Deepti S Karhade1, Jeff Roach2, Poojan Shrestha3, Miguel A Simancas-Pallares4, Jeannie Ginnis5, Zachary J S Burk6, Apoena A Ribeiro7, Hunyong Cho8, Di Wu9, Kimon Divaris10. 1. Dr. Karhade is a pediatric dentistry resident, Division of Pediatric and Public Health, Adams School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA; deepti_karhade@unc. edu. 2. Dr. Roach is a senior scientific research associate, Research Computing, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 3. Dr. Shrestha is a pediatric dentistry resident, Division of Pediatric and Public Health, Adams School of Dentistry, and PhD candidate, Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 4. Dr. Simancas-Pallares is a pediatric dentistry resident, Division of Pediatric and Public Health, Adams School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 5. Dr. Ginnis is an assistant professor, Division of Pediatric and Public Health, Adams School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 6. Mr. Burk is a DDS candidate, Adams School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 7. Dr. Ribeiro is an associate professor, Division of Diagnostic Sciences, Adams School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 8. Mr. Cho is a PhD candidate, Department of Biostatistics, Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 9. Dr. Wu is an associate professor, Department of Biostatistics, Gillings School of Global Public Health, and Division of Oral and Craniofacial Health Research, Adams School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA. 10. Dr. Divaris is a professor, Division of Pediatric and Public Health, Adams School of Dentistry, University of North Carolina at Chapel Hill, Chapel Hill, N.C., USA.
Abstract
Purpose: The purpose of the study was to develop and evaluate an automated machine learning algorithm (AutoML) for children's classification according to early childhood caries (ECC) status. Methods: Clinical, demographic, behavioral, and parent-reported oral health status information for a sample of 6,404 three- to five-year-old children (mean age equals 54 months) participating in an epidemiologic study of early childhood oral health in North Carolina was used. ECC prevalence (decayed, missing, and filled primary teeth surfaces [dmfs] score greater than zero, using an International Caries Detection and Assessment System score greater than or equal to three caries lesion detection threshold) was 54 percent. Ten sets of ECC predictors were evaluated for ECC classification accuracy (i.e., area under the ROC curve [AUC], sensitivity [Se], and positive predictive value [PPV]) using an AutoML deployment on Google Cloud, followed by internal validation and external replication. Results: A parsimonious model including two terms (i.e., children's age and parent-reported child oral health status: excellent/very good/good/fair/poor) had the highest AUC (0.74), Se (0.67), and PPV (0.64) scores and similar performance using an external National Health and Nutrition Examination Survey (NHANES) dataset (AUC equals 0.80, Se equals 0.73, PPV equals 0.49). Contrarily, a comprehensive model with 12 variables covering demographics (e.g., race/ethnicity, parental education), oral health behaviors, fluoride exposure, and dental home had worse performance (AUC equals 0.66, Se equals 0.54, PPV equals 0.61). Conclusions: Parsimonious automated machine learning early childhood caries classifiers, including single-item self-reports, can be valuable for ECC screening. The classifier can accommodate biological information that can help improve its performance in the future.
Purpose: The purpose of the study was to develop and evaluate an automated machine learning algorithm (AutoML) for children's classification according to early childhood caries (ECC) status. Methods: Clinical, demographic, behavioral, and parent-reported oral health status information for a sample of 6,404 three- to five-year-old children (mean age equals 54 months) participating in an epidemiologic study of early childhood oral health in North Carolina was used. ECC prevalence (decayed, missing, and filled primary teeth surfaces [dmfs] score greater than zero, using an International Caries Detection and Assessment System score greater than or equal to three caries lesion detection threshold) was 54 percent. Ten sets of ECC predictors were evaluated for ECC classification accuracy (i.e., area under the ROC curve [AUC], sensitivity [Se], and positive predictive value [PPV]) using an AutoML deployment on Google Cloud, followed by internal validation and external replication. Results: A parsimonious model including two terms (i.e., children's age and parent-reported child oral health status: excellent/very good/good/fair/poor) had the highest AUC (0.74), Se (0.67), and PPV (0.64) scores and similar performance using an external National Health and Nutrition Examination Survey (NHANES) dataset (AUC equals 0.80, Se equals 0.73, PPV equals 0.49). Contrarily, a comprehensive model with 12 variables covering demographics (e.g., race/ethnicity, parental education), oral health behaviors, fluoride exposure, and dental home had worse performance (AUC equals 0.66, Se equals 0.54, PPV equals 0.61). Conclusions: Parsimonious automated machine learning early childhood caries classifiers, including single-item self-reports, can be valuable for ECC screening. The classifier can accommodate biological information that can help improve its performance in the future.
Authors: Benjamin W Chaffee; Carlos Alberto Feldens; Priscila Humbert Rodrigues; Márcia Regina Vítolo Journal: Community Dent Oral Epidemiol Date: 2015-03-05 Impact factor: 3.383
Authors: Xiaoli Gao; Ivy Di Wu; Edward Chin Man Lo; Chun Hung Chu; Chin-Ying Stephen Hsu; May Chun Mei Wong Journal: J Dent Date: 2013-06-19 Impact factor: 4.379
Authors: Sergeui Pakhomov; Nilay Shah; Penny Hanson; Saranya Balasubramaniam; Steven A Smith; Steven Allan Smith Journal: AMIA Annu Symp Proc Date: 2008-11-06