier. The number of classified individuals was smaller than gradient boosting since the input data of this model were unclassified individuals by gradient boosting. The level of difficulty of classification increases as the cascade classifier progresses. However, 34 individuals out of the 160 received were successfully classified. The results of the confusion matrix are quite good since the false-negative value was still low (3), with a recall of almost 70%.
- -
- Logistic regression was used as the third-level classifier. This classifier classified the fewest individuals, since their factors did not clearly express to the model any type of classification within the established levels. The results reveal that the other 24 individuals were successfully classified with an accuracy of 83% and an excellent positive recall of 93%, since only one false negative was obtained. This means that, of the 15 overweight cases that had entered this model, only one of them was wrongly classified as non-overweight.
3.4. Comparison of Effectiveness between Classical Machine Learning Algorithms and Cascade Classifier for Predicting Overweight/Obesity
3.5. Variables with the Greatest Impact on Overweight/Obesity Predictions: Interpretation of Personalized Prediction
4. Discussion
5. Conclusions
- Three-stage classification model based on a combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately.
- The predictive model created and SHAP technique had the ability to show those individualized modifiable factors with significant impacts on weight gain. This offers a transparent explanation of personalized risk prediction, enabling health professionals to gain an intuitive understanding of the impact of key features in the model.
- More studies are needed to further improve the quality of predictions, exploring the effect of other factors not included in the dataset. The validation of the results might help to optimize the designs of health policies and programs to decrease obesity incidence/prevalence and, in turn, reduce the severity as well as the cost of treating obesity and obesity-related conditions, which eventually could improve the health and well-being of the population.
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Consumer Affairs. Ministry of Health and Social Welfare. National Health Survey. Spain. 2017. Available online: https://www.sanidad.gob.es/estadEstudios/estadisticas/encuestaNacional/encuestaNac2017/ENSE2017_notatecnica.pdf (accessed on 15 January 2021). (In Spanish).
- Fruh, S.M. Obesity: Risk factors, complications, and strategies for sustainable long-term weight management. J. Am. Assoc. Nurse Pract. 2017, 29, S3–S14. [Google Scholar] [CrossRef] [PubMed]
- WHO. Obesity and Overweight. 2024. Available online: https://www.who.int/news-room/fact-sheets/detail/obesity-and-overweight (accessed on 15 July 2024).
- Telleria-Aramburu, N.; Arroyo-Izaga, M. Risk factors of overweight/obesity-related lifestyles in university students: Results from the EHU12/24 study. Br. J. Nutr. 2022, 127, 914–926. [Google Scholar] [CrossRef] [PubMed]
