Receiver operating characteristic curve-based prediction model for periodontal disease updated with the calibrated community periodontal index

Chiu Wen Su, Amy Ming Fang Yen, Hongmin Lai, Hsiu Hsi Chen, Sam Li Sheng Chen

研究成果: 雜誌貢獻文章

2 引文 斯高帕斯(Scopus)

摘要

Background: 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. Methods: 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. Results: 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 (P <0.05). Conclusion: An improvement in the updated prediction model was demonstrated for periodontal disease as measured by the calibrated CPI derived from a large epidemiologic survey.
原文英語
頁(從 - 到)1348-1355
頁數8
期刊Journal of Periodontology
88
發行號12
DOIs
出版狀態已發佈 - 十二月 1 2017

ASJC Scopus subject areas

  • Periodontics

指紋 深入研究「Receiver operating characteristic curve-based prediction model for periodontal disease updated with the calibrated community periodontal index」主題。共同形成了獨特的指紋。

  • 引用此