Skip to main content

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

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

ML model (Lasso regression) *

Classical statistical model (Multiple Linear regression) **

High fear of feeling pain during treatment

High fear of panic attack

High fear of the sound or vibration of the drill

High of feeling pain during treatment

High fear of root canal treatment

High fear of the sound or vibration of the drill

High fear of panic attacks

High fear of root canal treatment

High fear of injection in the mouth

High fear of injection in the mouth

High fear of needing a lot of dental treatment

Moderate fear of root canal treatment

High fear of being embarrassed

High fear of needing a lot of dental treatment

Moderate fear of root canal treatment

High fear of being embarrassed

Moderate fear of panic attacks

Moderate fear of panic attacks

High fear of being injured

Frequency of dental visits (3 months to less than 6 months)

Moderate fear of the sound or vibration of the drill

Moderate fear of the sound or feel of scraping during teeth cleaning

Frequency of dental visits (3 months to less than 6 months)

Moderate fear of the sound or vibration of the drill

Frequency of dental visits less than 3 months

Frequency of dental visits less than 3 months

Comparison of performance of the ML model versus classical statistical model

RMSE = 0.617

RMSE = 3.16

R2 = 0.615

R2 = 0.67

  1. * Ranking was based on the permuted mean RMSE.
  2. ** Ranking was based on the beta coefficient and statistical significance (p < 0.05)
  3. Note: Lower RMSE equals better model performance.