- Cheadle, A.; Atiedu, A.; Rauzon, S.; Schwartz, P.M.; Keene, L.; Davoudi, M.; Spring, R.; Molina, M.; Lee, L.; Boyle, K.; et al. A Community-Level Initiative to Prevent Obesity: Results from Kaiser Permanente’s Healthy Eating Active Living Zones Initiative in California. Am. J. Prev. Med. 2018, 54 (Suppl. S2), S150–S159. [Google Scholar] [CrossRef] [PubMed]
- Narciso, J.; Silva, A.J.; Rodrigues, V.; Monteiro, M.J.; Almeida, A.; Saavedra, R.; Costa, A.M. Behavioral, contextual and biological factors associated with obesity during adolescence: A systematic review. PLoS ONE 2019, 14, e0214941. [Google Scholar] [CrossRef] [PubMed]
- Chatterjee, A.; Gerdes, M.W.; Martinez, S.G. Identification of Risk Factors Associated with Obesity and Overweight—A Machine Learning Overview. Sensors 2020, 20, 2734. [Google Scholar] [CrossRef] [PubMed]
- Börnhorst, C.; Russo, P.; Veidebaum, T.; Tornaritis, M.; Molnár, D.; Lissner, L.; Mårild, S.; De Henauw, S.; Moreno, L.A.; Floegel, A.; et al. The role of lifestyle and non-modifiable risk factors in the development of metabolic disturbances from childhood to adolescence. Int. J. Obes. 2020, 44, 2236–2245. [Google Scholar] [CrossRef] [PubMed]
- Hruby, A.; Hu, F.B. The Epidemiology of Obesity: A Big Picture. Pharmacoeconomics 2015, 33, 673–689. [Google Scholar] [CrossRef] [PubMed]
- Battineni, G.; Sagaro, G.G.; Chinatalapudi, N.; Amenta, F. Applications of Machine Learning Predictive Models in the Chronic Disease Diagnosis. J. Pers. Med. 2020, 10, 21. [Google Scholar] [CrossRef] [PubMed]
- Dick, S. Artificial intelligence. Harv. Data Sci. Rev. 2019, 1, 7. [Google Scholar]
- Scheinker, D.; Valencia, A.; Rodriguez, F. Identification of Factors Associated with Variation in US County-Level Obesity Prevalence Rates Using Epidemiologic vs. Machine Learning Models. JAMA Netw. Open 2019, 2, e192884. [Google Scholar] [CrossRef]
- DeGregory, K.W.; Kuiper, P.; DeSilvio, T.; Pleuss, J.D.; Miller, R.; Roginski, J.W.; Fisher, C.B.; Harness, D.; Viswanath, S.; Heymsfield, S.B.; et al. A review of machine learning in obesity. Obes. Rev. 2018, 19, 668–685. [Google Scholar] [CrossRef] [PubMed]
- Golino, H.F.; Amaral, L.S.D.B.; Duarte, S.F.P.; Gomes, C.M.A.; Soares, T.D.J.; Reis, L.A.D.; Santos, J. Predicting increased blood pres-sure using machine learning. J. Obes. 2014, 2014, 637635. [Google Scholar] [CrossRef] [PubMed]
- Pleuss, J.D.; Talty, K.; Morse, S.; Kuiper, P.; Scioletti, M.; Heymsfield, S.B.; Thomas, D.M. A machine learning approach relating 3D body scans to body composition in humans. Eur. J. Clin. Nutr. 2019, 73, 200–208. [Google Scholar] [CrossRef] [PubMed]
- Maharana, A.; Nsoesie, E.O. Use of deep learning to examine the association of the built environment with prevalence of neighborhood adult obesity. JAMA Netw. Open 2018, 1, e181535. [Google Scholar] [CrossRef] [PubMed]
- Pouladzadeh, P.; Kuhad, P.; Peddi, S.V.B.; Yassine, A.; Shirmohammadi, S. Food calorie measurement using deep learning neural network. In Proceedings of the 2016 IEEE International Instrumentation and Measurement Technology Conference, Taipei, Taiwan, 23–26 May 2016; pp. 1–6. [Google Scholar]
