TITLE

Analysis of Caries Experience Taking Inter-observer Bias and Variability into Account

AUTHOR(S)

Lesaffre, E.; Mwalili, S. M.; Declerck, D.

PUB. DATE

December 2004

SOURCE

Journal of Dental Research;Dec2004, Vol. 83 Issue 12, p951

SOURCE TYPE

Academic Journal

DOC. TYPE

Article

ABSTRACT

In larger oral health surveys, clinical measurements are often obtained using several examiners. This raises the issue of inter-observer variability in measurement. Often, the problem is dealt with by reporting kappa values obtained in a calibration exercise. In the present study, the limitations of this statistic are presented, and an alternative, based on a Bayesian approach, is proposed. When the alternative approach was applied to caries experience data obtained in an oral health screening survey in seven-year-old Flemish children (Signal Tandmobiel� study), it could be ruled out that the observed geographic East-West gradient was due to bias induced by variability in scoring of the different dental examiners involved. The proposed method offers an opportunity to refine existing analytical approaches and is relevant to any health outcome study.

ACCESSION #

36455820

Tags: HEALTH surveys;  DENTAL surveys;  CALIBRATION;  LOGISTIC regression analysis;  DENTAL caries;  BAYESIAN statistical decision theory

 

Related Articles

• Dental Caries Prevalence and Tooth Loss in Chilean Adult Population: First National Dental Examination Survey. Urzua, I.; Mendoza, C.; Arteaga, O.; Rodríguez, G.; Cabello, R.; Faleiros, S.; Carvajal, P.; Muñoz, A.; Espinoza, I.; Aranda, W.; Gamonal, J. // International Journal of Dentistry;2012, p1 

  The purpose of this study was to assess the prevalence of dental caries, tooth loss, and risk factors among adult population of Chile. Furthermore, age, gender, and behavioural specific differences in caries prevalence and tooth loss were examined. A national stratified multistage probabilistic...

• Information Market-Based Decision Fusion. Perols, Johan; Chari, Kaushal; Agrawal, Manish // Management Science;May2009, Vol. 55 Issue 5, p827 

  Improved classification performance has practical real-world benefits ranging from improved effectiveness in detecting diseases to increased efficiency in identifying firms that are committing financial fraud. Multiclassifier combination (MCC) aims to improve classification performance by...

• Using Bayesian neural networks with ARD input selection to detect malignant ovarian masses prior to surgery. Van Calster, Ben; Timmerman, Dirk; Nabney, Ian T.; Valentin, Lil; Testa, Antonia C.; Van Holsbeke, Caroline; Vergote, Ignace; Van Huffel, Sabine // Neural Computing & Applications;2008, Vol. 17 Issue 5/6, p489 

  In this paper, we applied Bayesian multi-layer perceptrons (MLP) using the evidence procedure to predict malignancy of ovarian masses in a large ( n = 1,066) multi-centre data set. Automatic relevance determination (ARD) was used to select the most relevant inputs. Fivefold cross-validation...

• Combining instance-based learning and logistic regression for multilabel classification. Weiwei Cheng; H�llermeier, Eyke // Machine Learning;Sep2009, Vol. 76 Issue 2/3, p211 

  Multilabel classification is an extension of conventional classification in which a single instance can be associated with multiple labels. Recent research has shown that, just like for conventional classification, instance-based learning algorithms relying on the nearest neighbor estimation...

• Temporality in Link Prediction: Understanding Social Complexity. Potgieter, Anet; April, Kurt A.; Cooke, Richard J. E.; Osunmakinde, Isaac O. // Emergence: Complexity & Organization;2009, Vol. 11 Issue 1, p69 

  This article describes research into the discovery and modelling of emergent temporal phenomena in social networks. It summarizes experimental results that bring together two views in contemporary science: Bayesian analysis and link prediction, to enhance the current understanding of emergent...

• A Bayesian Analysis of a Random Effects Small Business Loan Credit Scoring Model. Farrell, Patrick J.; MacGibbon, Brenda; Tomberlin, Thomas J.; Doreen, Dale // Pakistan Journal of Statistics & Operation Research;Supplement, Vol. 7 Issue 2, p433 

  One of the most important aspects of credit scoring is constructing a model that has low misclassification rates and is also flexible enough to allow for random variation. It is also well known that, when there are a large number of highly correlated variables as is typical in studies involving...

• Analysis of genome-wide association data by large-scale Bayesian logistic regression. Yuanjia Wang; Nanshi Sha; Yixin Fang // BMC Proceedings;2009 Supplement 7, Vol. 3, Special section p1 

  Single-locus analysis is often used to analyze genome-wide association (GWA) data, but such analysis is subject to severe multiple comparisons adjustment. Multivariate logistic regression is proposed to fit a multi-locus model for case-control data. However, when the sample size is much smaller...

• Mixed-membership naive Bayes models. Shan, Hanhuai; Banerjee, Arindam // Data Mining & Knowledge Discovery;Jul2011, Vol. 23 Issue 1, p1 

  In recent years, mixture models have found widespread usage in discovering latent cluster structure from data. A popular special case of finite mixture models is the family of naive Bayes (NB) models, where the probability of a feature vector factorizes over the features for any given component...

• Calibration Choice, Rate Smoothing, and the Pattern of Tetrapod Diversification According to the Long Nuclear Gene RAG-1. Hugall, Andrew F.; Foster, Ralph; Lee, Michael S. Y. // Systematic Biology;Aug2007, Vol. 56 Issue 4, p543 

  A phylogeny of tetrapods is inferred from nearly complete sequences of the nuclear RAG-1 gene sampled across 88 taxa encompassing all major clades, analyzed via parsimony and Bayesian methods. The phylogeny provides support for Lissamphibia, Theria, Lepidosauria, a turtle-archosaur clade, as...

Read the Article