1
|
Shen S, Yuan X, Wang J, Fan L, Zhao J, Tao J. Evaluation of a machine learning algorithms for predicting the dental age of adolescent based on different preprocessing methods. Front Public Health 2022; 10:1068253. [PMID: 36530730 PMCID: PMC9751184 DOI: 10.3389/fpubh.2022.1068253] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2022] [Accepted: 11/14/2022] [Indexed: 12/05/2022] Open
Abstract
Background Machine learning (ML) algorithms play a key role in estimating dental age. In this study, three ML models were used for dental age estimation, based on different preprocessing methods. Aim The seven mandibular teeth on the digital panorama were measured and evaluated according to the Cameriere and the Demirjian method, respectively. Correlation data were used for decision tree (DT), Bayesian ridge regression (BRR), k-nearest neighbors (KNN) models for dental age estimation. An accuracy comparison was made among different methods. Subjects and methods We analyzed 748 orthopantomographs (392 males and 356 females) from eastern China between the age of 5 and 13 years in this retrospective study. Three models, DT, BRR, and KNN, were used to estimate the dental age. The data in ML is obtained according to the Cameriere method and the Demirjian method. Coefficient of determination (R2), mean error (ME), root mean square error (RMSE), mean square error (MSE) and mean absolute error (MAE), the above five metrics were used to evaluate the accuracy of age estimation. Results Our experimental results showed that the prediction accuracy of dental age was affected by ML algorithms. MD, MAD, MSE, RMSE of the dental age predicted by ML were significantly decreased. Among all the methods, the KNN model based on the Cameriere method had the highest accuracy (ME = 0.015, MAE = 0.473, MSE = 0.340, RMSE = 0.583, R2 = 0.94). Conclusion The results show that the prediction accuracy of dental age is influenced by ML algorithms and preprocessing method. The KNN model based on the Cameriere method was able to infer dental age more accurately in a clinical setting.
Collapse
Affiliation(s)
- Shihui Shen
- Department of General Dentistry, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Stomatology, Shanghai Jiao Tong University, Shanghai, China,National Center for Stomatology, Shanghai, China,National Clinical Research Center for Oral Diseases, Shanghai, China,Shanghai Key Laboratory of Stomatology, Shanghai, China,Shanghai Research Institute of Stomatology, Shanghai, China
| | - Xiaoyan Yuan
- Department of General Dentistry, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Stomatology, Shanghai Jiao Tong University, Shanghai, China,National Center for Stomatology, Shanghai, China,National Clinical Research Center for Oral Diseases, Shanghai, China,Shanghai Key Laboratory of Stomatology, Shanghai, China,Shanghai Research Institute of Stomatology, Shanghai, China
| | - Jian Wang
- Department of General Dentistry, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Stomatology, Shanghai Jiao Tong University, Shanghai, China,National Center for Stomatology, Shanghai, China,National Clinical Research Center for Oral Diseases, Shanghai, China,Shanghai Key Laboratory of Stomatology, Shanghai, China,Shanghai Research Institute of Stomatology, Shanghai, China
| | - Linfeng Fan
- College of Stomatology, Shanghai Jiao Tong University, Shanghai, China,National Center for Stomatology, Shanghai, China,National Clinical Research Center for Oral Diseases, Shanghai, China,Shanghai Key Laboratory of Stomatology, Shanghai, China,Shanghai Research Institute of Stomatology, Shanghai, China,Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Junjun Zhao
- Department of General Dentistry, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Stomatology, Shanghai Jiao Tong University, Shanghai, China,National Center for Stomatology, Shanghai, China,National Clinical Research Center for Oral Diseases, Shanghai, China,Shanghai Key Laboratory of Stomatology, Shanghai, China,Shanghai Research Institute of Stomatology, Shanghai, China,Junjun Zhao
| | - Jiang Tao
- Department of General Dentistry, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China,College of Stomatology, Shanghai Jiao Tong University, Shanghai, China,National Center for Stomatology, Shanghai, China,National Clinical Research Center for Oral Diseases, Shanghai, China,Shanghai Key Laboratory of Stomatology, Shanghai, China,Shanghai Research Institute of Stomatology, Shanghai, China,*Correspondence: Jiang Tao
| |
Collapse
|
2
|
Evaluation of the Relationship between the Weight and Height Percentiles and the Sequence and Chronology of Eruption in Permanent Dentition. Healthcare (Basel) 2022; 10:healthcare10081363. [PMID: 35893184 PMCID: PMC9330262 DOI: 10.3390/healthcare10081363] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2022] [Revised: 07/20/2022] [Accepted: 07/20/2022] [Indexed: 11/17/2022] Open
Abstract
