DATA MINING METHODS FOR OBESITY LEVEL RECOGNITION: A SYSTEMATIC REVIEW OF THE LITERATURE

Volume: 7    Issue: 2

Year of Publication: 2020

Pages: (12-24)

Authors: Rafael Luckert, Kevin De Alba, Jaime Sarmiento, Karen Salas Viloria, Alexis De la Hoz Manotas, Fabio Mendoza Palechor

Download Full Text (PDF)

Abstract

Obesity in teenagers and adults has increased worldwide, with serious impact and consequences for health in the short and long term. Technology has allowed to discover new ways of treating diseases and problems with health issues, and data mining has become a relevant area of research and discovery, especially in recent years due to its precision and reliability analyzing datasets of patients to detect diseases and facilitate their prevention. The goal of this study was to identify the techniques and algorithms in data mining most commonly used, to detect several factors that favor the apparition of obesity issues and to determine the reliability of those methods, based on the results obtained from a data mining model. Data mining methods as simple regression and decision trees, are most commonly used to detect obesity levels, where the simple regression method was found in 19% of the articles reviewed and the decision trees method was used in 11% of them.

References

1. OMS. (2020, 1 de abril). Obesidad y sobrepeso (Notas descriptivas) [Online]. En: https://www.who.int/es/news-room/fact-sheets/detail/obesity-and-overweight

2. P. Werner, E. Meiss, L. Scheja, J. Heeren y M. Fischer, “Metabolite profiling: development and application of an UHR-QTOF-MS(/MS) method approach for the assessment of metabolic changes in high fat diet fed mice”, P. Werner, E. Meiss, L. Scheja, J. Heeren y M. Fischer, Metabolomics, Volume 13, Issue 4, 1 April 2017, Article number 44.

3. [M. Meller MD, PhD, N. Toossi MD, M. H. Gonzalez MD, PhD, M. Son PhD, E. C. Lau MS, N. Johanson MD, “Surgical Risks and Costs of Care are Greater in Patients Who AreSuperObese and Undergoing THA”, Clinical Orthopaedics and Related Research, Volume 474, Issue 11, 1 November 2016, Pages 2472-2481

4. R. L. Figueroa y C. A. Flores, “Extracting Information from Electronic Medical Records to Identify the Obesity Status of a Patient Based on Comorbidities and Bodyweight Measures”, Journal of Medical Systems, Volume 40, Issue 8, 1 August 2016, Article number 191.

5. Karayianni, KN a , Grimaldi, KA a , Nikita, KS a , Valavanis, IK b, International Journal of Bioinformatics Research and Applications, Volume 11, Issue 3, 2015, Pages 233-246, 2015

6. C. Kim, F. Costello, K. Lee, Y. Li and C. Li, \"Predicting Factors Affecting Adolescent Obesity Using General Bayesian Network and What-If Analysis\", International Journal of Environmental Research and Public Health, vol. 16, no. 23, p. 4684, 2019.

7. L. Vigna., A. Silvia, E. Grossi, S. Turolo, L. Tomaino, F. Napolitano, \"Directional Relationship Between Vitamin D Status and Prediabetes: A New Approach from Artificial Neural Network in a Cohort of Workers with Overweight-Obesity\", Journal of the American College of Nutrition, vol. 38, no. 8, pp. 681-692, 2019.

8. H. Jelinek, A. Stranieri, A. Yatsko and S. Venkatraman, \"Personalised measures of obesity using waist to height ratios from an Australian health screening program\", DIGITAL HEALTH, vol. 5, p. 205520761984436, 2019.

9. L. Wen, Y. Yu, H. Lv, Y. He and B. Yang, \"FTO mRNA expression in the lower quartile is associated with bad prognosis in clear cell renal cell carcinoma based on TCGA data mining\", Annals of Diagnostic Pathology, vol. 38, pp. 1-5, 2019.

10. [P. Shi and J. Goodson, \"A Data Mining Approach Identified Salivary Biomarkers That Discriminate between Two Obesity Measures\", Journal of Obesity, vol. 2019, pp. 1-7, 2019.

11. T. Assmann, F. Milagro and J. Martínez, \"Crosstalk between microRNAs, the putative target genes and the lncRNA network in metabolic diseases\", Molecular Medicine Reports, 2019.

12. C. Johnson, C. Drummer, A. Virtue, T. Gao, S. Wu, M. Hernandez, L. Singh, H. Wang, X. Yang, \"Increased Expression of Resistin in MicroRNA-155-Deficient White Adipose Tissues May Be a Possible Driver of Metabolically Healthy Obesity Transition to Classical Obesity\", Frontiers in Physiology, vol. 9, 2018.

13. V. Guan, Y. Probst, E. Neale, M. Batterham and L. Tapsell, \"Identifying usual food choices at meals in overweight and obese study volunteers: implications for dietary advice\", British Journal of Nutrition, vol. 120, no. 4, pp. 472-480, 2018.

