Classification Tree Method for Determining Factors Associated with Halitosis

Year 2021, , 91 - 97, 01.05.2021

Mahmut Koparal , Utku Nezih Yılmaz , Ayşe Özcan Küçük , Aydın Keskinrüzgar , Fatih Üçkardeş

https://doi.org/10.19127/bshealthscience.845961

Cited By: 1

Abstract

Decision trees are data mining techniques for extracting hidden knowledge from large databases. This study was performed to establish the risk factors associated with halitosis by applying a decision tree model in a Turkish population and examining the interactions between these factors. We obtained data from a total of 1.290 patients, consisting of 645 patients with halitosis and 645 healthy controls. The subjects’ demographic characteristics, smoking status, alcohol intake, medical history and medications were assessed. The presence of potential intraoral causes of halitosis was determined by investigating perceived oral health problems such as caries, periodontal diseases, tongue coating, and oral cavity pathologies. Halitosis level was evaluated using an organoleptic scale. All data were subjected to classification tree analyses. Halitosis was significantly more common in patients with (80.9%) than without (20.7%) oral health problems (P < 0.001). Halitosis was significantly less common in non-smokers without oral health problems than in smokers with oral health problems (14.5%; P < .001). Halitosis was evident in all patients with oral health problems, smokers, and those with respiratory diseases (100%). The effects of systemic diseases on halitosis were significant in non-smokers without oral health problems (P < 0.05). Respiratory conditions showed significant effects on halitosis in smokers with oral health problems (P < 0.01). We developed a decision tree model to identify risk factors associated with halitosis. The classification tree method showed that the most significant factors affecting halitosis were oral health problems followed by smoking status.

Keywords

Halitosis, Bad breath, Classification tree method, Data mining, Decision tree, Causes