The standard eruption of the permanent dentition in growing patients is influenced by multiple environmental factors. The objective of this research was to study the relationship between height and weight percentiles and the eruption of the permanent dentition. The design of the study was transversal based on the review of the clinical history, visual dental inspection, weight and height indicators, and their respective percentiles in patients in the mixed and definitive dentition stage. The descriptive and comparative analysis of the data was carried out with the statistical software R version 4.1.1. The sample size was 725 participants. The mean age of eruption of the first tooth was 8.0. The eruption sequence in the upper arch was first molar, central and lateral incisor, first premolar, canine, second premolar, and second molar. In the lower arch, the eruption sequence was: central incisor, first molar, lateral incisor, canine, first and second premolar, and second molar. The most frequent weight percentile was P50-97 (50.34%) and height P3-50 (53.38%). Weight (0.0129; 0.0426; 0.0495; 0.000166) and height (0.00768; 0.00473; 0.00927; 10−5) variables significantly influenced dental eruption. The factor that most influences the eruption of the permanent dentition is the height percentile.
Collapse
|
3
|
Evaluation of the Relationship between the BMI and the Sequence and Chronology of Eruption in Permanent Dentition in Spanish Population. Healthcare (Basel) 2022; 10:healthcare10061046. [PMID: 35742098 PMCID: PMC9222528 DOI: 10.3390/healthcare10061046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2022] [Revised: 05/31/2022] [Accepted: 06/02/2022] [Indexed: 11/17/2022] Open
Abstract
The aim was to analyze the relationship between BMI (body mass index) and the sequence and chronology of the eruption of permanent teeth in a sample of Spanish children. Methods: The study design was descriptive, cross-sectional, observational, and epidemiological. Patients of pediatric age were included. Emerged teeth, and patient’s age, race, and sex were recorded. The nutritional status of the child was assessed by calculating the BMI, according to the WHO parameters. Statistical analysis was carried out with a confidence interval of 95%. A prediction model with logistic regression models was obtained. Results: A total of 725 pediatric patients between 4 and 14 years old were analyzed. BMI acts as a predictor variable for eruption symmetry, as it was most frequent in overweight children (p < 0.001). The probability of symmetry in dental eruption increases for South American children, for an extra month of age, and each meter of height. BMI had an influence in the first tooth to appear only in the fourth quadrant. BMI did not seem to influence present teeth, and the sequence of permanent dental eruption was not influenced by the BMI category. Conclusions: Age, weight, height, and BMI act as significant predictors for eruption symmetry. BMI does not produce alterations in the eruption sequence of the permanent dentition.
Collapse
|
4
|
Cummaudo M, De Angelis D, Magli F, Minà G, Merelli V, Cattaneo C. Age estimation in the living: A scoping review of population data for skeletal and dental methods. Forensic Sci Int 2021; 320:110689. [PMID: 33561788 DOI: 10.1016/j.forsciint.2021.110689] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2020] [Revised: 01/07/2021] [Accepted: 01/11/2021] [Indexed: 11/22/2022]
Abstract
Age estimation of living individuals has become a crucial part of the forensic practice, especially due to the global increase in cross-border migration. The low rate of birth registration in many countries, hence of identification documents of migrants, especially in Africa and Asia, highlights the importance of reliable methods for age estimation of living individuals. Despite the fact that a number of skeletal and dental methods for age estimation have been developed, their main limitation is that they are based on specific reference samples and there is still no consensus among researchers on whether these methods can be applied to all populations. Though this issue remains still unsolved, population information at a glance could be useful for forensic practitioners dealing with such issues. This study aims at presenting a scoping review and mapping of the current situation concerning population data for skeletal (hand-wrist and clavicle) and dental methods (teeth eruption and third molar formation) for age estimation in the living. Two hundred studies on the rate of skeletal maturation and four hundred thirty-nine on the rate of dental maturation were found, covering the period from 1952 and 2020 for a total of ninety-eight countries. For most of the western and central African countries there are currently no data on the rate of skeletal and dental maturation. The same applies to the countries of the Middle East, as well as the eastern European countries, especially as regard the skeletal development.