14. S. Harous, M. El Menshawy, M. Serhani and A. Benharref, \"Mobile health architecture for obesity management using sensory and social data\", Informatics in Medicine Unlocked, vol. 10, pp. 27-44, 2018.

15. M. Tayefi, M. Saberi-Karimian, H. Esmaeili, A. Zadeh, M. Ebrahimi, M. Mohebati, A. Heidari-Bakavoli, M. Reza, M. Heshmati, M. Safarian, S. Reza, G. Ferns, M. Ghayour-Mobarhan, \"Evaluating of associated risk factors of metabolic syndrome by using decision tree\", Comparative Clinical Pathology, vol. 27, no. 1, pp. 215-223, 2017.

16. F. Cheng, X. Gao, L. Bao, D. Mitchell, C. Wood, M. Sliwinski, H. Smiciklas-Wright, C. Still, D. Rolston, G. Jensen, \"Obesity as a risk factor for developing functional limitation among older adults: A conditional inference tree analysis\", Obesity, vol. 25, no. 7, pp. 1263-1269, 2017.

17. Q. Nguyen, H. Meng, S. Kath, M. McCullough, D. Paul, P. Kanokvimankul, T. Nguyen, F. Li, \"Social media indicators of the food environment and state health outcomes\", Public Health, vol. 148, pp. 120-128, 2017.

18. L. Al-Khudairy, E. Loveman, J. Colquitt, E. Mead, R. Johnson, H. Fraser, J. Olajide, M. Murphy, R. Marian, C. O’Malley, L. Azevedo, L. Ells, M. Metzendorf, K. Ress, \"Diet, physical activity and behavioural interventions for the treatment of overweight or obese adolescents aged 12 to 17 years\", Cochrane Database of Systematic Reviews, 2017.

19. A. R. Olivera, V. Roesler, C. Iochpe, M. I. Schmidt, Á. Vigo, S. M. Barreto, “Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes – ELSA-Brasil: accuracy study”, Sao Paulo Medical Journal, Volumen 135, Número 3, mayo-junio de 2017, páginas 234-246. 

20. C. Ferrajolo, K. M. C. Verhamme, G. Trifiro, G. W. ‘t Jong. G. Picelli, C. Giaquinto, G. Mazzaglia, B. H. Stricker, F. Rossi. A. Capuano y M. C. J. M. Sturkenboom. “Antibiotic-Induced Liver Injury in Paediatric Outpatients: A Case-Control Study in Primary Care Databases”, Drug Safety, Volume 40, Issue 4, 1 April 2017, Pages 305-315. 

21. P. Werner, E. Meiss, L. Scheja, J. Heeren y M. Fischer, “Metabolite profiling: development and application of an UHR-QTOF-MS(/MS) method approach for the assessment of metabolic changes in high fat diet fed mice”, Metabolomics, Volume 13, Issue 4, 1 April 2017, Article number 44. 

22. D. Gu, J. Li, X. Li, C. Liang, “Visualizing the knowledge structure and evolution of big data research in healthcare informatics”, International Journal of Medical Informatics, Volume 98, 1 February 2017, Pages 22-32. 

23. M. Meller MD, PhD, N. Toossi MD, M. H. Gonzalez MD, PhD, M. Son PhD, E. C. Lau MS, N. Johanson MD, “Surgical Risks and Costs of Care are Greater in Patients Who Are Super Obese and Undergoing THA”, Clinical Orthopaedics and Related Research, Volume 474, Issue 11, 1 November 2016, Pages 2472-2481 

24. R. L. Figueroa y C. A. Flores, “Extracting Information from Electronic Medical Records to Identify the Obesity Status of a Patient Based on Comorbidities and Bodyweight Measures”, Journal of Medical Systems, Volume 40, Issue 8, 1 August 2016, Article number 191. 

25. N. Fujimura, J. Xiong, PhD, E. B. Kettler, H. Xuan, K. J. Glover, M. W. Mell, B. Xu, and R. L. Dalman, “Metformin treatment status and abdominal aortic aneurysm disease progression”, Journal of Vascular Surgery, Volume 64, Issue 1, 1 July 2016, Pages 46-54.e8. 

26. P. A. Patel, C. G. Scott, R. J. Rodeheffer and H. Chen, “The Natural History of Patients with Isolated Metabolic Syndrome”, Mayo Clinic Proceedings, Volume 91, Issue 5, 1 May 2016, Pages 623-633. 

27. A. Khan, N. Choudhury, S. Uddin, L. Hossain, and L. A Baur, “Longitudinal trends in global obesity research and collaboration: a review using bibliometric metadata”, Obesity Reviews, Volume 17, Issue 4, 1 April 2016, Pages 377-385. 

28. É.O. Rodrigues, F.F.C. Morais, N.A.O.S. Morais, L.S. Conci, L.V. Neto y A. Conci, “A novel approach for the automated segmentation and volume quantification of cardiac fats on computed tomography”, Computer Methods and Programs in Biomedicine, Volume 123, 1 January 2016, Pages 109-128. 