References

• Alizadehsani R, Habibi J, Hosseini MJ, Mashayekhi H, Boghrati R, Ghandeharioun A, Bahadorian B, Sani ZA. 2013. A data mining approach for diagnosis of coronary artery disease. Comput Methods Programs Biomed, 111(1): 52-61.
• AlSadhan SA. 2016. Self-perceived halitosis and related factors among adults residing in Riyadh, Saudi Arabia. A cross-sectional study. Saudi Dent J, 28(3):118-123.
• Amir E, Shimonov R, Rosenberg M. 1999. Halitosis in children. J Pediatr, 134: 338-343.
• Ansai T, Takehara T. 2005. Tonsillolith as a halitosis-inducing factor. Br Dent J, 198(5): 263-264.
• Arino M, Ito A, Fujiki S, Sugiyama S, Hayashi M. 2016. Multicenter study on caries risk assessment in adults using survival classification and regression trees. Sci Rep, 6: 29190.
• Barlin JN, Zhou Q, St Clair CM, Iasonos A, Soslow RA, Alektiar KM, Hensley ML, Jr. Leitao MM, Barakat RR, Abu-Rustum NR. 2013. Classification and regression tree (CART) analysis of endometrial carcinoma: Seeing the forest for the trees. Gynecol Oncol, 130: 452-456.
• Bollen CM, Beikler T. 2012. Halitosis: the multidisciplinary approach. Int J Oral Sci, 4(2): 55-63.
• Bornstein MM, Stocker BL, Seemann R, Bürgin WB, Lussi A. 2009. Prevalence of halitosis in young male adults: a study in Swiss army recruits comparing self-reported and clinical data. J Periodontol, 80(1): 24-31.
• Camdeviren HA, Yazici AC, Akkus Z, Bugdayci R, Sungur MA. 2007. Comparison of logistic regression model and classification tree: An application to postpartum depression data. Expert Sys App, 32: 987-994.
• Chang LY, Wang HW. 2006. Analysis of traffic injury severity: an application of non-parametric classification tree techniques. Acc Anly Prev, 38: 1019-1127.
• Chen X, Zhang Y, Lu HX, Feng XP. 2016. Factors associated with halitosis in white-collar employees in Shanghai, China. PLoS One, 11: e0155592.
• Christen AG.1992. The impact of tobacco use and cessation on oral and dental diseases and conditions. Am J Med, 93: 25-31.
• Codinach MM, Salas EJ. 2014 Halitosis: Diagnóstico y tratamiento. Av Odontoestomatol, 30: 155-160.
• Cortelli JR, Barbosa MD, Westphal MA. 2008. Halitosis: A review of associated factors and therapeutic approach. Braz Oral Res, 22: 44-54.
• D’Alisa S, Miscio G, Baudo S, Simone A, Tesio L, Mauro A. 2006. Depression is the main determinant of quality of life in multiple sclerosis: A classification regression (CART) study. Disabil Rehabil, 28: 307-314.
• Eldarrat AH. 2016. Influence of oral health and lifestyle on oral malodour. Int Dent J, 61(1): 47-51.
• Fonarow GC, Adams KFJr, Abraham WT, Yancy CW, Boscardin WJ. 2005. Risk stratification for in-hospital mortality in acutely decompensated heart failure: Classification and regression tree analysis. JAMA, 293: 572-580.
• Haumann TJ, Kneepkens CM. 2000. Halitosis in two children caused by a foreign body in the nose. Ned Tijdschr Geneeskd, 144: 1129-1130.
• Hebert M, Collin-Vezina D, Daigneault I, Parent N, Tremblay C. 2006. Factors linked to outcomes in sexually abused girls: a regression tree analysis. Comp Psych, 47: 443-455.
• Ito A, Hayashi M, Hamasaki T, Ebisu S. 2011. Risk assessment of dental caries by using Classification and Regression Trees. J Dent, 39: 457-463.
• Jiun IL, Siddik SN, Malik SN, Tin-Oo MM, Alam MK, Khan MM. 2015. Association between oral hygiene status and halitosis among smokers and nonsmokers. Oral Health Prev Dent, 13(5): 395-405.
• Kapoor U, Sharma G, Juneja M, Nagpal A. 2016. Halitosis: Current concepts on etiology, diagnosis and management. Eur J Dent, 10: 292-300.
• Kislig K, Wilder-Smith CH, Bornstein MM, Lussi A, Seemann R. 2013. Halitosis and tongue coating in patients with erosive gastroesophageal reflux disease versus nonerosive gastroesophageal reflux disease. Clin Oral Investig, 17: 159-165.
• Kurt I, Ture M, Kurum AT. 2008. Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease. Expert Syst Appl, 34(1): 366-374.
• Machuca C, Vettore MV, Krasuska M, Baker SR, Robinson PG. 2017. Using classification and regression tree modelling to investigate response shift patterns in dentine hypersensitivity. BMC Med Res Methodol, 17: 120-130.
• Madhushankari GS, Yamunadevi A, Selvamani M, Mohan Kumar KP, Basandi PS. 2015 Halitosis–An overview: Part-I–Classification, etiology, and pathophysiology of halitosis. J Pharm Bioallied Sci, 7: 339-343.
• Monfort-Codinach M, Chimenos-Küstner E, Alburquerque R, López-López J. 2014. Update of intra and extra oral causes of halitosis: a systematic review. OHDM, 13: 975-981.
• Moshkowitz M, Horowitz N, Leshno M, Halpern Z. (2007) Halitosis and gastroesophageal reflux disease: a possible association. Oral Dis, 13(6): 581-585.