- De-La-Hoz-Correa, E.; Mendoza Palechor, E.; De-La-Hoz-Manotas, E.; Morales Ortega, A.; Sánchez Hernández, R.; Adriana, B. Obesity level estimation software based on decision trees. J. Comput. Sci. 2019, 15, 67–77. [Google Scholar] [CrossRef]
- Singh, B.; Tawfik, H. Machine Learning Approach for the Early Prediction of the Risk of Overweight and Obesity in Young People. In Proceedings of the Computational Science—ICCS 2020: 20th International Conference, Amsterdam, The Netherlands, 3–5 June 2020; Volume 12140, pp. 523–535. [Google Scholar]
- Breiman, L. Bagging predictors. J. Time Ser. Anal. 1994, 17, 421. [Google Scholar] [CrossRef]
- Natekin, A.; Knoll, A. Gradient boosting machines, a tutorial. Front. Neurorobotics 2013, 7, 21. [Google Scholar] [CrossRef] [PubMed]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Monaghan, T.F.; Rahman, S.N.; Agudelo, C.W.; Wein, A.J.; Lazar, J.M.; Everaert, K.; Dmochowski, R.R. Foundational Statistical Principles in Medical Research: Sensitivity, Specificity, Positive Predictive Value, and Negative Predictive Value. Medicina 2021, 57, 503. [Google Scholar] [CrossRef] [PubMed]
- Friedman, M. The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J. Am. Stat. Assoc. 1937, 32, 675–701. [Google Scholar] [CrossRef]
- Friedman, M. A Comparison of Alternative Tests of Significance for the Problem of m Rankings. Ann. Math. Stat. 1940, 11, 86–92. [Google Scholar] [CrossRef]
- Derrac, J.; García, S.; Molina, D.; Herrera, F. A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evol. Comput. 2011, 1, 3–18. [Google Scholar] [CrossRef]
- Futagami, K.; Fukazawa, Y.; Kapoor, N.; Kito, T. Pairwise acquisition prediction with SHAP value interpretation. J. Financ. Data Sci. 2021, 7, 22–44. [Google Scholar] [CrossRef]
- Mangalathu, S.; Hwang, S.H.; Jeon, J.S. Failure mode and effects analysis of RC members based on machine-learning-based Shapley Additive Explanations (SHAP) approach. Eng. Struct. 2020, 219, 110927. [Google Scholar] [CrossRef]
- Zeng, W.; Davoodi, A.; Topaloglu, R.O. Explainable DRC Hotspot Prediction with Random Forest and SHAP Tree Explainer. In Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 9–13 March 2020; pp. 1151–1156. [Google Scholar]
- Lundberg, S.M.; Lee, S.I. Unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 2017, 30, 4765–4774. [Google Scholar]
- Zou, Q.; Qu, K.; Luo, Y.; Yin, D.; Ju, Y.; Tang, H. Predicting Diabetes Mellitus with Machine Learning Techniques. Front. Genet. 2018, 9, 515. [Google Scholar] [CrossRef] [PubMed]
- Acharjee, A.; Ament, Z.; West, J.A.; Stanley, E.; Griffin, J.L. Integration of metabolomics, lipidomics and clinical data using a machine learning method. BMC Bioinform. 2016, 17 (Suppl. S15), 440. [Google Scholar] [CrossRef]
- Dugan, T.M.; Mukhopadhyay, S.; Carroll, A.; Downs, S. Machine Learning Techniques for Prediction of Early Childhood Obesity. Appl. Clin. Inform. 2015, 6, 506–520. [Google Scholar]
- Ellis, K.; Kerr, J.; Godbole, S.; Staudenmayer, J.; Lanckriet, G. Hip and Wrist Accelerometer Algorithms for Free-Living Behavior Classification. Med. Sci. Sports Exerc. 2016, 48, 933. [Google Scholar] [CrossRef]
