Back to Search
Start Over
Receiver Operating Characteristic Curve–Based Prediction Model for Periodontal Disease Updated With the Calibrated Community Periodontal Index
- Source :
- Journal of Periodontology. 88:1348-1355
- Publication Year :
- 2017
- Publisher :
- Wiley, 2017.
-
Abstract
- The accuracy of a prediction model for periodontal disease using the community periodontal index (CPI) has been undertaken by using an area under a receiver operating characteristics (AUROC) curve. How the uncalibrated CPI, as measured by general dentists trained by periodontists in a large epidemiologic study, and affects the performance in a prediction model, has not been researched yet.A two-stage design was conducted by first proposing a validation study to calibrate CPI between a senior periodontal specialist and trained general dentists who measured CPIs in the main study of a nationwide survey. A Bayesian hierarchical logistic regression model was applied to estimate the non-updated and updated clinical weights used for building up risk scores. How the calibrated CPI affected performance of the updated prediction model was quantified by comparing AUROC curves between the original and updated models.Estimates regarding calibration of CPI obtained from the validation study were 66% and 85% for sensitivity and specificity, respectively. After updating, clinical weights of each predictor were inflated, and the risk score for the highest risk category was elevated from 434 to 630. Such an update improved the AUROC performance of the two corresponding prediction models from 62.6% (95% confidence interval [CI]: 61.7% to 63.6%) for the non-updated model to 68.9% (95% CI: 68.0% to 69.6%) for the updated one, reaching a statistically significant difference (P0.05).An improvement in the updated prediction model was demonstrated for periodontal disease as measured by the calibrated CPI derived from a large epidemiologic survey.
- Subjects :
- Adult
Male
Validation study
Epidemiologic study
Index (economics)
Adolescent
Alcohol Drinking
020205 medical informatics
Bayesian probability
Dentistry
02 engineering and technology
Nationwide survey
Logistic regression
Young Adult
03 medical and health sciences
Sex Factors
0302 clinical medicine
Periodontal disease
Risk Factors
Statistics
0202 electrical engineering, electronic engineering, information engineering
Humans
Medicine
Periodontal Diseases
Aged
Aged, 80 and over
Models, Statistical
Receiver operating characteristic
business.industry
Smoking
Age Factors
Reproducibility of Results
Bayes Theorem
030206 dentistry
Middle Aged
Logistic Models
ROC Curve
Calibration
Educational Status
Periodontics
Periodontal Index
business
Subjects
Details
- ISSN :
- 19433670 and 00223492
- Volume :
- 88
- Database :
- OpenAIRE
- Journal :
- Journal of Periodontology
- Accession number :
- edsair.doi.dedup.....53561972e3de886194e159fcd75dc27e