Short form development for oral health patient-reported outcome evaluation in children and adolescents

Development of short forms for screening children's dental caries and urgent treatment needs using item response theory and machine learning methods

OBJECTIVES

Surveys can assist in screening oral diseases in populations to enhance the early detection of disease and intervention strategies for children in need. This paper aims to develop short forms of child-report and proxy-report survey screening instruments for active dental caries and urgent treatment needs in school-age children.

METHODS

This cross-sectional study recruited 497 distinct dyads of children aged 8-17 and their parents between 2015 to 2019 from 14 dental clinics and private practices in Los Angeles County. We evaluated responses to 88 child-reported and 64 proxy-reported oral health questions to select and calibrate short forms using Item Response Theory. Seven classical Machine Learning algorithms were employed to predict children's active caries and urgent treatment needs using the short forms together with family demographic variables. The candidate algorithms include CatBoost, Logistic Regression, K-Nearest Neighbors (KNN), Naïve Bayes, Neural Network, Random Forest, and Support Vector Machine. Predictive performance was assessed using repeated 5-fold nested cross-validations.

RESULTS

We developed and calibrated four ten-item short forms. Naïve Bayes outperformed other algorithms with the highest median of cross-validated area under the ROC curve. The means of best testing sensitivities and specificities using both child-reported and proxy-reported responses were 0.84 and 0.30 for active caries, and 0.81 and 0.31 for urgent treatment needs respectively. Models incorporating both response types showed a slightly higher predictive accuracy than those relying on either child-reported or proxy-reported responses.

CONCLUSIONS

The combination of Item Response Theory and Machine Learning algorithms yielded potentially useful screening instruments for both active caries and urgent treatment needs of children. The survey screening approach is relatively cost-effective and convenient when dealing with oral health assessment in large populations. Future studies are needed to further leverage the customize and refine the instruments based on the estimated item characteristics for specific subgroups of the populations to enhance predictive accuracy.

Artificial Intelligence Its Uses and Application in Pediatric Dentistry: A Review

In the global epidemic era, oral problems significantly impact a major population of children. The key to a child’s optimal health is early diagnosis, prevention, and treatment of these disorders. In recent years, the field of artificial intelligence (AI) has seen tremendous pace and progress. As a result, AI’s infiltration is witnessed even in those areas that were traditionally thought to be best left to human specialists. The ultimate ability to improve patient care and make precise diagnoses of illnesses has revolutionized the world of healthcare. In the field of dentistry, the competence to execute treatment measures while still providing appropriate patient behavior counseling is in high demand, particularly in the field of pediatric dental care. As a result, we decided to conduct this review specifically to examine the applications of AI models in pediatric dentistry. A comprehensive search of the subjects was done using a wide range of databases to look for studies that have been published in peer-reviewed journals from its inception until 31 December 2022. After the application of the criteria, only 25 of the 351 articles were taken into consideration for this review. According to the literature, AI is frequently used in pediatric dentistry for the purpose of making an accurate diagnosis and assisting clinicians, dentists, and pediatric dentists in clinical decision making, developing preventive strategies, and establishing an appropriate treatment plan.

Quantitative data collection approaches in subject-reported oral health research: a scoping review

Background

This scoping review reports on studies that collect survey data using quantitative research to measure self-reported oral health status outcome measures. The objective of this review is to categorize measures used to evaluate self-reported oral health status and oral health quality of life used in surveys of general populations.

Methods

The review is guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) with the search on four online bibliographic databases. The criteria include (1) peer-reviewed articles, (2) papers published between 2011 and 2021, (3) only studies using quantitative methods, and (4) containing outcome measures of self-assessed oral health status, and/or oral health-related quality of life. All survey data collection methods are assessed and papers whose methods employ newer technological approaches are also identified.

Results

Of the 2981 unduplicated papers, 239 meet the eligibility criteria. Half of the papers use impact scores such as the OHIP-14; 10% use functional measures, such as the GOHAI, and 26% use two or more measures while 8% use rating scales of oral health status. The review identifies four data collection methods: in-person, mail-in, Internet-based, and telephone surveys. Most (86%) employ in-person surveys, and 39% are conducted in Asia-Pacific and Middle East countries with 8% in North America. Sixty-six percent of the studies recruit participants directly from clinics and schools, where the surveys were carried out. The top three sampling methods are convenience sampling (52%), simple random sampling (12%), and stratified sampling (12%). Among the four data collection methods, in-person surveys have the highest response rate (91%), while the lowest response rate occurs in Internet-based surveys (37%). Telephone surveys are used to cover a wider population compared to other data collection methods. There are two noteworthy approaches: 1) sample selection where researchers employ different platforms to access subjects, and 2) mode of interaction with subjects, with the use of computers to collect self-reported data.