- Triantafyllidis, A.; Polychronidou, E.; Alexiadis, A.; Rocha, C.L.; Oliveira, D.N.; da Silva, A.S.; Freire, A.L.; Macedo, C.; Sousa, I.F.; Werbet, E.; et al. Computerized decision support and machine learning applications for the prevention and treatment of childhood obesity: A systematic review of the literature. Artif. Intell. Med. 2020, 104, 101844. [Google Scholar] [CrossRef]
- Yi, X.; He, Y.; Gao, S.; Li, M. A review of the application of deep learning in obesity: From early prediction aid to advanced management assistance. Diabetes Metab. Syndr. Clin. Res. Rev. 2024, 18, 103000. [Google Scholar] [CrossRef] [PubMed]
- Safaei, M.; Sundararajan, E.A.; Driss, M.; Boulila, W.; Shapi’i, A. A systematic literature review on obesity: Understanding the causes & consequences of obesity and reviewing various machine learning approaches used to predict obesity. Comput. Biol. Med. 2021, 136, 104754. [Google Scholar]
- Singh, B.; Tawfik, H. A Machine Learning Approach for Predicting Weight Gain Risks in Young Adults. In Proceedings of the 2019 10th International Conference on Dependable Systems, Services and Technologies (DESSERT), Leeds, UK, 5–7 June 2019; pp. 231–234. [Google Scholar]
- Uçar, M.K.; Uçar, Z.; Köksal, F.; Daldal, N. Estimation of body fat percentage using hybrid machine learning algorithms. Measurement 2021, 167, 108173. [Google Scholar] [CrossRef]
- Zheng, Z.; Ruggiero, K. Using machine learning to predict obesity in high school students. In Proceedings of the 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Kansas City, MO, USA, 13–16 November 2017; pp. 2132–2138. [Google Scholar]
- Solomon, D.D.; Khan, S.; Garg, S.; Gupta, G.; Almjally, A.; Alabduallah, B.I.; Alsagri, H.S.; Ibrahim, M.M.; Abdallah, A.M.A. Hybrid Majority Voting: Prediction and Classification Model for Obesity. Diagnostics 2023, 13, 2610. [Google Scholar] [CrossRef] [PubMed]
- Taghiyev, A.; Altun, A.A.; Caglar, S.A. Hybrid Approach Based on Machine Learning to Identify the Causes of Obesity. J. Control Eng. Appl. Inform. 2020, 22, 56–66. [Google Scholar]
- Jindal, K.; Baliyan, N.; Rana, P.S. Obesity prediction using ensemble machine learning approaches. In Recent Findings in Intelligent Computing Techniques; Springer: Singapore, 2018; pp. 355–362. [Google Scholar]
- Ngiam, K.Y.; Khor, I.W. Big data and machine learning algorithms for health-care delivery. Lancet Oncol. 2019, 20, e262–e273. [Google Scholar] [CrossRef] [PubMed]
- Thamrin, S.A.; Arsyad, D.S.; Kuswanto, H.; Lawi, A.; Nasir, S. Predicting Obesity in Adults Using Machine Learning Techniques: An Analysis of Indonesian Basic Health Research 2018. Front. Nutr. 2021, 8, 669155. [Google Scholar] [CrossRef] [PubMed]
- Lin, W.; Shi, S.; Huang, H.; Wen, J.; Chen, G. Predicting risk of obesity in overweight adults using interpretable machine learning algorithms. Front. Endocrinol. 2023, 14, 1292167. [Google Scholar] [CrossRef]
- Mancuso, P.; Bouchard, B. The Impact of Aging on Adipose Function and Adipokine Synthesis. Front. Endocrinol. 2019, 10, 137. [Google Scholar] [CrossRef]