29. G. Karystianis, A. Dehghan, A. Kovacevic, J. A. Keane, and G. Nenadic, “Using local lexicalized rules to identify heart disease risk factors in clinical notes,” J. Biomed. Inform., vol. 58, pp. S183–S188, 2015, doi: 10.1016/j.jbi.2015.06.013.

30. H. Yang and J. M. Garibaldi, “A hybrid model for automatic identification of risk factors for heart disease,” J. Biomed. Inform., vol. 58, pp. S171–S182, 2015, doi: 10.1016/j.jbi.2015.09.006.

31. C. Shivade, P. Malewadkar, E. Fosler-Lussier, and A. M. Lai, “Comparison of UMLS terminologies to identify risk of heart disease using clinical notes,” J. Biomed. Inform., vol. 58, pp. S103–S110, 2015, doi: 10.1016/j.jbi.2015.08.025.

32. A. Stubbs, Ö. Uzuner, “Annotating risk factors for heart disease in clinical narratives for diabetic patients,” J. Biomed. Inform., vol. 58, pp. S78–S91, Dec. 2015, doi: 10.1016/j.jbi.2015.05.009.

33. M. Torii, J. Fan, T. Lee, T. Wiley, D. Zisook, Y. Huang, “Risk factor detection for heart disease by applying text analytics in electronic medical records,” J. Biomed. Inform., vol. 58, pp. S164–S170, 2015, doi: 10.1016/j.jbi.2015.08.011.

34. K. Jung, P. LePendu, S. Iyer, A. Bauer-Mehren, B. Percha, and N. H. Shah, “Functional evaluation of out-of-the-box text-mining tools for data-mining tasks,” J. Am. Med. Informatics Assoc., vol. 22, no. 1, pp. 121–131, 2015, doi: 10.1136/amiajnl-2014-002902.

35. T. Kobayashi, T. Osaki, and S. Oikawa, “Use of T-RFLP and seven restriction enzymes to compare the faecal microbiota of obese and lean Japanese healthy men,” Benef. Microbes, vol. 6, no. 5, pp. 735–745, 2015, doi: 10.3920/BM2014.0147.

36. S. N. Partington, T. J. Menzies, T. A. Colburn, B. E. Saelens, and K. Glanz, “Reduced-item food audits based on the nutrition environment measures surveys,” Am. J. Prev. Med., vol. 49, no. 4, pp. e23–e33, 2015, doi: 10.1016/j.amepre.2015.04.036.

37. K. N. Karayianni, K. A. Grimaldi, K. S. Nikita, and I. K. Valavanis, “Mining nutrigenetics patterns related to obesity: Use of parallel multifactor dimensionality reduction,” Int. J. Bioinform. Res. Appl., vol. 11, no. 3, pp. 233–246, 2015, doi: 10.1504/IJBRA.2015.069194.

38. A. Ramezankhani, O. Pournik, J. Shahrabi, F. Azizi, and F. Hadaegh, “An application of association rule mining to extract risk pattern for type 2 diabetes using tehran lipid and glucose study database,” Int. J. Endocrinol. Metab., vol. 13, no. 2, 2015, doi: 10.5812/ijem.25389.

39. H. Straub, M. Adams, and R. K. Silver, “Can an electronic health record system be used for preconception health optimization?,” Matern. Child Health J., vol. 18, no. 9, pp. 2134–2140, 2014, doi: 10.1007/s10995-014-1461-8.

40. R. Charlton, M. Gravenor, A. Rees, G. Knox, R. Hill, M. Rahman, K. Jones, D. Christian, J. Baker, G. Straton, S. Brophy, “Factors associated with low fitness in adolescents - A mixed methods study,” BMC Public Health, vol. 14, no. 1, 2014, doi: 10.1186/1471-2458-14-764.

41. J. Zhou, X. Zhang, H. Zhang, Y. Jia, Y. Liu, Y. Tuang, X. Li, “Use of data mining to determine changes in the gene expression profiles of rat embryos following prenatal exposure to inflammatory stimulants,” Mol. Med. Rep., vol. 8, no. 1, pp. 95–102, 2013, doi: 10.3892/mmr.2013.1498.

42. A. H. Youssefagha, D. K. Lohrmann, and W. P. Jayawardene, “Use of Data Mining to Reveal Body Mass Index (BMI): Patterns Among Pennsylvania Schoolchildren, Pre-K to Grade 12,” J. Sch. Health, vol. 83, no. 2, pp. 85–92, 2013, doi: 10.1111/josh.12002.

43. Palechor, F. M., & de la Hoz Manotas, A. (2019). Dataset for estimation of obesity levels based on eating habits and physical condition in individuals from Colombia, Peru and Mexico. Data in brief, 25, 104344.

Keywords

obesity, data mining, overweight.