Collapse
Affiliation(s)
- Marco Cummaudo
- LABANOF, Laboratorio di Antropologia e Odontologia Forense, Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy; Centro Servizi MSNA Zendrini, Via Bernardino Zendrini, 15 - 20147, Milano, Italy.
| | - Danilo De Angelis
- LABANOF, Laboratorio di Antropologia e Odontologia Forense, Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy; Centro Servizi MSNA Zendrini, Via Bernardino Zendrini, 15 - 20147, Milano, Italy
| | - Francesca Magli
- LABANOF, Laboratorio di Antropologia e Odontologia Forense, Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy; Centro Servizi MSNA Zendrini, Via Bernardino Zendrini, 15 - 20147, Milano, Italy
| | - Giulia Minà
- LABANOF, Laboratorio di Antropologia e Odontologia Forense, Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy
| | - Vera Merelli
- LABANOF, Laboratorio di Antropologia e Odontologia Forense, Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy; Centro Servizi MSNA Zendrini, Via Bernardino Zendrini, 15 - 20147, Milano, Italy
| | - Cristina Cattaneo
- LABANOF, Laboratorio di Antropologia e Odontologia Forense, Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy; Centro Servizi MSNA Zendrini, Via Bernardino Zendrini, 15 - 20147, Milano, Italy
| |
Collapse
|
5
|
Yisak H, Tadege M, Ambaw B, Ewunetei A. Prevalence and Determinants of Stunting, Wasting, and Underweight Among School-Age Children Aged 6-12 Years in South Gondar Zone, Ethiopia. Pediatric Health Med Ther 2021; 12:23-33. [PMID: 33500678 PMCID: PMC7822222 DOI: 10.2147/phmt.s287815] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2020] [Accepted: 12/10/2020] [Indexed: 11/23/2022] Open
Abstract
BACKGROUND Underweight, wasting, and stunting are the commonest nutritional disorders among children, especially in developing countries. The aim of this study was to assess the prevalence and determinant factors of underweight, wasting, and stunting among school-age children in 2019. METHODS A cross-sectional study was conducted in the five special districts of South Gondar Zone, among 314 school-age children. WHO AnthroPlus software was used to build Z-scores from anthropometric measurement. The data were analyzed by SPSS Version 20. The degrees of association were assessed using adjusted odds ratio (AOR) and 95% confidence interval during multivariable logistic regression. A P-value less than 0.05 was considered to be statistically significant. RESULTS Of the total study participants, 232 (77.3%) were from public schools. The mean±standard deviation (SD) of height of children was 132.9±9.8 cm, and the mean±SD weight of children was 27.7±5.8 kg. The prevalence of stunting, wasting, and underweight was 11%, 6.3%, and 11.4%, respectively. Students who ate their breakfast rarely were 8-times more likely to be underweight than those who ate their breakfast always (AOR=7.9, 95% CI=4.8-14.8). Those who were sick in the past 2 weeks were more likely to be underweight than their counterparts (AOR=7.3, 95% CI=2.8-14.4). Those who never consume milk or milk products were 6.5 (AOR=6.5, 95% CI=1.7-23) times more likely to be stunted than those who consumed this always. Sickness in the past 2 weeks prior to data collection was significantly associated with thinness (AOR=6 0.9, 95% CI=4.1-10.1). CONCLUSION The overall prevalence of wasting, stunting, and underweight was a mild public health problem in the study area.