- Wang, X.; Xu, M.; Li, Y. Adipose Tissue Aging and Metabolic Disorder, and the Impact of Nutritional Interventions. Nutrients 2022, 14, 3134. [Google Scholar] [CrossRef]
- Conte, M.; Martucci, M.; Sandri, M.; Franceschi, C.; Salvioli, S. The Dual Role of the Pervasive “Fattish” Tissue Remodeling with Age. Front. Endocrinol. 2019, 10, 114. [Google Scholar] [CrossRef] [PubMed]
- Davis, S.R.; Castelo-Branco, C.; Chedraui, P.; Lumsden, M.A.; Nappi, R.E.; Shah, D.; Villaseca, P.; Writing Group of the International Menopause Society for World Menopause Day 2012. Understanding weight gain at menopause. Climacteric 2012, 15, 419–429. [Google Scholar] [CrossRef] [PubMed]
- Milewicz, A.; Tworowska, U.; Demissie, M. Menopausal obesity–myth or fact? Climacteric 2001, 4, 273–283. [Google Scholar] [PubMed]
- Kostoglou-Athanassiou, I.; Athanassiou, P. Metabolic syndrome and sleep apnea. Hippokratia 2008, 12, 81–86. [Google Scholar] [PubMed]
- Lam, J.C.; Mak, J.C.; Ip, M.S. Obesity, obstructive sleep apnea and metabolic syndrome. Respirology 2012, 17, 223–236. [Google Scholar] [CrossRef] [PubMed]
- Zhao, X.; An, X.; Yang, C.; Sun, W.; Ji, H.; Lian, F. The crucial role and mechanism of insulin resistance in metabolic disease. Front. Endocrinol. 2023, 14, 1149239. [Google Scholar] [CrossRef]
- Li, M.; Chi, X.; Wang, Y.; Setrerrahmane, S.; Xie, W.; Xu, H. Trends in insulin resistance: Insights into mechanisms and therapeutic strategy. Signal Transduct. Target. Ther. 2022, 7, 216. [Google Scholar] [CrossRef] [PubMed]
- Patel, S.R.; Hu, F.B. Short sleep duration and weight gain: A systematic review. Obesity 2008, 16, 643–653. [Google Scholar] [CrossRef] [PubMed]
- Leproult, R.; Van Cauter, E. Role of sleep and sleep loss in hormonal release and metabolism. Endocr. Dev. 2010, 17, 11–21. [Google Scholar]
- Cappuccio, F.P.; Miller, M.A. The epidemiology of sleep and cardiovascular risk and disease. In Sleep, Health and Society: From Aetiology to Public Health; Cappuccio, F.P., Miller, M.A., Lockley, S.W., Eds.; Oxford Academic: Oxford, UK, 2010. [Google Scholar]
- Cappuccio, F.P.; Miller, M.A.; Lockley, S.W.; Rajaratnam, S.M.W. Sleep, Health, and Society: From Aetiology to Public Health, 2nd ed.; Oxford University Press: Oxford, UK, 2018. [Google Scholar]
- Kerkadi, A.; Sadig, A.H.; Bawadi, H.; Al Thani, A.A.M.; Al Chetachi, W.; Akram, H.; Al-Hazzaa, H.M.; Musaiger, A.O. The Relationship between Lifestyle Factors and Obesity Indices among Adolescents in Qatar. Int. J. Environ. Res. Public Health 2019, 16, 4428. [Google Scholar] [CrossRef]
- Petrella, E.; Malavolti, M.; Bertarini, V.; Pignatti, L.; Neri, I.; Battistini, N.C.; Facchinett, F. Gestational weight gain in overweight and obese women enrolled in a healthy lifestyle and eating habits program. J. Matern.-Fetal Neonatal Med. 2014, 27, 1348–1352. [Google Scholar] [CrossRef]
- Rosi, A.; Giopp, F.; Milioli, G.; Melegari, G.; Goldoni, M.; Parrino, L.; Scazzina, F. Weight Status, Adherence to the Mediterranean Diet, Physical Activity Level, and Sleep Behavior of Italian Junior High School Adolescents. Nutrients 2020, 12, 478. [Google Scholar] [CrossRef] [PubMed]
