Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7
Background: Dental caries is the most common chronic childhood infectious disease and is a serious public health problem affecting both developing and industrialized countries, yet it is preventable in most cases. This study evaluated the potential of screening for dental caries among children using...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Dentistry Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6767/9/12/141 |
| _version_ | 1797505552572481536 |
|---|---|
| author | Francisco Ramos-Gomez Marvin Marcus Carl A. Maida Yan Wang Janni J. Kinsler Di Xiong Steve Y. Lee Ron D. Hays Jie Shen James J. Crall Honghu Liu |
| author_facet | Francisco Ramos-Gomez Marvin Marcus Carl A. Maida Yan Wang Janni J. Kinsler Di Xiong Steve Y. Lee Ron D. Hays Jie Shen James J. Crall Honghu Liu |
| author_sort | Francisco Ramos-Gomez |
| collection | DOAJ |
| description | Background: Dental caries is the most common chronic childhood infectious disease and is a serious public health problem affecting both developing and industrialized countries, yet it is preventable in most cases. This study evaluated the potential of screening for dental caries among children using a machine learning algorithm applied to parent perceptions of their child’s oral health assessed by survey. Methods: The sample consisted of 182 parents/caregivers and their children 2–7 years of age living in Los Angeles County. Random forest (a machine learning algorithm) was used to identify survey items that were predictors of active caries and caries experience. We applied a three-fold cross-validation method. A threshold was determined by maximizing the sum of sensitivity and specificity conditional on the sensitivity of at least 70%. The importance of survey items to classifying active caries and caries experience was measured using mean decreased Gini (MDG) and mean decreased accuracy (MDA) coefficients. Results: Survey items that were strong predictors of active caries included parent’s age (MDG = 0.84; MDA = 1.97), unmet needs (MDG = 0.71; MDA = 2.06) and the child being African American (MDG = 0.38; MDA = 1.92). Survey items that were strong predictors of caries experience included parent’s age (MDG = 2.97; MDA = 4.74), child had an oral health problem in the past 12 months (MDG = 2.20; MDA = 4.04) and child had a tooth that hurt (MDG = 1.65; MDA = 3.84). Conclusion: Our findings demonstrate the potential of screening for active caries and caries experience among children using surveys answered by their parents. |
| first_indexed | 2024-03-10T04:20:13Z |
| format | Article |
| id | doaj.art-ac100a5e79d147ab9308ebf4de6abdb0 |
| institution | Directory Open Access Journal |
| issn | 2304-6767 |
| language | English |
| last_indexed | 2024-03-10T04:20:13Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Dentistry Journal |
| spelling | doaj.art-ac100a5e79d147ab9308ebf4de6abdb02023-11-23T07:51:45ZengMDPI AGDentistry Journal2304-67672021-12-0191214110.3390/dj9120141Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7Francisco Ramos-Gomez0Marvin Marcus1Carl A. Maida2Yan Wang3Janni J. Kinsler4Di Xiong5Steve Y. Lee6Ron D. Hays7Jie Shen8James J. Crall9Honghu Liu10Section of Pediatric Dentistry, Division of Growth & Development, School of Dentistry, University of California, Los Angeles, CA 90095, USADivision of Public Health & Community Dentistry, School of Dentistry, University of California, Los Angeles, CA 90095, USADivision of Public Health & Community Dentistry, School of Dentistry, University of California, Los Angeles, CA 90095, USADivision of Infectious Diseases, David Geffen School of Medicine, University of California, Los Angeles, CA 90095, USASection of Pediatric Dentistry, Division of Growth & Development, School of Dentistry, University of California, Los Angeles, CA 90095, USADivision of Public Health & Community Dentistry, School of Dentistry, University of California, Los Angeles, CA 90095, USADivision of Constitutive and Regenerative Sciences, School of Dentistry, University of California, Los Angeles, CA 90095, USADepartment of Health Policy and Management, School of Public Health, University of California, Los Angeles, CA 90095, USADivision of Public Health & Community Dentistry, School of Dentistry, University of California, Los Angeles, CA 90095, USADivision of Public Health & Community Dentistry, School of Dentistry, University of California, Los Angeles, CA 90095, USADivision of Public Health & Community Dentistry, School of Dentistry, University of California, Los Angeles, CA 90095, USABackground: Dental caries is the most common chronic childhood infectious disease and is a serious public health problem affecting both developing and industrialized countries, yet it is preventable in most cases. This study evaluated the potential of screening for dental caries among children using a machine learning algorithm applied to parent perceptions of their child’s oral health assessed by survey. Methods: The sample consisted of 182 parents/caregivers and their children 2–7 years of age living in Los Angeles County. Random forest (a machine learning algorithm) was used to identify survey items that were predictors of active caries and caries experience. We applied a three-fold cross-validation method. A threshold was determined by maximizing the sum of sensitivity and specificity conditional on the sensitivity of at least 70%. The importance of survey items to classifying active caries and caries experience was measured using mean decreased Gini (MDG) and mean decreased accuracy (MDA) coefficients. Results: Survey items that were strong predictors of active caries included parent’s age (MDG = 0.84; MDA = 1.97), unmet needs (MDG = 0.71; MDA = 2.06) and the child being African American (MDG = 0.38; MDA = 1.92). Survey items that were strong predictors of caries experience included parent’s age (MDG = 2.97; MDA = 4.74), child had an oral health problem in the past 12 months (MDG = 2.20; MDA = 4.04) and child had a tooth that hurt (MDG = 1.65; MDA = 3.84). Conclusion: Our findings demonstrate the potential of screening for active caries and caries experience among children using surveys answered by their parents.https://www.mdpi.com/2304-6767/9/12/141dental carieschildrenoral healthdisparitiesmachine learning algorithmsrandom forest |
| spellingShingle | Francisco Ramos-Gomez Marvin Marcus Carl A. Maida Yan Wang Janni J. Kinsler Di Xiong Steve Y. Lee Ron D. Hays Jie Shen James J. Crall Honghu Liu Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7 Dentistry Journal dental caries children oral health disparities machine learning algorithms random forest |
| title | Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7 |
| title_full | Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7 |
| title_fullStr | Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7 |
| title_full_unstemmed | Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7 |
| title_short | Using a Machine Learning Algorithm to Predict the Likelihood of Presence of Dental Caries among Children Aged 2 to 7 |
| title_sort | using a machine learning algorithm to predict the likelihood of presence of dental caries among children aged 2 to 7 |
| topic | dental caries children oral health disparities machine learning algorithms random forest |
| url | https://www.mdpi.com/2304-6767/9/12/141 |
| work_keys_str_mv | AT franciscoramosgomez usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT marvinmarcus usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT carlamaida usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT yanwang usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT jannijkinsler usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT dixiong usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT steveylee usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT rondhays usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT jieshen usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT jamesjcrall usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 AT honghuliu usingamachinelearningalgorithmtopredictthelikelihoodofpresenceofdentalcariesamongchildrenaged2to7 |