• Murata T, Yamaga T, Iida T, Miyazaki H, Yaegaki K. 2002. Classification and examination of halitosis. Int Dent J, 52: 181-186.
• Nalcaci R, Baran I. 2008. Factors associated with self-reported halitosis (SRH) and perceived taste disturbance (PTD) in elderly. Arch Gerontol Geriatr, 46(3): 307-316.
• Nalçaci R, Dülgergil T, Oba AA, Gelgör IE. 2008. Prevalence of breath malodour in 7–11-year-old children living in Middle Anatolia, Turkey. Community Dent Health, 25(3): 173-177.
• Nazir MA, Almas K, Majeed MI. 2017. The prevalence of halitosis (oral malodour) and associated factors among dental students and interns Lahore. Pakistan Eur J Dent, 11(4): 480-485.
• Oyetola OE, Owotade FJ, Fatusi OA, Olatunji S. 2016. Pattern of presentation and outcome of routine dental interventions in patients with halitosis. Niger Postgrad Med J, 23(4): 215-220.
• Patel RB, Mathur MB, Gould M, Uyeki TM, Bhattacharya J, Xiao Y, Khazeni N. 2014. Demographic and clinical predictors of mortality from highly pathogenic avian influenza A (H5N1) virus infection: CART analysis of international cases. PLoS One, 25: 9:e91630.
• Porter SR, Scully C. 2006. Oral malodour (halitosis). BMJ, 333(7569): 632-635.
• Rio AC, Franchi-Teixeira, AR, Nicola EM. 2008. Relationship between the presence of tonsilloliths and halitosis in patients with chronic caseous tonsillitis. Br Dent J, 204(2): E4.
• Rosenberg M, Gelernter I, Barki M, Bar-Ness R. 1992. Day-long reduction of oral malodor by a two-phase oil: water mouthrinse as compared to chlorhexidine and placebo rinses. J Periodontol, 63(1): 39-43.
• Rosenfeld B, Lewis C. 2005. Assessing violence risk in stalking cases: A regression tree approach. Law Hum Behav, 29: 343-357.
• Rosenberg M, Knaan T, Cohen D. 2007. Association among bad breath, body mass index, and alcohol intake. J Dent Res, 86: 997-1000.
• Rösing CK, Loesche W. 2015. Halitosis: An overview of epidemiology, etiology and clinical management. Braz Oral Res, 25: 466-471.
• Sikorska-Żuk M, Bochnia M. 2018. Halitosis in children with adenoid hypertrophy. J Breath Res, 12(2): 026011.
• Schumacher MG, Zürcher A, Filippi A. 2017. Evaluation of a halitosis clinic over a period of eleven years. Swiss Dent J, 127(10): 846-851.
• Scully C, Greenman J. 2012. Halitology (breath odour: aetiopathogenesis and management). Oral Dis, 18(4): 333-345.
• Song YY, Lu Y. 2015. Decision tree methods: Applications for classification and prediction. Shanghai Arch Psychiatry, 27(2): 130-135.
• Söder B, Johansson B, Söder PO. 2000. The relation between foetor ex ore, oral hygiene and periodontal disease. Swed Dent J, 24(3): 73–82.
• Struch F, Schwahn C, Wallaschofski H, Grabe HJ, Völzke H, Lerch MM, Meisel P, Kocher T. 2008. Self-reported halitosis and gastro-esophageal reflux disease in the general population. J Gen Intern Med, 23(3): 260-266.
• Şanlı A, Bekmez E, Yıldız G, Erdoğan BA, Yılmaz HB, Altın G. 2016. Relationship between smoking and otorhinolaryngological symptoms. Kulak Burun Bogaz Ihtis Derg, 26(1): 28-33.
• Tas A, Köklü S, Yüksel I, Basar O, Akbal E, Cimbek A. 2011. No significant association between halitosis and upper gastrointestinal endoscopic findings: a prospective study. Chin Med J, 124: 3707-3710.
• Tayefi M, Esmaeili H, Saberi Karimian M, Amirabadi Zadeh A, Ebrahimi M, Safarian M, Nematy M, Parizadeh SMR, Ferns GA, Mobarhan MG. 2017a. The application of a decision tree to establish the parameters associated with hypertension. Comput Methods Programs Biomed,139: 83–91.
• Tayefi M, Tajfard M, Saffar S, Hanachi P, Amirabadizadeh AR, Esmaeily H, Taghipour A, Ferns GA, Moohebati M, Mobarhan MG. 2017b. hs-CRP is strongly associated with coronary heart disease (CHD): A data mining approach using decision tree algorithm. Comput Methods Programs Biomed, 141: 105-109.
• Van den Broek AM, Feenstra L, De Baat C. 2007. A review of the current literature on aetiology and measurement methods of halitosis. J Dent, 35: 627-635.
• Vayssières MP, Plant RE, Allen-Diaz BH. 2000. Classification trees: An alternative non-parametric approach for predicting species distributions. J Veg Sci, 11: 679-694.
• Yamauchi K, Ono Y, Baba K, Ikegami N. 2001. The actual process of rating the global assessment of functioning scale. Compr Psychiatry, 42: 403-409.
• Yokoyama S, Ohnuki M, Shinada K, Ueno M, Wright FA, Kawaguchi Y. 2010. Oral malodor and related factors in Japanese senior high school students, J Sch Health, 80(7): 346-352.
• Zimmerman RK, Balasubramani GK, Nowalk MP, Eng H, Urbanski L, Jackson ML, Jackson LA, McLean HQ, Belongia EA, Monto AS, Malosh RE, Gaglani M, Clipper L, Flannery B, Wisniewski SR. 2016. Classification and Regression Tree (CART) analysis to predict influenza in primary care patients. BMC Infect Dis, 16: 503-513.