- Cheng, X.; Lin, S.Y.; Liu, J.; Liu, S.; Zhang, J.; Nie, P.; Fuemmeler, B.F.; Wang, Y.; Xue, H. Does Physical Activity Predict Obesity-A Machine Learning and Statistical Method-Based Analysis. Int. J. Environ. Res. Public Health 2021, 18, 3966. [Google Scholar] [CrossRef] [PubMed]
- Williamson, D.F.; Madans, J.; Anda, R.F.; Kleinman, J.C.; Giovino, G.A.; Byers, T. Smoking cessation and severity of weight gain in a national cohort. N. Engl. J. Med. 1991, 324, 739–745. [Google Scholar]
- Pisinger, C.; Jorgensen, T. Weight concerns and smoking in a general population: The Inter99 study. Prev. Med. 2007, 44, 283–289. [Google Scholar] [CrossRef] [PubMed]
- Lycett, D.; Munafò, M.; Johnstone, E.; Murphy, M.; Aveyard, P. Associations between weight change over 8 years and baseline body mass index in a cohort of continuing and quitting smokers. Addiction 2011, 106, 188–196. [Google Scholar] [CrossRef] [PubMed]
- O’Hara, P.; Connett, J.E.; Lee, W.W.; Nides, M.; Murray, R.; Wise, R. Early and late weight gain following smoking cessation in the Lung Health Study. Am. J. Epidemiol. 1998, 148, 821–830. [Google Scholar] [PubMed]
- Kase, C.A.; Piers, A.D.; Schaumberg, K.; Forman, E.M.; Butryn, M.L. The relationship of alcohol use to weight loss in the context of behavioral weight loss treatment. Appetite 2016, 99, 105–111. [Google Scholar] [CrossRef] [PubMed]
- Tolstrup, J.S.; Heitmann, B.L.; Tjønneland, A.M.; Overvad, O.K.; Sørensen, T.I.; Grønbaek, M.N. The relation between drinking pattern and body mass index and waist and hip circumference. Int. J. Obes. 2005, 29, 490–497. [Google Scholar] [CrossRef]
- Arif, A.A.; Rohrer, J.E. Patterns of alcohol drinking and its association with obesity: Data from the Third National Health and Nutrition Examination Survey, 1988–1994. BMC Public Health 2005, 5, 126. [Google Scholar] [CrossRef]
- Wang, K.; Wu, C.; Yao, Y.; Zhang, S.; Xie, Y.; Shi, K.; Yuan, Z. Association between socio-economic factors and the risk of overweight and obesity among Chinese adults: A retrospective cross-sectional study from the China Health and Nutrition Survey. Glob. Health Res. Policy 2022, 7, 41. [Google Scholar] [CrossRef] [PubMed]
- Rummo, P.E.; Feldman, J.M.; Lopez, P.; Lee, D.; Thorpe, L.E.; Elbel, B. Impact of Changes in the Food, Built, and Socioeconomic Environment on BMI in US Counties, BRFSS 2003–2012. Obesity 2020, 28, 31–39. [Google Scholar] [CrossRef] [PubMed]
- Ohlsson, B.; Manjer, J. Sociodemographic and Lifestyle Factors in relation to Overweight Defined by BMI and “Normal-Weight Obesity”. J. Obes. 2020, 2020, 2070297. [Google Scholar] [CrossRef]
- Pou, S.A.; Diaz, M.D.P.; Velázquez, G.A.; Aballay, L.R. Sociodemographic disparities and contextual factors in obesity: Updated evidence from a National Survey of Risk Factors for Chronic Diseases. Public Health Nutr. 2022, 25, 3377–3389. [Google Scholar] [CrossRef] [PubMed]
- Van Domelen, D.R.; Koster, A.; Caserotti, P.; Brychta, R.J.; Chen, K.Y.; McClain, J.J.; Troiano, R.P.; Berrigan, D.; Harris, T.B. Employment and physical activity in the U.S. Am. J. Prev. Med. 2011, 4, 136–145. [Google Scholar] [CrossRef]
