Skip to main content
Download PDF

Predicting dental anxiety in young adults: classical statistical modelling approach versus machine learning approach

BMC Oral Health volume 24, Article number: 313 (2024) Cite this article

Abstract

Objectives

To predict and identify the key demographic and clinical exposure factors associated with dental anxiety among young adults, and to compare if the traditional statistical modelling approach provides similar results to the machine learning (ML) approach in predicting factors for dental anxiety.

Methods

A cross-sectional study of Western Illinois University students. Three survey instruments (sociodemographic questionnaire, modified dental anxiety scale (MDAS), and dental concerns assessment tool (DCA)) were distributed via email to the students using survey monkey. The dependent variable was the mean MDAS scores, while the independent variables were the sociodemographic and dental concern assessment variables. Multivariable analysis was done by comparing the classical statistical model and the machine learning model. The classical statistical modelling technique was conducted using the multiple linear regression analysis and the final model was selected based on Akaike information Criteria (AIC) using the backward stepwise technique while the machine learining modelling was performed by comparing two ML models: LASSO regression and extreme gradient boosting machine (XGBOOST) under 5-fold cross-validation using the resampling technique. All statistical analyses were performed using R version 4.1.3.

Results

The mean MDAS was 13.73 ± 5.51. After careful consideration of all possible fitted models and their interaction terms the classical statistical approach yielded a parsimonious model with 13 predictor variables with Akaike Information Criteria (AIC) of 2376.4. For the ML approach, the Lasso regression model was the best-performing model with a mean RMSE of 0.617, R2 of 0.615, and MAE of 0.483. Comparing the variable selection of ML versus the classical statistical model, both model types identified 12 similar variables (out of 13) as the most important predictors of dental anxiety in this study population.

Conclusion

There is a high burden of dental anxiety within this study population. This study contributes to reducing the knowledge gap about the impact of clinical exposure variables on dental anxiety and the role of machine learningin the prediction of dental anxiety. The predictor variables identified can be used to inform public health interventions that are geared towards eliminating the individual clinical exposure triggers of dental anxiety are recommended.

Peer Review reports

Introduction

Dental fear or anxiety (DA) can be described as a subjective negative reaction to dental treatment resulting from a learned negative behavior and often attributed to the aggressive conditioning process which occurred during childhood [1]. Fear of pain has been found to be the main cause of anxiety and a major barrier to seeking dental care [2, 3]. Dental avoidance has been linked with dental fear and anxiety in many patients and thus has led to the deterioration of their oral health state [4, 5]. In severe cases of dental anxiety, the dentist-patient relation may be hampered and sometimes lead to misdiagnoses of anxiety for pain which might result in wrong treatment administration [4, 6]. The standardized and validated tool for the measurement of dental anxiety is known as the Modified Dental Anxiety Scale (MDAS) [7].

Globally, several reports have shown the prevalence of dental anxiety to be between 2.5 and 20% depending on population and methods of assessment [8,9,10]. Studies have also reported dental anxiety to occur more in females than males [7, 11]. Recent studies have shown that 51% of subjects reported dental anxiety onset in childhood, 22% in adolescence, and 27% in adulthood [8, 12]. Studies have shown gender and age differences in the prevalence of dental anxiety but more importantly, the socioeconomic differences which bother mostly on fear of treatment cost [7, 11, 13].

There are limited studies on the burden of dental anxiety among university students in the US, which constitute a reasonable population of adolescents and young adults in the country [14]. Also, very few studies have explored the clinical exposure variables that may be associated with dental anxiety among young adults [15]. A study of Washington University students showed that about one out of five students reported high levels of dental anxiety (mean DAS = 9.2; SD = 3.4) and most of the students reported that their dental anxiety was due to dental injection [16]. Previous studies in the U.S. have focused on dental anxiety among American children and older adults with only a few studies on young adults or adolescents [14, 15]. Thus, there is a need for more studies among young adults to understand the clinical exposure variables contributing to dental anxiety.

