An Oversampling Technique for Handling Imbalanced Data in Patients with Metabolic Syndrome and Periodontitis

Sema Merve Altıngöz; Batuhan Bakırarar; Elif Ünsal; Sivge Kurgan; Meral Günhan

doi:10.7126/cumudj.1332452

EN

An Oversampling Technique for Handling Imbalanced Data in Patients with Metabolic Syndrome and Periodontitis

Abstract

Objectives: Periodontitis has been suggested to be associated with several systemic diseases and conditions including obesity, metabolic syndrome, diabetes, chronic renal disease, respiratory disorders, and cardiovascular diseases. Metabolic syndrome (MetS) is a collection of impairment and is a risk factor for type 2 diabetes and cardiovascular disease. Our study is aimed to handle MetS unbalanced data using the synthetic minority over-sampling technique (SMOTE) to increase accuracy and reliability. Materials and Methods: Six metabolic syndrome patients and 26 systemically healthy subjects with periodontitis were recruited in this study. Clinical parameters (Plaque index (PI), gingival index (GI), probing pocket depth (PPD), clinical attachment loss (CAL), and bleeding on probing (BOP)) were obtained, smoking status and body-mass index (BMI), systemic diseases, fasting glucose levels, hemoglobin A1c (HbA1c) levels and serum advanced glycation end-products (AGE) levels were recorded by one examiner. First, the data was pre-processed by removing missing values, outliers and normalizing the data. Then, SMOTE technique was used to oversample the minority class. SMOTE works by creating synthetic data points that are similar to the existing minority class instances. The experimental dataset included numerous machine learning algorithms and assessed accuracy using both pre- and post-oversampling methods. Results: Our findings suggest that by increasing the sample size of a study, researchers can gain more accurate and reliable results. This is especially important when studying a population with a lower sample size, as the results may be skewed. Conclusion: SMOTE may result in over fitting on numerous copies of minority class samples.

Keywords

References

1. Pihlstrom BL, Michalowicz BS, Johnson NW. Periodontal diseases. Lancet 2005, 366, 1809–1820.
2. Slade GD, Offenbacher S, Beck JD, et al. Acute-phase inflammatory response to periodontal disease in the US population. J Dent Res. 2000;79:49-57.
3. Saito T, Shimazaki Y, Kiyohara Y, et al. The severity of periodontal disease is associated with the development of glucose intolerance in non-diabetics: The Hisayama study. J Dent Res. 2004;83:485-490.
4. Taylor BA, Tofler GH, Carey HM, et al. Full-mouth tooth extraction lowers systemic inflammatory and thrombotic markers of cardiovascular risk. J Dent Res. 2006;85:74-78.
5. Higashi Y, Goto C, Jitsuiki D, et al. Periodontal infection is associated with endothelial dysfunction in healthy subjects and hypertensive patients. Hypertension. 2008;51:446-453.
6. Tonetti MS, D’Aiuto F, Nibali L, et al. Treatment of periodontitis and endothelial function. N Engl J Med. 2007;356:911-920.
7. Katz J, Flugelman MY, Goldberg A, et al. Association between periodontal pockets and elevated cholesterol and low density lipoprotein cholesterol levels. J Periodontol. 2002;73:494 500.
8. Losche W, Karapetow F, Pohl A, et al. Plasma lipid and blood glucose levels in patients with destructive periodontal disease. J Clin Periodontol. 2000;27:537-541.