- Hosmer, D.W., Jr.; Lemeshow, S.; Sturdivant, R.X. Applied Logistic Regression, 3rd ed.; John Wiley & Sons: Hoboken, NJ, USA, 2013. [Google Scholar]
- Khalaf, M.; Hussain, A.J.; Keight, R.; Al-Jumeily, D.; Fergus, P.; Keenan, R.; Tso, P. Machine learning approaches to the application of disease modifying therapy for sickle cell using classification models. Neurocomputing 2017, 228, 154–164. [Google Scholar] [CrossRef]
Model | Accuracy | Std |
---|---|---|
Bagging | 0.72 | 0.10 |
Logistic Regression | 0.70 | 0.13 |
Gradient Boosting | 0.71 | 0.10 |
Extra Trees | 0.70 | 0.10 |
Random Forest | 0.69 | 0.08 |
Gaussian Nb | 0.67 | 0.12 |
Bernoulli Nb | 0.67 | 0.10 |
Decision Tree | 0.64 | 0.05 |
AdaBoost | 0.63 | 0.05 |
Metric Variables | Categories | Instance 38 (N = 295) | Instance 37a (N = 295) | Instance 37c (N = 295) |
---|---|---|---|---|
Correct classification rate | 0.81 | 0.79 | 0.80 | |
Subjects classified | 193 | 151 | 175 | |
Subjects unclassified | 102 | 144 | 120 | |
Variable number | 38 | 37 | 37 | |
Precision | Normal weight | 0.85 | 0.86 | 0.78 |
Overweight/obesity | 0.78 | 0.76 | 0.82 | |
Macro avg | 0.81 | 0.81 | 0.80 | |
Weighted avg | 0.81 | 0.81 | 0.80 | |
Recall | Normal weight | 0.75 | 0.68 | 0.79 |
Overweight/obesity | 0.87 | 0.90 | 0.81 | |
Macro avg | 0.81 | 0.79 | 0.80 | |
Weighted avg | 0.81 | 0.79 | 0.80 | |
F1-score | Normal weight | 0.79 | 0.76 | 0.79 |
Overweight/obesity | 0.82 | 0.82 | 0.81 | |
Macro avg | 0.81 | 0.79 | 0.80 | |
Weighted avg | 0.81 | 0.79 | 0.80 |
Algorithm | Instance | Accuracy | Precision | Recall | |||||
---|---|---|---|---|---|---|---|---|---|
Best | Worst | Mean | Std | Normal Weight | Overweight/Obesity | Normal Weight | Overweight/Obesity | ||
AdaBoost | 38 | 0.7119 | 0.5661 | 0.6297 | 0.0255 | 0.7312 | 0.6889 | 0.7358 | 0.6838 |
AdaBoost | 37a | 0.7017 | 0.5797 | 0.6448 | 0.0271 | 0.7386 | 0.6620 | 0.7019 | 0.7015 |
AdaBoost | 37c | 0.6915 | 0.5864 | 0.6406 | 0.0208 | 0.6795 | 0.7050 | 0.7211 | 0.6622 |
Bagging | 38 | 0.7695 | 0.6576 | 0.7091 | 0.0251 | 0.7925 | 0.7426 | 0.7826 | 0.7537 |
Bagging | 37a | 0.7356 | 0.6271 | 0.6921 | 0.0221 | 0.7635 | 0.7075 | 0.7244 | 0.7482 |
Bagging | 37c | 0.7627 | 0.6542 | 0.7141 | 0.0212 | 0.7484 | 0.7786 | 0.7891 | 0.7365 |
Bernoulli NB | 38 | 0.7390 | 0.5932 | 0.6718 | 0.0275 | 0.7386 | 0.7395 | 0.8075 | 0.6567 |
Bernoulli NB | 37a | 0.7356 | 0.6271 | 0.6745 | 0.0221 | 0.7222 | 0.7565 | 0.8228 | 0.6350 |
Bernoulli NB | 37c | 0.7763 | 0.6271 | 0.6760 | 0.0266 | 0.7596 | 0.8036 | 0.8634 | 0.6716 |
Decision Tree | 38 | 0.7492 | 0.6271 | 0.6907 | 0.0235 | 0.7322 | 0.7768 | 0.8428 | 0.6397 |
Decision Tree | 37a | 0.7661 | 0.6136 | 0.6823 | 0.0266 | 0.7486 | 0.7917 | 0.8397 | 0.6835 |
Decision Tree | 37c | 0.7458 | 0.6237 | 0.6882 | 0.0252 | 0.7485 | 0.7422 | 0.7911 | 0.6934 |
Extra Trees | 38 | 0.7695 | 0.6576 | 0.7094 | 0.0217 | 0.7484 | 0.7941 | 0.8095 | 0.7297 |
Extra Trees | 37a | 0.7593 | 0.6305 | 0.6889 | 0.0251 | 0.7831 | 0.7287 | 0.7879 | 0.7231 |