Supervised machine learning (ML) is a subset of artificial intelligence used in the prediction of outcome measures based on several input measures. The goal of the ML model is to optimize the bias-variance trade-off and prevent model underfitting or overfitting [17]. Machine Learningprovides a robust approach for the identification and selection of the most important predictors, without running into issues of numerical convergence and the “curse of dimensionality” a phenomenon common in classical statistical modeling with a lot of predictor variables. Most importantly, there is a dearth of literature comparing classical statistical modeling and ML model in predicting oral health outcomes and more specifically dental anxiety.

The objectives of this study were to predict and identify the key demographic and clinical exposure factors associated with dental anxiety among young adults, and to compare if the traditional statistical modelling approach provides similar results to the machine learning (ML) approach in predicting factors for dental anxiety.

Methods

This is a cross-sectional study of university students recruited from Western Illinois University (WIU). Eligible participants were graduate and undergraduate students registered for the 2017 Spring semester at WIU at both campuses (Macomb and the Quad Cities campuses). Using the pwr package [18] in R for generalized linear regression, we estimated the sample size of 1062 students based on the following assumptions – small effect size of 2%, 21 variables, and 80% power, and 95% confidence level.

Data collection

After obtaining approval from the IRB, we obtained the list of emails of the students registered for the Spring semester of 2017 and emailed the survey instruments to the participants electronically via Survey Monkey. The survey instrument consisted of a self-administered structured questionnaire, a validated modified dental anxiety scale (MDAS) [7], and a Dental Concern/Fear Assessment tool (DCA) [19]. The inclusion criteria were all students (undergraduate, graduate, and doctoral) registered for the spring 2017 semester. The e-mails were sent two times, the first one in March and the second one in April 2017. The termination date for the survey return was set at two weeks after the first survey was sent. The survey emails were sent in the evening, assuming that students would be more relaxed in the evenings and have more time to complete the survey. Informed consent was obtained from all subjects and their legal guardian(s) before responding to the questionnaires.

The dependent variable was the mean MDAS scores. The independent variables (see Appendix I for details) include age group, sex, socioeconomic status, dental visit, frequency of dental visit, level of education, and the dental concern variables (Sound or vibration of the drill, dislike of the numb feeling, injection in the mouth, sound or feel of scraping during teeth cleaning, cold air on the teeth, root canal treatment, tooth removal, fear of being injured, panic attacks, fear of feeling pain during treatment, the concern of being embarrassed, smells in the dental office, worried about need a lot of dental treatment, cost of the dental treatment). Studies have identified the cognitive conditioning pathway as a framework elucidating the aetiology of dental anxiety. Within this framework, individuals with negative experiences during dental visits may establish a conditioned association linking the dentist with anxiety [20, 21]. The DCA tool was modified and adapted for our study to consist of 15 short dental anxiety-specific questions with three rank-order response options and was used to measure dental anxiety concerning individual triggers or aggravating factors from dental procedures. Before the primary data collection, a pilot study was conducted using a randomly selected thirty (30) participants to check the response rate, acceptability and the validity of the assessment tools that were utilized for the study.

Statistical analysis

Only participants who have complete data for all the variables were included in the final analysis. No imputation of data was done. The univariate analyses were conducted for both the dependent and independent variables. The one-way ANOVA test was used to assess the bivariate relationship between each categorical independent variable and the continuous dependent variable (MDAS score). Only the statistically significant variables (p < 0.05) were included in the final model for both the classical statistical approach and the ML approach.

Multivariable analysis was done to ascertain the relationship between the independent variables and the MDAS score and identify the predictors of dental anxiety by comparing the results from two modelling approaches: The classical statistical approach and the machine learning approach. The classical statistical modelling technique was conducted using the multiple linear regression analysis and the final model was selected based on Akaike information Criteria (AIC) using the backward stepwise technique. The root mean square error (RMSE), and coefficient of determination (R2) for the classical statistical modelling approach was calculated. For comparison, the machine learning technique was performed by comparing two ML models: LASSO regression [22] and extreme gradient boosting machine (XGBOOST) [23] under 5-fold cross-validation using the resampling technique. The data pre-processing (Standardization and normalization) for the machine learning model was done using the recipes package [24]. The model performance was based on RMSE, R2, and mean absolute error (MAE). The RMSE value was the main metric for performance assessment and comparison of both model types. The RMSE value indicates measures difference between the predicted values and the observed values. Therefore, the lower the RMSE, the better the model performance. All statistical analyses were performed using R version 4.1.3.