Conclusion

The study provides an assessment of oral health outcome measures, including subject-reported oral health status and notes newly emerging computer technological approaches recently used in surveys conducted on general populations. These newer applications, though rarely used, hold promise for both researchers and the various populations that use or need oral health care.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12903-022-02399-5.

Investigating Perceptions of Teachers and School Nurses on Child and Adolescent Oral Health in Los Angeles County

This study reports the results of focus groups with school nurses and teachers from elementary, middle, and high schools to explore their perceptions of child and adolescent oral health. Participants included 14 school nurses and 15 teachers (83% female; 31% Hispanic; 21% White; 21% Asian; 14% African American; and 13% Others). Respondents were recruited from Los Angeles County schools and scheduled by school level for six one-hour focus groups using Zoom. Audio recordings were transcribed, reviewed, and saved with anonymization of speaker identities. NVivo software (QSR International, Melbourne, Australia) was used to facilitate content analysis and identify key themes. The nurses’ rate of “Oral Health Education” comments statistically exceeded that of teachers, while teachers had higher rates for “Parental Involvement” and “Mutual Perception” comments. “Need for Care” was perceived to be more prevalent in immigrants to the United States based on student behaviors and complaints. “Access to Care” was seen as primarily the nurses’ responsibilities. Strong relationships between community clinics and schools were viewed by some as integral to students achieving good oral health. The results suggest dimensions and questions important to item development for oral health surveys of children and parents to address screening, management, program assessment, and policy planning.

Dimensional Structure of the Early Childhood Oral Health Impact Scale

Background:

Detecting the latent dimensions of quality of life as affected by oral diseases is essential for promoting oral health in children. This study aimed to test the Early Childhood Oral Health Impact Scale (ECOHIS) via an appropriate method to detect its dimensions of quality of life as affected by oral diseases.

Methods:

An analytical cross-sectional study was carried out in Shiraz, Iran, between 2014 and 2015. A multistage stratified design was used to select 830 parents or the guardians of primary school children aged six years. The Farsi version of the Early Childhood Oral Health Impact Scale (F-ECOHIS) was used to evaluate the children’s oral health-related quality of life. The parents were interviewed to collect data on ECOHIS. Mplus, version 7, was employed for descriptive and analytical analyses in the present study. Exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) were performed to extract and verify the latent dimensions of ECOHIS.

Results:

Out of the 830 invited parents or guardians, 801 participated in this study. The mean ECOHIS score was 21.95±7.45. The mean child impact score and the mean family impact score were 14.25±5.72 and 7.70±3.62, respectively. EFA yielded a 3-factor model: symptom and function, social interaction, and family impact. CFA confirmed the 3-dimensional model (root mean square error of approximation=0.045). The fit indices of the 1- and 2-dimensional models (the child and family domains) were not within the acceptable range.

Conclusion:

F-ECOHIS is a 3-dimensional model rather than the hypothetical 6-dimensional model. ECOHIS appears to be a useful scale for measuring the multidimensional impact of oral diseases in children.

Computerized adaptive testing and short form development for child and adolescent oral health patient-reported outcomes measurement

OBJECTIVES

To develop computerized adaptive testing (CAT) and short forms of self-report oral health measures that are predictive of both the children's oral health status index (COHSI) and the children's oral health referral recommendation (COHRR) scales, for children and adolescents, ages 8-17.

MATERIAL AND METHODS

Using final item calibration parameters (discrimination and difficulty parameters) from the item response theory analysis, we performed post hoc CAT simulation. Items most frequently administered in the simulation were incorporated for possible inclusion in final oral health assessment toolkits, to select the best performing eight items for COHSI and COHRR.

RESULTS

Two previously identified unidimensional sets of self-report items consisting of 19 items for the COHSI and 22 items for the COHRR were administered through CAT resulting in eight-item short forms for both the COHSI and COHRR. Correlations between the simulated CAT scores and the full item bank representing the latent trait are r = .94 for COHSI and r = .96 for COHRR, respectively, which demonstrated high reliability of the CAT and short form.

CONCLUSIONS

Using established rigorous measurement development standards, the CAT and corresponding eight-item short form items for COHSI and COHRR were developed to assess the oral health status of children and adolescents, ages 8-17. These measures demonstrated good psychometric properties and can have clinical utility in oral health screening and evaluation and clinical referral recommendations.

Developing Children's Oral Health Assessment Toolkits Using Machine Learning Algorithm

OBJECTIVES

Evaluating children's oral health status and treatment needs is challenging. We aim to build oral health assessment toolkits to predict Children's Oral Health Status Index (COHSI) score and referral for treatment needs (RFTN) of oral health. Parent and Child toolkits consist of short-form survey items (12 for children and 8 for parents) with and without children's demographic information (7 questions) to predict the child's oral health status and need for treatment.

METHODS

Data were collected from 12 dental practices in Los Angeles County from 2015 to 2016. We predicted COHSI score and RFTN using random Bootstrap samples with manually introduced Gaussian noise together with machine learning algorithms, such as Extreme Gradient Boosting and Naive Bayesian algorithms (using R). The toolkits predicted the probability of treatment needs and the COHSI score with percentile (ranking). The performance of the toolkits was evaluated internally and externally by residual mean square error (RMSE), correlation, sensitivity and specificity.

RESULTS

The toolkits were developed based on survey responses from 545 families with children aged 2 to 17 y. The sensitivity and specificity for predicting RFTN were 93% and 49% respectively with the external data. The correlation(s) between predicted and clinically determined COHSI was 0.88 (and 0.91 for its percentile). The RMSEs of the COHSI toolkit were 4.2 for COHSI (and 1.3 for its percentile).

CONCLUSIONS

Survey responses from children and their parents/guardians are predictive for clinical outcomes. The toolkits can be used by oral health programs at baseline among school populations. The toolkits can also be used to quantify differences between pre- and post-dental care program implementation. The toolkits' predicted oral health scores can be used to stratify samples in oral health research.

KNOWLEDGE TRANSFER STATEMENT

This study creates the oral health toolkits that combine self- and proxy- reported short forms with children's demographic characteristics to predict children's oral health and treatment needs using Machine Learning algorithms. The toolkits can be used by oral health programs at baseline among school populations to quantify differences between pre and post dental care program implementation. The toolkits can also be used to stratify samples according to the treatment needs and oral health status.

Development of toolkits for detecting dental caries and caries experience among children using self-report and parent report

OBJECTIVES

To develop child- and parent-reported toolkits for active caries and caries experience in children and adolescents, ages 8-17.

METHODS

A sample of 398 child/parent dyads recruited from 12 dental practices in Los Angeles County completed a computer-assisted survey that assessed oral health perceptions. In addition, children received a dental examination that identified the presence or absence of active caries and caries experience. A Multiple Adaptive Regression Splines model was used to identify a subset of survey items associated with active caries and caries experience. The splines and coefficients were refined by generalized cross-validation. Sensitivity and specificity for both dependent variables were evaluated.

RESULTS

Eleven child self-reported items were identified that had sensitivity of 0.82 and specificity of 0.45 relative to active caries. Twelve parent-reported items had a sensitivity of 0.86 and specificity of 0.50. Seven child self-reported items had a sensitivity of 0.86 and specificity of 0.34, and 11 parent-reported items had a sensitivity of 0.86 and specificity of 0.47 for caries experience.

CONCLUSIONS

The survey items identified here are useful in distinguishing children with and without active caries and with and without caries experience. This research presents a path towards using children's and their parents' reports about oral health to screen for clinically determined caries and caries exposure. The items identified in this study can be useful when clinical information is unavailable.

Development of a parents' short form survey of their children's oral health

BACKGROUND

Parents play an important role in their children's oral health behaviors, provide oral health access, initiate prevention, and coping strategies for health care.

AIM

This paper develops a short form (SF) to assist parents to evaluate their children's oral health status using Patient-Reported Outcome Measurement Information System (PROMIS) framework that conceptualized health as physical, mental, and social components.

DESIGN

Surveys of parents were conducted at dental clinics in Los Angeles County, together with an on-site clinical examination by dentists to determine clinical outcomes, Children's Oral Health Status Index (COHSI), and referral recommendations (RRs). Graded response models in item response theory were used to create the SF. A toolkit including SF, demographic information, and algorithms was developed to predict the COHSI and RRs.

RESULTS

The final SF questionnaire consists of eight items. The square root mean squared error for the prediction of COHSI is 7.6. The sensitivity and specificity of using SF to predict immediate treatment needs (binary RRs) are 85% and 31%.

CONCLUSIONS

The parent SF is an additional component of the oral health evaluation toolkit that can be used for oral health screening, surveillance program, policy planning, and research of school-aged children and adolescents from guardian perspectives.