Extra Trees | 37c | 0.7627 | 0.6508 | 0.7101 | 0.0249 | 0.7419 | 0.7857 | 0.7931 | 0.7333 |
Gradient Boosting | 38 | 0.7763 | 0.6576 | 0.7256 | 0.0206 | 0.7701 | 0.7851 | 0.8375 | 0.7037 |
Gradient Boosting | 37a | 0.7559 | 0.6576 | 0.7094 | 0.0226 | 0.7803 | 0.7213 | 0.7988 | 0.6984 |
Gradient Boosting | 37c | 0.7864 | 0.6576 | 0.7284 | 0.0222 | 0.7747 | 0.8053 | 0.8650 | 0.6894 |
Gaussian NB | 38 | 0.7085 | 0.6102 | 0.6590 | 0.0221 | 0.6814 | 0.7971 | 0.9167 | 0.4331 |
Gaussian NB | 37a | 0.6949 | 0.6034 | 0.6517 | 0.0214 | 0.6524 | 0.8000 | 0.8896 | 0.4823 |
Gaussian NB | 37c | 0.7390 | 0.5932 | 0.6584 | 0.0235 | 0.7110 | 0.8182 | 0.9172 | 0.5000 |
Logistic Regression | 38 | 0.7898 | 0.6610 | 0.7115 | 0.0234 | 0.8042 | 0.7763 | 0.7718 | 0.8082 |
Logistic Regression | 37a | 0.7017 | 0.5831 | 0.6446 | 0.0241 | 0.6871 | 0.7162 | 0.7063 | 0.6974 |
Logistic Regression | 37c | 0.7729 | 0.6644 | 0.7144 | 0.0214 | 0.7425 | 0.8125 | 0.8378 | 0.7075 |
Random Forest | 38 | 0.7797 | 0.6814 | 0.7183 | 0.0190 | 0.7546 | 0.8106 | 0.8311 | 0.7279 |
Random Forest | 37a | 0.7458 | 0.6407 | 0.6999 | 0.0220 | 0.7284 | 0.7669 | 0.7919 | 0.6986 |
Random Forest | 37c | 0.7763 | 0.6644 | 0.7255 | 0.0236 | 0.7582 | 0.7958 | 0.8000 | 0.7533 |
Cascade Classifier | 38 | 0.8678 | 0.7320 | 0.7926 | 0.0283 | 0.8442 | 0.8866 | 0.8553 | 0.8776 |
Cascade Classifier | 37a | 0.8395 | 0.6875 | 0.7704 | 0.0330 | 0.8923 | 0.8041 | 0.7532 | 0.9176 |
Cascade Classifier | 37c | 0.8432 | 0.7287 | 0.7968 | 0.0234 | 0.8295 | 0.8557 | 0.8391 | 0.8469 |
Instance | AdaBoost | Bagging | Bernoulli NB | Decision Tree | Extra Trees | GB | Gaussian NB | LR | RF | Cascade |
---|---|---|---|---|---|---|---|---|---|---|
38 | 10 | 5.5 | 8 | 7 | 5.5 | 2 | 9 | 4 | 3 | 1 |
37a | 9.5 | 4 | 7 | 6 | 5 | 2 | 8 | 9.5 | 3 | 1 |
37c | 10 | 4.5 | 8 | 7 | 6 | 2 | 9 | 4.5 | 3 | 1 |
Average | 9.8 | 4.7 | 7.7 | 6.7 | 5.5 | 2 | 8.7 | 6 | 3 | 1 |
Std | 0.3 | 0.7 | 0.6 | 0.6 | 0.5 | 0 | 0.6 | 3.0 | 0 | 0 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Gutiérrez-Gallego, A.; Zamorano-León, J.J.; Parra-Rodríguez, D.; Zekri-Nechar, K.; Velasco, J.M.; Garnica, Ó.; Jiménez-García, R.; López-de-Andrés, A.; Cuadrado-Corrales, N.; Carabantes-Alarcón, D.; et al. Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults. J. Pers. Med. 2024, 14, 816. https://doi.org/10.3390/jpm14080816
Gutiérrez-Gallego A, Zamorano-León JJ, Parra-Rodríguez D, Zekri-Nechar K, Velasco JM, Garnica Ó, Jiménez-García R, López-de-Andrés A, Cuadrado-Corrales N, Carabantes-Alarcón D, et al. Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults. Journal of Personalized Medicine. 2024; 14(8):816. https://doi.org/10.3390/jpm14080816
Chicago/Turabian StyleGutiérrez-Gallego, Alberto, José Javier Zamorano-León, Daniel Parra-Rodríguez, Khaoula Zekri-Nechar, José Manuel Velasco, Óscar Garnica, Rodrigo Jiménez-García, Ana López-de-Andrés, Natividad Cuadrado-Corrales, David Carabantes-Alarcón, and et al. 2024. "Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults" Journal of Personalized Medicine 14, no. 8: 816. https://doi.org/10.3390/jpm14080816