Collapse
Affiliation(s)
- Hiwot Yisak
- Department of Public Health, College of Health Sciences, Debre Tabor University, Debre Tabor, Ethiopia
| | - Melaku Tadege
- Department of Public Health, College of Health Sciences, Debre Tabor University, Debre Tabor, Ethiopia
| | - Birhanie Ambaw
- Department of Public Health, College of Health Sciences, Debre Tabor University, Debre Tabor, Ethiopia
| | - Amien Ewunetei
- Department of Pharmacy, College of Health Sciences, Debre Tabor University, Debre Tabor, Ethiopia
| |
Collapse
|
6
|
Djaharu'ddin I. Prediction Formula of Permanent Canine and Premolar Eruption in Mixed Dentition Patients at Universitas Airlangga, Dental Hospital Surabaya, Indonesia. Contemp Clin Dent 2020; 10:105-109. [PMID: 32015651 PMCID: PMC6975001 DOI: 10.4103/ccd.ccd_464_18] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
Abstract
Background The eruption of permanent canine, first and second premolars need to be predicted because they are erupted last, before the eruption of permanent first and second molars, in order to estimate the available space in orthodontic treatment. Aim This study aimed to predict the eruption of permanent canine, first and second premolars in mixed dentition. Materials and Methods A cross sectional clinical observation was conducted in 21 subjects of 13 males nad 8 females with the age range of 8-12 years old. Their panoramic radiographs were used to create a prediction formula of permanent canine and premolars. The independent variables of this research are age, weight, height, birth weight, birth height, period of breastfeeding, and vertical distance of eruption. Data were analyzed by coefficient of multiple correlation followed by multiple linear regression analysis. Results The prediction formula is as follows: Y = -5107 + 1645 X 1 + 078 X 2, where Y is the time of eruption, X 1 is the height, and X 2 is the vertical distance of eruption. Conclusion The prediction formula is useful for serial extraction in orthodontic treatment. It is also useful for forensic odontology, especially in the determination or identification of ages. It is recommended to be implemented in the science of development, especially in orthodontics and forensic odontology.
Collapse
Affiliation(s)
- Irwadi Djaharu'ddin
- Department of Orthodontics, Faculty of Dental Medicine, Universitas Airlangga, Surabaya, Indonesia
| |
Collapse
|
7
|
Šindelářová R, Broukal Z. Polymorphism in sequence of permanent tooth emergence in Czech children. Cent Eur J Public Health 2019; 27:165-169. [DOI: 10.21101/cejph.a5238] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2017] [Accepted: 03/28/2019] [Indexed: 11/15/2022]
|
8
|
Šindelářová R, Žáková L, Broukal Z. Standards for permanent tooth emergence in Czech children. BMC Oral Health 2017; 17:140. [PMID: 29187175 PMCID: PMC5708178 DOI: 10.1186/s12903-017-0427-9] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2017] [Accepted: 11/19/2017] [Indexed: 11/12/2022] Open
Abstract
Background The aim of this study is to develop a population-specific reference for permanent tooth emergence among 4–15 years old Czech Republic children. The reference derived from this sample population are essential for pediatric dental diagnostics, orthodontic treatment planning, as well as anthropological and forensic applications. Methods In this cross-sectional epidemiological survey, dental examinations of 1,370 Czech children (696 girls (50,8%) and 674 boys (49,2%), whose parents or legal guardians all signed informed consent forms) from 11 elementary schools and kindergartens were performed in the classroom. During the examination, previously emerged permanent teeth (other than third molars), the child's age and gender were recorded. A tooth is defined as having erupted when at least any part of the crown penetrates the gingiva, and is clinically seen in the oral cavity. A logistic regression model was used to calculate the median emergence age per tooth for both genders and the total sample. The data was statistically processed (using IBM SPSS Statistics 23) and carried out at a deviation level of 0.05. The statistical significance of the differences in the emergence of permanent teeth (contralateral, intermaxillary, inter-gender differences) was evaluated by the McNemar test. Results No statistically significant differences were observed in the emergence times between right and left sides. In addition, mandibular teeth emerged earlier than the corresponding maxillary ones (with the exception of the first and second premolars). Permanent teeth were found to emerge sooner in girls. Furthermore, the greatest inter-gender difference was observed in maxillary canines. Conclusions The new data reported can now be used as standards when assessing permanent tooth emergence of Czech children.
Collapse
Affiliation(s)
- Romana Šindelářová
- Institute of Dental Medicine, 1st Medical Faculty of Charles University, Prague, Czech Republic.
