Skip to main content

Table 4 Logistic regression models for predicting severe periodontitis and their performance

From: A rapid, non-invasive tool for periodontitis screening in a medical care setting

Predictor Model 1:
Questionnaire, demographic data and biomarkers
Model 2:
Questionnaire and demographic data
Model 3:
Questionnaire only
Contributing to model Reference
category
B Contributing to model Reference
category
B Contributing to model Reference
category
B
Predictor
 Q1. Gum disease + Yes 1.573       
 Q2. Own teeth/gum health        + Negative 1.152
 Q3. Gum treatment + Yes 2.100 + Yes 2.073 + Yes 2.235
 Q4. Loose teeth     + Yes 1.277 + Yes 1.306
 Q5. Lost bone
 Q6. Tooth appearance     + Yes 1.590 + Yes 0.973
 Q8. Mouthwash use + 1–7 days 1.745 + 1–7 days 1.440 + 1–7 days 1.181
 Age (years) + > 39 1.455 + > 39 1.615    
 Sex + Male 1.272 + Male 1.091    
 Smoking + Yes 2.007       
 Albumin concentration + n/a 0.727       
 Chitinase activity
 Protease activity
Model performance
 AUROCC (95% CI) 0.89 (0.85–0.95) 0.82 (0.75–0.89) 0.78 (0.71–0.86)
 Predicted probability cut-off 0.250 0.214 0.273
 Hosmer-Lemeshow 0.827 0.963 0.717
 Sensitivity (95% CI), (%) 86 (71–95) 80 (66–90) 65 (52–79)
 Specificity (95% CI), (%) 78 (68–86) 70 (60–79) 81 (73–88)
 PPV (95% CI), (%) 62 (52–71) 56 (48–64) 62 (48–75)
 NPV (95% CI), (%) 93 (86–97) 88 (81–93) 83 (76–90)
  1. The table lists all candidate predictors (data presented in Table 1, Table 2, and Fig. 1). The predictors marked with a + are the ones that remained in the prediction model after stepwise backward regression modeling (see Methods section of main text). The reference category represents the response which was coded 1 in the analysis. B is the regression coefficient of the predictor, indicating its weight
  2. n/a not applicable, AUROCC area under receiver operator characteristic curve, PPV positive predictive value, NPV negative predictive value