Results

A total of 454 students (45% response rate) completed the dental anxiety questionnaire (i.e. completely answered at least the Sociodemographic and MDAS sections of the questionnaire) by the end of the survey period and thus were included in the study. No data were inputted. The pilot study of 30 students showed a response rate of 100%. All the 30 participants accepted the questionnaires and had no worries or questions about the content of measurement tools. Thus, the questionnaires were validated for the measurement of dental anxiety within this population and their responses were included in the study.

As shown in Table 1, about two-thirds of the participants were female (69.40%). Most of the respondents were within the age range of 15 to 24 (68.10%). Most of the respondents (98.20%) have visited a dentist. About 35.20% of the respondents had not visited the dentist in the last 12 months. More than half of the respondents reported a household income of $74,999 or less.

Table 1 Descriptive statistics of the dental anxiety scores, demographic and dental concern assessment variables
Full size table

Table 1 also showed the different levels of dental concerns/fear about various triggers of dental anxiety among the study participants. The study participants had a fairly equal level of dental concern/fear about the sound or vibration of the drill. Up to 57% expressed a low level of concern about the numb feeling from dental treatment while 45.2% said they have a high level of concern about injection in the mouth. About 41% and 44% had a low concern about the sound or feel of scraping during teeth cleaning and cold air in the mouth respectively. The study participants had high levels of concerns (67%) for both root canal treatment and extractions. About 62% had high dental concerns for panic attacks during treatment.

The mean MDAS was 13.73 ± 5.51 (Table 1). The prevalence of dental anxiety among the respondents was 63.90%. The prevalence of extreme anxiety was 19.50% while high anxiety and moderate anxieties were 21.50% and 22.90% respectively (See details in Table 1 on how the MDAS scores were categorized). As shown in Table 2, all predictor variables were statistically significant (p < 0.001) except age, dental visit, and education (see Table 2 for details).

Table 2 One-way ANOVA: independent variables versus mean MDAS score
Full size table

Multivariable analyses

Classical statistical model (multiple Linear regression)

As shown in Table 3, after careful consideration of all possible fitted models and their interaction terms for multiple linear regression analysis, the parsimonious model had 9 variables with Akaike Information Criteria (AIC) of 2376.4. The RMSE and R2 were 3.16 and 0.67, respectively.

Table 3 Summary output of the final (reduced) model from generalized linear model (Arranged in the order of variable importance based on the magnitude of their beta coefficient)
Full size table

Holding all other variables in the model constant, high and moderate fear of panic attacks during treatment were significantly associated with higher mean DA compared to low fear of panic attacks (β = 3.14, p < 0.01; β = 1.28, p < 0.01, respectively). High fear of feeling pain during treatment was associated with a higher mean DA compared to low fear (β = 2.70, p < 0.01). High and moderate fear of the sound or vibration of drills was associated with a higher mean DA score compared to having low fear (β = 2.70, p < 0.01; β = 0.98, p = 0.02, respectively). High and moderate fear of root canal treatment was associated with higher mean DA compared to low fear of root canal treatment (β = 2.69, p < 0.01; β = 1.62, p = 0.01). High fear of injection was associated with higher mean DA compared to low fear of injection (β = 1.91, p < 0.01). High fear of needing a lot of dental treatment was significantly associated with higher mean DA compared to low fear (β = 1.60, p < 0.01). High fear of being embarrassed was significantly associated with higher mean DA compared to low fear of being embarrassed (β = 1.52, p = 0.01). The frequency of dental visits of less than 3 months and 3 months to less than 6 months were associated with a lower mean DA score compared to dental visit frequency of 12 months and above (β = -0.94, p = 0.02; β = -1.17, p = 0.01). Moderate fear of the sound or feel of scraping during teeth cleaning was associated with a higher mean DA compared to low fear (β = 0.82, p = 0.04).

Machine learning model

After a comparison of the Lasso regression and XGBOOST model, the Lasso regression model was found to be the best-performing model with a mean RMSE of 0.617, R2 of 0.615, and MAE of 0.483 (Table 4). The details of the performance of the XGBOOST model can be found in Appendix VII. The calibration plot of the Lasso regression model showed a close calibration between the observed and the predicted means (Appendix III). The variable importance assessment found identified 28 predictors of dental anxiety in this population and these variables were ranked based on their permuted mean RMSE score (Table 5).

Table 4 Showing the performance of the LASSO regression model
Full size table
Table 5 Showing variable importance based on permitted mean RMSE.
Full size table

Comparing variable importance of ML versus classical statistical model

As shown in Table 3, the classical statistical model had only 13 statistically significant variables and as such we selected the top 13 predictors of DA from the ML model variable importance estimation for comparison (Table 5). As shown in Table 6, both model types identified 12 similar variables (out of 13) as the most important predictors of dental anxiety in this study population. The ranking of the variable importance across the different model types varied however the top 5 predictors of DA were high fear of pain, panic attack, sound or vibration of drill, root canal, and injection in the mouth. The RMSE and R2 of the classical statistical model were 3.16 and 0.67, respectively versus the RMSE and R2 of the ML model which were 0.617 and 0.615, respectively (Table 6).

Table 6 Comparison of the 10 most important predictors of DA identified using ML model versus classical statistical model
Full size table

Discussion

Dental anxiety is a huge concern for dental professionals, public health specialists, and patients because of its association with poor oral health outcomes. Recent studies have shown a surge in the prevalence of dental anxiety [25, 26]. However, there are very few recent studies on young adults, especially in the United States of America [27, 28]. There are no existing studies that compared classical statistical models versus machine learning models in predicting and identifying the predictors of dental anxiety.

The high mean MDAS score found in this study is higher than the average MDAS score of 12.34 found in the Saatchi et al. study [29]. Comparable studies in the U.S. by Locker and Liddle (mean DAS = 7.8) and Kaako et al. study among university students (mean DAS = 9.2) have also shown lower scores even though they used DAS for measurement [13, 16]. It is crucial to highlight that the DAS (Corah’s Dental Anxiety Scale) comprises four items, yielding scores from 4 to 20. In contrast, the MDAS (Modified Dental Anxiety Scale) utilized in our study is a five-item measure, with score range of 5 to 25. Most of the study participants were females below age 25 and come from lower-income households. Almost all the participants had visited a dentist before and therefore have had some prior exposure to the clinical triggers of dental anxiety assessed in this study.

When compared to the ML model approach, the classical statistical model approach showed a much higher RMSE and slightly higher R2. This implies that our ML model performed better than the classical statistical model in predicting dental anxiety due to the higher error rate in the classical statistical model and bearing in mind that R2 is sensitive to the number of variables in the model and therefore not a very accurate measure of model performance. Also, our classical statistical model (multiple linear regression) revealed only 13 predictors of DA in this study population based on the beta coefficient and p-value. In contrast, our ML model (Lasso regression) identified 28 predictors of DA based on the permuted mean RMSE. This highlights the ability of machine learning to model complex interactions between variables and identify a wider range of predictors beyond the classical model.

Interestingly, our study showed a very comparable performance between the classical statistical modelling approach and the machine learning approach in terms of variable selection. When we compared the 13 predictors of DA from the classical statistical model to the top 13 predictor variables from the machine learning model, both models identified 12 similar predictors of dental anxiety. The predictors include high fear of feeling pain during treatment, high fear of the sound or vibration of the drill, high fear of root canal treatment, high fear of panic attacks, high fear of injection in the mouth, high fear of needing a lot of dental treatment, high fear of being embarrassed, moderate fear of root canal treatment moderate fear of panic attacks, moderate fear of sound or vibration of the drill, frequency of dental visit (3 months to less than 6 months) and frequency of dental visit (less than 3 months).

High fear of pain during treatment and fear of injection in the mouth were associated with higher dental anxiety. More than half of the participants rated their level of fear of pain during treatment as high while more than three-quarters of the participants indicated moderate to high levels of fear of injection. Our findings align with the studies from Georgelin-Gurgel et al. [30] that found an association between higher levels of DA and fear of intraoral injection. Individuals who had high fear of the sound or vibration of drills had a 2.70 higher mean DA score compared to those who had low low fear of the sound or vibration of drills. This agrees with the Cohen et al.28 study that found a significant relationship between DA and the sound/vibration of drills.

High fear of root canal treatment was associated with a 2.6 higher mean DA score compared to low fear of root canal treatment with more than about two-thirds of the participants indicating high level of fear about root canal treatment which aligns with similar findings by Alghofaily et al. [31].

Individuals with high fear of panic attacks during treatment had a 3.22 higher mean DA score compared to those who had low panic attacks during treatment. Also, participants with high fear of being embarrassed had a 1.5 higher mean DA compared to those who had low fear of being embarrassed. A high level of concern about needing a lot of dental treatment was significantly associated with 1.84 higher mean DA compared to a low level of concern about needing a lot of dental treatment. The public health relevance of these findings is that if an individual feels they are going to be embarrassed or get diagnosed with more dental issues, they become more anxious and avoid routine dental care visits altogether.

Individuals who visited the dentist more frequently were significantly less likely to have dental anxiety. Individuals who have visited a dentist in the past 6 months had at least a 1.18 lower average DA score compared to those who have not visited the dentist in the past 12 months. This finding conforms with the study by Doerr et al. study where those who did not go for a checkup at least once a year were found to be more dentally anxious than subjects receiving more frequent dental care [27]. This implies that frequent visits to the dentist could help decrease dental anxiety due to continuous exposure to dental anxiety stimuli thereby improving the patient’s self-efficacy. Inversely, high dental anxiety can be said to have caused the low frequency of visits within this study population possibly due to previous personal experience or experiences of a family member, friends, or colleagues. Our study found no association between dental anxiety and the average household income, level of education, and sex. Both Our Machine Learning (ML) and the classical statistical approach identified set of variables as predictors for dental anxiety. These variables hold the potential to form the basis for developing a web application tailored to aid the diagnosis of dental anxiety and the customization of patient-specific interventions. It is important to highlight that our findings were derived from a sample of 454 students, which differs greatly from the initially calculated sample size of 1062 students and may have limited external validity.

The limitations of this study include the lack of generalizability to other populations due to the differences in population characteristics. The data obtained from WIU might not be representative of other universities in America. The study participants might not have given adequate and accurate information regarding the level of dental anxiety since its measurement is subjective. Reliability testing of the modified DCA questionnaire was not conducted, therefore caution should be applied when using the modified DCA questionnaires outside this study population. Similarly, it was not feasible to determine the reasons behind non-responses from certain study participants or elucidate factors implicated in the low response rates. This limitation may have significant implications for the strength of our study’s conclusions. However, a smaller sample size may affect the statistical power of our analysis, which may underestimate the actual effect or relationships present in this population.

Also, due to the sampling method and sensitivity of the topic, the true cases might have been missed out. Other than comparing the variable selection, there are no existing objective metrics for comparing classical statistical versus machine learning models.

In future studies, a more diverse and larger sample size will be considered to enhance the strength, reliability and applicability of our study.

Conclusion

There is a high burden of dental anxiety within this study population and continues to constitute a serious dental public health issue because those impacted are known to avoid dental visits. More frequent exposure to the clinic environment through routine visits plays a huge role in reducing the burden of dental anxiety, especially in young adults. This study contributes to reduce the knowledge gap about the impact of clinical exposure variables on dental anxiety and the role of machine learningin the prediction of dental anxiety. Behavioral theory (such as motivational interviewing) based public health interventions that are geared towards eliminating the individual clinical exposure triggers of dental anxiety are recommended.

Data availability

The data that support the findings of this study are available on request from the corresponding author.

References

  1. Rubin JG, Slovin HI, Krochak M. The psychodynamics of dental anxiety and dental phobia. Dent Clin North Am. 1988;32:647–56.

    Article  CAS  PubMed  Google Scholar 

  2. Klepac RI, Doding J, Hauge G. Characteristics of clients seeking therapy for the reduction of dental avoidance: reactions to pain. J Bebar Exp Psychiat. 1982;13:293–300.

    CAS  Google Scholar 

  3. Woolgrave J, Cumberbatch G. Dental anxiety and regularity of dental attendance. J Dent. 1986;14:209–13.

    Article  Google Scholar 

  4. Eli I. Dental anxiety: a cause for possible misdiagnosis of tooth vitality. Int Endod J. 1993;26:251–3.

    Article  CAS  PubMed  Google Scholar 

  5. Freeman R. A psychodynamic theory for dental phobia. Br Dent J. 1998;184:170–2.

    Article  CAS  PubMed  Google Scholar 

  6. Johansson P, Berggren U, Hakeberg M, Hirsch JM. Measures of dental beliefs and attitudes: their relationships with measures of fear. Community Dent Health. 1993;10(1):31–9.

    CAS  PubMed  Google Scholar 

  7. Humphris GM, Dyer TA, Robinson PG. The modified dental anxiety scale: UK general public population norms in 2008 with further psychometrics and effects of age. BMC Oral Health. 2009;9:20. https://doi.org/10.1186/1472-6831-9-20.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Milgrom P, Fiset L, hlelnick S, et al. The prevalence and practice management consequences of dental fear in a major US city. J Am Dent Assoc. 1988;116:641–7.

    Article  CAS  PubMed  Google Scholar 

  9. Locker D, Liddel A, Burman D. Dental fear and anxiety in an older adult population. Community Dent Oral Epidemiol. 1991;19:120–4.

    Article  CAS  PubMed  Google Scholar 

  10. Hakeberg M, Berggren U, Carlsson SG. Prevalence of dental anxiety in an adult population in a major urban area in Sweden. Community Dent Oral Epidemiol. 1992;20:97–101.

    Article  CAS  PubMed  Google Scholar 

  11. Frazer M, Hampson S. Some personality factors related to dental anxiety and fear of pain. Br Dent J. 1988;165:436–9.

    Article  CAS  PubMed  Google Scholar 

  12. Ost I. Age of onset of different phobias. J Abnorm Psychol. 1987;96:223–9.

    Article  CAS  PubMed  Google Scholar 

  13. Locker D, Liddell A. Correlates of Dental anxiety among older adults. J Dent Res. 1991;70(3):198–203. https://doi.org/10.1177/00220345910700030801.

    Article  CAS  PubMed  Google Scholar 

  14. Raadal M, Milgrom P, Weinstein P, Mancl L, Cauce AM. The prevalence of dental anxiety in children from low-income families and its relationship to personality traits. J Dent Res. 1995;74(8):1439–43.

    Article  CAS  PubMed  Google Scholar 

  15. Elter JR, Strauss RP, Beck JD. Assessing dental anxiety, dental care use, and oral health status in older adults. JADA. 1997;128(5):591–7.

    CAS  PubMed  Google Scholar 

  16. Kaakko T, Milgrom P, Coldwell SE, Getz T, Weinstein P, Ramsay DS. Dental fear among university students: implications for pharmacological research. Anesth Prog. 1998;45(2):62–7.

    CAS  PubMed  PubMed Central  Google Scholar 

  17. James G, Witten D, Hastie T, Tibshirani R. An introduction to statistical learning. Volume 112. New York: springer; 2013 Jun. p. 18.

  18. Champely S et al. pwr: Basic Functions for Power Analysis_. R package version 1.3-0. 2020. https://CRAN.R-project.org/package=pwr.

  19. Clarke JH, Rustvold S. Corah’s dental anxiety scale, revised (DAS-R). Oregon Health Sciences University School of Dentistry, 1993 [revised 1998]. Retrieved from http://www.dentalfearcentral.org/media/dental_anxiety_scale.pdf.

  20. Klingberg G, Broberg AG. Dental fear/anxiety and dental behaviour management problems in children and adolescents: a review of prevalence and concomitant psychological factors. Int J Paediatr Dent. 2007;17:391–406.

    Article  PubMed  Google Scholar 

  21. Carter AE, Carter G, Boschen M, AlShwaimi E, George R. Pathways of fear and anxiety in dentistry: a review. World J Clin Cases. 2014;2(11):642–53. https://doi.org/10.12998/wjcc.v2.i11.642.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Tibshirani R. Regression shrinkage and selection via the lasso. J Roy Stat Soc: Ser B (Methodol). 1996;58(1):267–88.

    MathSciNet  Google Scholar 

  23. Chen T, Guestrin C, Xgboost. A scalable tree boosting system. in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016 Aug 13 (pp. 785–794).

  24. Kuhn M, Wickham H. recipes: Preprocessing tools to create design matrices R package version (2020) 1.8. 0. https://github.com/tidymodels/recipes.

  25. Humphris G, Crawford JR, Hill K, Gilbert A, Freeman R. UK Population norms for the modified dental anxiety scale with percentile calculator: adult dental health survey 2009 results. BMC Oral Health. 2013;13:29. https://doi.org/10.1186/1472-6831-13-29.

    Article  PubMed  PubMed Central  Google Scholar 

  26. Geer JH. The development of a scale to measure fear. Behav Res Ther. 1965;3:45–53. https://doi.org/10.1016/0005-7967(65)90040-9.

    Article  CAS  PubMed  Google Scholar 

  27. Doerr PA, Lang WP, Nyquist LV, Ronis DL. Factors Associated with Dental anxiety. J Am Dent Assoc. 1998;129(8):1111–9.

    Article  CAS  PubMed  Google Scholar 

  28. Bare LC, Dundes L. Strategies for combating dental anxiety. J Dent Educ. 2004;68(11):1172–7. doi:68/11/1172 [pii].

    Article  PubMed  Google Scholar 

  29. Saatchi M, Abtahi M, Mohammadi G, Mirdamadi M, Binandeh ES. The prevalence of dental anxiety and fear in patients referred to Isfahan Dental School, Iran. Dent Res J. 2015;12(3):248–53.

    Google Scholar 

  30. Georgelin-Gurgel M, Diemer F, Nicolas E, Hennequin M. Surgical and nonsurgical endodontic treatment-induced stress. J Endod. 2009;35(1):19–22.

    Article  PubMed  Google Scholar 

  31. Alghofaily M, Alsalleeh F. Levels of anxiety and fear related to non-surgical root canal treatment performed by endodontic residents and endodontists. Front Dent Med:20.

Download references

Acknowledgements

I would like to acknowledge the contributions of Chukwuebuka Ogwo (the corresponding authors) led and contributed to the conception, design, data acquisition, and interpretation, performed all statistical analyses, and drafted and critically revised the manuscript. Ifeanyi David Okoye and Wisdom Osisioma contributed to the conception, design, data analysis, writing, and preparing the tables and figures for the manuscript. Jay Patel contributed to the data analysis, interpretation, drafting, and revision of the manuscript. Thank you, Professor Marisol Tellez Merchan for her expert guidance and comments during the final revision of the manuscript.

Funding

This research was supported by Temple University Kornberg School of Dentistry and the Cary Kleinman Oral Health Sciences Research Fund.

Author information

Authors and Affiliations

  1. Department of Oral Health Sciences, Maurice H Kornberg School of Dentistry, Temple University, Philadelphia, PA, 19140, US

    Chukwuebuka Ogwo, David Ifeanyi Okoye & Jay Patel

  2. School of Public Health, Texas A&M University, College Station, TX, USA

    Wisdom Osisioma

Authors
  1. Chukwuebuka Ogwo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wisdom Osisioma
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. David Ifeanyi Okoye
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jay Patel
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Chukwuebuka Ogwo (the corresponding authors) led and contributed to the conception, design, data acquisition, and interpretation, performed all statistical analyses, and drafted and critically revised the manuscript. Ifeanyi David Okoye and Wisdom Osisioma contributed to the conception, design, data analysis, writing, and preparing the tables and figures for the manuscript. Jay Patel contributed to the data analysis, interpretation, drafting, and revision of the manuscript. All authors gave their final approval and agreed to be accountable for all aspects of the work.

Corresponding author

Correspondence to Chukwuebuka Ogwo.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

Approval for the conduct and collection of the data for this study was obtained from Western Illinois University Institutional Review Board. All components and procedures of the study were conducted in accordance with the guidelines and regulations of the Western Illinois University Institutional Review Board. Informed consent was obtained from all subjects and their legal guardian(s) before responding to the questionnaires.

Consent for publication

Not applicable.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ogwo, C., Osisioma, W., Okoye, D.I. et al. Predicting dental anxiety in young adults: classical statistical modelling approach versus machine learning approach. BMC Oral Health 24, 313 (2024). https://doi.org/10.1186/s12903-024-04012-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1186/s12903-024-04012-3

BMC Oral Health

ISSN: 1472-6831

Contact us