| | - Lucie Žáková
- Institute of Dental Medicine, 1st Medical Faculty of Charles University, Prague, Czech Republic
| | - Zdeněk Broukal
- Institute of Dental Medicine, 1st Medical Faculty of Charles University, Prague, Czech Republic
| |
Collapse
|
9
|
DuPlessis EA, Araujo EA, Behrents RG, Kim KB. Relationship between body mass and dental and skeletal development in children and adolescents. Am J Orthod Dentofacial Orthop 2017; 150:268-73. [PMID: 27476359 DOI: 10.1016/j.ajodo.2015.12.031] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2014] [Revised: 12/01/2015] [Accepted: 12/01/2015] [Indexed: 11/18/2022]
Abstract
INTRODUCTION The purpose of this investigation was to determine whether a relationship exists between body mass and dental and skeletal development in children and adolescents. A sample of 197 orthodontic patients (82 boys, 115 girls) was selected. Ethnicity was recorded, and body mass index (BMI) was calculated according to the standard equation from the Centers for Disease Control and Prevention, and then a BMI percentile according to sex and age was obtained. The panoramic radiographs were used to calculate the dental ages with an index. The chronologic ages were subtracted from the calculated dental ages to determine a "dental age difference" for each subject. The lateral cephalogram radiographs were analyzed for skeletal development using the cervical vertebral maturation stage method. RESULTS The white population (60%) had an average BMI percentile of 53.6 and was statistically different from the Hispanic/black population (40%), which had an average percentile of 64.3. There were no significant differences for boys and girls for the BMI percentile and dental age difference, or for the BMI percentile and cervical vertebral stages. The multiple regression model showed that BMI percentile and ethnicity were statistically significant explanatory variables for the dental age difference. CONCLUSIONS A relationship exists between body mass and dental and skeletal development. BMI percentile, dental age difference, and cervical vertebral stage are weakly correlated. No significant differences existed between boys and girls in any variables. BMI percentile and ethnicity are weak predictors of the discrepancy between dental age and chronologic age.
Collapse
Affiliation(s)
| | - Eustaquio A Araujo
- Professor, Department of Orthodontics, Saint Louis University, St Louis, Mo
| | - Rolf G Behrents
- Professor, Department of Orthodontics, Saint Louis University, St Louis, Mo
| | - Ki Beom Kim
- Associate professor, Department of Orthodontics, St Louis University, Saint Louis, Mo.
| |
Collapse
|
10
|
Elamin F, Liversidge HM. Malnutrition has no effect on the timing of human tooth formation. PLoS One 2013; 8:e72274. [PMID: 24023614 PMCID: PMC3758289 DOI: 10.1371/journal.pone.0072274] [Citation(s) in RCA: 72] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2013] [Accepted: 07/15/2013] [Indexed: 11/18/2022] Open
Abstract
The effect of nutrition on the timing of human tooth formation is poorly understood. Delays and advancements in dental maturation have all been reported as well as no effect. We investigated the effect of severe malnutrition on the timing of human tooth formation in a large representative sample of North Sudanese children. The sample (1102 males, 1013 females) consisted of stratified randomly selected healthy individuals in Khartoum, Sudan, aged 2-22 years using a cross-sectional design following the STROBE statement. Nutritional status was defined using WHO criteria of height and weight. Body mass index Z-scores and height for age Z-scores of ≤−2 (cut-off) were used to identify the malnourished group (N = 474) while the normal was defined by Z-scores of ≥0 (N = 799). Clinical and radiographic examination of individuals, with known ages of birth was performed including height and weight measurements. Mandibular left permanent teeth were assessed using eight crown and seven root established tooth formation stages. Mean age at entry and mean age within tooth stages were calculated for each available tooth stage in each group and compared using a t-test. Results show the mean age at entry and mean age within tooth stages were not significantly different between groups affected by severe malnutrition and normal children (p>0.05). This remarkable finding was evident across the span of dental development. We demonstrate that there is little measurable effect of sustained malnutrition on the average timing of tooth formation. This noteworthy finding supports the notion that teeth have substantial biological stability and are insulated from extreme nutritional conditions compared to other maturing body systems.
Collapse
Affiliation(s)
- Fadil Elamin
- Queen Mary University of London, Institute of Dentistry, Bart’s and The London School of Medicine and Dentistry, London, United Kingdom
- Khartoum Centre for Research and Medical Training, Qasr Street, Khartoum, Sudan
- El Razi Dental School, Elazhari 2, Khartoum, Sudan
- * E-mail:
| | - Helen M. Liversidge
- Queen Mary University of London, Institute of Dentistry, Bart’s and The London School of Medicine and Dentistry, London, United Kingdom
| |
Collapse
|
11
|
Gaur R, Kumar P. Effect of undernutrition on deciduous tooth emergence among Rajput children of Shimla District of Himachal Pradesh, India. AMERICAN JOURNAL OF PHYSICAL ANTHROPOLOGY 2012; 148:54-61. [DOI: 10.1002/ajpa.22041] [Citation(s) in RCA: 20] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/03/2011] [Accepted: 01/20/2012] [Indexed: 11/10/2022]
|