9. International Diabetes Federation. The IDF Consensus Definition of the Metabolic Syndrome in Children and Adolescents, 2007.
10. Ford ES, Giles WH, Mokdad AH. Increasing prevalence of the metabolic syndrome among U.S. adults. Diabetes Care 2004, 27, 2444–2449.
11. Makkar H, Reynolds MA, Wadhawan A, Dagdag A, Merchant AT, Postolache TT. Periodontal, metabolic, and cardiovascular disease: exploring the role of inflammation and mental health. Pteridines.2018;29:124-163.
12. Grundy SM, Cleeman JI, Daniels SR, et al. Diagnosis and management of the metabolic syndrome: An American Heart Association/National Heart, Lung, and Blood Institute scientific statement. Cardiol Rev. 2005;13:322-327.
13. Nibali L, D’Aiuto F, Griffiths G, Patel K, Suvan J, Tonetti MS. Severe periodontitis is associated with systemic inflammation and a dysmetabolic status: a case-control study. J Clin Periodontol.2007;34:931-937.
14. Menardi G, Torelli N. Training and assessing classification rules with imbalanced data. Data Min. Knowl. Disc. 28(1), 92–122 (2014).
15. Fernndez A, Garca S, del Jesus MJ, Herrera F. A study of the behaviour of linguistic fuzzy rule based classification systems in the framework of imbalanced data-sets, Fuzzy Sets and Systems, 159(18), 23782398, 2008.
16. Tonetti MS, Greenwell H, Kornman KS. Staging and grading of periodontitis: framework and proposal of a new classification and case definition. J Periodontol. 2018; 89(Suppl 1): 159-172.
17. Silness J, Loe H. Periodontal disease in pregnancy. II. Correlation between oral hygiene and periodontal condition. Acta Odontol Scand. 1964;22:121–135.
18. Loe H, Silness J. Periodontal disease in pregnancy. I. Prevalence and Severity. Acta Odontol Scand. 1963;21:533–551.
19. Caglayan F, Miloglu O, Altun O, et al. Oxidative stress and myeloperoxidase levels in saliva of patients with reccurrent aphthous stomatitis. Oral Dis. 2008;12:700–704.
20. Tayman MA, Kurgan Ş, Önder C, Güney Z, Serdar MA, Kantarcı A, Günhan M (2019) Affiliations expandA disintegrin-like and metalloproteinase with thrombospondin-1 (ADAMTS-1) levels in gingival crevicular fluid correlate with vascular endothelial growth factor-A, hypoxia-inducible factor-1α, and clinical parameters in patients with advanced periodontitis. J Periodontol 90(10):1182–1189.
21. El-Sayed AA, Mahmood MAM, Meguid NA, Hefny HA. Handling autism imbalanced data using synthetic minority over-sampling technique (SMOTE), 2015 Third World Conference on Complex Systems (WCCS), Marrakech, 2015, pp. 1-5.
22. Shin D, Lee KJ, Adeluwa T, Hur J. Machine Learning-Based Predictive Modeling of Postpartum Depression. Journal of clinical medicine, 2020. 9(9), 2899.
23. Ramezankhani A, Pournik O, Shahrabi J, Azizi F, Hadaegh F, Khalili D. The Impact of Oversampling with SMOTE on the Performance of 3 Classifiers in Prediction of Type 2 Diabetes. Medical decision making:an international journal of the Society for Medical Decision Making, 2016, 36(1), 137–144.
24. Fotouhi S, Asadi S, Kattan MW. A comprehensive data level analysis for cancer diagnosis on imbalanced data. Journal of biomedical informatics, 2019, 90, 103089.
25. Nguyen BP, Pham HN, Tran H, Nghiem N, Nguyen QH, Do T T T, et al. Predicting the onset of type 2 diabetes using wide and deep learning with electronic health records. Computer methods and programs in biomedicine, 2019, 182, 105055.
26. Cui S, Luo Y, Tseng HH, Ten Haken RK, El Naqa I. Combining handcrafted features with latent variables in machine learning for prediction of radiation-induced lung damage. Medical physics, 2019, 46(5), 2497–2511.

Details

Primary Language

English

Subjects

Dentistry (Other)

Journal Section

Research Article

Authors

Sema Merve Altıngöz ^*
0000-0002-9709-6226
Türkiye

Batuhan Bakırarar
0000-0002-5662-8193
Türkiye

Elif Ünsal
0000-0002-7843-6088
Türkiye

Sivge Kurgan
0000-0002-7868-4217
Türkiye

Meral Günhan
0000-0002-3848-6195
Türkiye

Publication Date

December 31, 2023

Submission Date

July 25, 2023

Acceptance Date

November 29, 2023

Published in Issue

Year 2023 Volume: 26 Number: 4

DOI

https://doi.org/10.7126/cumudj.1332452

IZ

https://izlik.org/JA89WW63KY

Cite

RIS / Bibtex

EndNote

Altıngöz SM, Bakırarar B, Ünsal E, Kurgan S, Günhan M (December 1, 2023) An Oversampling Technique for Handling Imbalanced Data in Patients with Metabolic Syndrome and Periodontitis. Cumhuriyet Dental Journal 26 4 374–380.

Öz

An Oversampling Technique for Handling Imbalanced Data in Patients with Metabolic Syndrome and Periodontitis

Abstract

Keywords

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite