Importance of socioeconomic factors in predicting tooth loss among older adults in Japan: Evidence from a machine learning analysis

Childhood Socioeconomic Status Affects Dental Pain in Later Life

OBJECTIVES

Lower socioeconomic status (SES) is associated with increased dental pain among children. Lower SES in childhood may also contribute to the experience of dental pain among older adults, regardless of the SES in later life. However, this association is still unclear.

METHODS

We used cross-sectional data from the 2019 Japan Gerontological Evaluation Study using self-administrated questionnaires to investigate the causal mediating pathways between childhood SES and dental pain in later life using several SES variables collected at older age as potential mediators. A total of 21,212 physically and cognitively independent participants aged 65 y or older were included in the analysis. The dependent variable was experiencing dental pain during the past 6 mo. The independent variable was the SES at the age of 15 y (low/middle/high). Ten covariates were selected covering demographics and other domains. Education, subjective current income, objective current income, objective current property ownership, and the number of remaining teeth were used as mediators. Prevalence ratios (PRs) and 95% confidence intervals (95% CIs) for dental pain by childhood SES were calculated using a modified Poisson regression model.

RESULTS

The mean age of the study participants was 74.5 ± 6.2 y, and 47.5% were men. Of these, 6,222 participants (29.3%) experienced dental pain during the past 6 mo, and 8,537 participants (40.2%) were of low childhood SES. Adjusted for covariates and mediators, the participants with middle and high childhood SES had a lower PR of dental pain (PR = 0.93 [95%, CI 0.89-0.98], PR = 0.79 [95% CI, 0.73-0.85], respectively). Almost 40% of the association between childhood SES and dental pain at older age was mediated via SES in later life and the number of teeth.

CONCLUSIONS

This study reemphasizes the importance of support for early-life SES to maintain favorable oral health outcomes at an older age.

KNOWLEDGE TRANSFER STATEMENT

The results of this study can be used by policymakers to promote policies based on a life-course approach that supports children living in communities with low SES and helps them maintain favorable oral health outcomes into their older age.

Research trends in lung cancer and the tumor microenvironment: a bibliometric analysis of studies published from 2014 to 2023

Background

Lung cancer (LC) is one of the most common malignant tumors in the world and the leading cause of cancer-related deaths, which seriously threatens human life and health as well as brings a heavy burden to the society. In recent years, the tumor microenvironment (TME) has become an emerging research field and hotspot affecting tumor pathogenesis and therapeutic approaches. However, to date, there has been no bibliometric analysis of lung cancer and the tumor microenvironment from 2014 to 2023.This study aims to comprehensively summarize the current situation and development trends in the field from a bibliometric perspective.

Methods

The publications about lung cancer and the tumor microenvironment from 2014 to 2023 were extracted from the Web of Science Core Collection (WoSCC). The Microsoft Excel, Origin, R-bibliometrix, CiteSpace, and VOSviewer software are comprehensively used to scientifically analyze the data.

Results

Totally, 763 publications were identified in this study. A rapid increase in the number of publications was observed after 2018. More than 400 organizations published these publications in 36 countries or regions. China and the United States have significant influence in this field. Zhou, CC and Frontiers in Immunology are the most productive authors and journals respectively. Besides, the most frequently cited references were those on lung cancer pathogenesis, clinical trials, and treatment modalities. It suggests that novel lung cancer treatment models mainly based on the TME components, such as cancer-associated fibroblasts (CAFs) may lead to future research trends.

Conclusions

The field of lung cancer and the tumor microenvironment research is still in the beginning stages. Gene expression, molecular pathways, therapeutic modalities, and novel detection technologies in this field have been widely studied by researchers. This is the first bibliometric study to comprehensively summarize the research trend and development regarding lung cancer and tumor microenvironment over the last decade. The result of our research provides the updated perspective for scholars to understand the key information and cutting-edge hotspots in this field, as well as to identify future research directions.

Relationship between the number of lost teeth and the occurrence of depressive symptoms in middle-aged adults: a cross-sectional study

BACKGROUND

Many recent studies suggest the existence of a relationship between oral health and the occurrence of depressive symptoms. The aim of this study was to assess the relationship between the number of lost teeth and the occurrence of depressive symptoms in middle-aged adults.

METHODS

An analysis was performed on the data obtained from the PONS project (POlish-Norwegian Study), conducted in the Świętokrzyskie Province in Poland in 2010-2011. The research material included the cross-sectional data of 11,901 individuals aged 40-64 years (7967 women). Depressive symptoms, used as outcome variables, were assessed with a questionnaire. The participants provided the responses to questions concerning the occurrence of eight symptoms over the last 12 months. The answers were scored as 1 point or 0 points. The participants were divided into three tercile groups based on their total scores: no or mild (0-2 points), moderate (3-5 points), and severe depressive symptoms (6-8 points). The self-reported number of lost teeth was analysed according to the following categories: 0-4, 5-8, 9-27, and a complete lack of natural teeth. Multivariable logistic regression analysis for depressive symptoms was used in relation to the number of lost teeth. The following covariates were included in the adjusted model: age, sex, place of residence, education, marital status, BMI, diabetes status, stressful life events in the last year, use of antidepressants, smoking, and sugar and sweet consumption.

RESULTS

The likelihood of both moderate (OR = 1.189; 95%CI: 1.028-1.376; p < .020) and severe (OR = 1.846; 95%CI: 1.488-2.290; p < .001) depressive symptoms showed the strongest relationship with a total lack of natural teeth. A loss of more than 8 natural teeth was also significantly associated (OR = 1.315; 95%CI: 1.075-1.609; p < .008) with the occurrence of severe depressive symptoms.

CONCLUSIONS

The loss of natural teeth was positively related to the occurrence of depressive symptoms in middle-aged adults. Thus, there is an urgent need to intensify stomatological prophylaxis, education and treatment for middle-aged individuals.

Identifying predictors of the tooth loss phenotype in a large periodontitis patient cohort using a machine learning approach

OBJECTIVES

This study aimed to identify predictors associated with the tooth loss phenotype in a large periodontitis patient cohort in the university setting.

METHODS

Information on periodontitis patients and nineteen factors identified at the initial visit was extracted from electronic health records. The primary outcome is tooth loss phenotype (presence or absence of tooth loss). Prediction models were built on significant factors (single or combinatory) selected by the RuleFit algorithm, and these factors were further adopted by regression models. Model performance was evaluated by Area Under the Receiver Operating Characteristic Curve (AUROC) and Area Under the Precision-Recall Curve (AUPRC). Associations between predictors and the tooth loss phenotype were also evaluated by classical statistical approaches to validate the performance of machine learning models.

RESULTS

In total, 7840 patients were included. The machine learning model predicting the tooth loss phenotype achieved AUROC of 0.71 and AUPRC of 0.66. Age, periodontal diagnosis, number of missing teeth at baseline, furcation involvement, and tooth mobility were associated with the tooth loss phenotype in both machine learning and classical statistical models.

CONCLUSIONS

The rule-based machine learning approach improves model explainability compared to classical statistical methods. However, the model's generalizability needs to be further validated by external datasets.

CLINICAL SIGNIFICANCE

Predictors identified by the current machine learning approach using the RuleFit algorithm had clinically relevant thresholds in predicting the tooth loss phenotype in a large and diverse periodontitis patient cohort. The results of this study will assist clinicians in performing risk assessment for periodontitis at the initial visit.

Trend in the Incidence of Severe Partial Edentulism among Adults Using the Korean National Health Insurance Service Claim Data, 2014-2018

PURPOSE

Missing teeth is one of the most important indicators of oral health behavior and the result of dental caries, periodontal disease, and injuries. This study examined a trend in the incidence of severe partial edentulism (SPE) using the Korean National Health Insurance Service (KNHIS) data.

MATERIALS AND METHODS

Data of adults aged ≥20 years were obtained from the KNHIS for the 2014-2018 period. SPE was defined in dental information within a population with a treatment history of dental scaling as having 1 to 8 natural teeth. Crude incidence rates (CIRs) and age-standardized incidence rates (AIRs) with 95% confidence interval were calculated per 100000 persons. The Cochran Armitage trend (CAT) test and average annual percentage change were used to analyze SPE trends.

RESULTS

The CIRs among Korean adults were from 346.29 to 391.11 in 2014-2016 and from 391.11 to 354.09 in 2016-2018. The AIRs trend statistically increased by 4.31% from 346.29 to 376.80 and decreased by 4.72% from 376.80 to 342.10. The AIRs in men increased by 4.00% and decreased by 3.01%. The AIRs in women decreased by 2.18% and increased by 2.11% (CAT; p<0.01). The AIRs by region and income also showed trends of increase and decrease.

CONCLUSION

The study showed that the incidence trend of SPE increased and decreased from 2014 to 2018. This result would be able to aid in the planning of public oral health, and may also serve as fundamental data for verifying the impact of the public oral health policies implemented.

Machine learning to predict untreated dental caries in adolescents

OBJECTIVE

This study aimed to predict adolescents with untreated dental caries through a machine-learning approach using three different algorithms METHODS: Data came from an epidemiological survey in the five largest cities in Mato Grosso do Sul, Brazil. Data on sociodemographic characteristics, consumption of unhealthy foods and behaviours (use of dental floss and toothbrushing) were collected using Sisson's theoretical model, in 615 adolescents. For the machine learning, three different algorithms were used: (1) XGboost; (2) decision tree and (3) logistic regression. The epidemiological baseline was used to train and test predictions to detect individuals with untreated dental caries, through eight main predictor variables. Analyzes were performed using the R software (R Foundation for Statistical Computing, Vienna, Austria). The Ethics Committee approved the study..

RESULTS

For the 615 adolescents, xgboost performed better with an area under the curve (AUC) of 84% versus 81% for the decision tree algorithm. The most important variables were the use of dental floss, unhealthy food consumption, self-declared race and exposure to fluoridated water.

CONCLUSIONS

Family health teams can improve the work process and use artificial intelligence mechanisms to predict adolescents with untreated dental caries, and, in this way, schedule dental appointments for the treatment of adolescents earlier.

Application of machine learning in measurement of ageing and geriatric diseases: a systematic review

BACKGROUND

As the ageing population continues to grow in many countries, the prevalence of geriatric diseases is on the rise. In response, healthcare providers are exploring novel methods to enhance the quality of life for the elderly. Over the last decade, there has been a remarkable surge in the use of machine learning in geriatric diseases and care. Machine learning has emerged as a promising tool for the diagnosis, treatment, and management of these conditions. Hence, our study aims to find out the present state of research in geriatrics and the application of machine learning methods in this area.

METHODS

This systematic review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and focused on healthy ageing in individuals aged 45 and above, with a specific emphasis on the diseases that commonly occur during this process. The study mainly focused on three areas, that are machine learning, the geriatric population, and diseases. Peer-reviewed articles were searched in the PubMed and Scopus databases with inclusion criteria of population above 45 years, must have used machine learning methods, and availability of full text. To assess the quality of the studies, Joanna Briggs Institute's (JBI) critical appraisal tool was used.

RESULTS

A total of 70 papers were selected from the 120 identified papers after going through title screening, abstract screening, and reference search. Limited research is available on predicting biological or brain age using deep learning and different supervised machine learning methods. Neurodegenerative disorders were found to be the most researched disease, in which Alzheimer's disease was focused the most. Among non-communicable diseases, diabetes mellitus, hypertension, cancer, kidney diseases, and cardiovascular diseases were included, and other rare diseases like oral health-related diseases and bone diseases were also explored in some papers. In terms of the application of machine learning, risk prediction was the most common approach. Half of the studies have used supervised machine learning algorithms, among which logistic regression, random forest, XG Boost were frequently used methods. These machine learning methods were applied to a variety of datasets including population-based surveys, hospital records, and digitally traced data.

CONCLUSION

The review identified a wide range of studies that employed machine learning algorithms to analyse various diseases and datasets. While the application of machine learning in geriatrics and care has been well-explored, there is still room for future development, particularly in validating models across diverse populations and utilizing personalized digital datasets for customized patient-centric care in older populations. Further, we suggest a scope of Machine Learning in generating comparable ageing indices such as successful ageing index.

Last dental visit and severity of tooth loss: a machine learning approach

The aims of the present study were to investigate last dental visit as a mediator in the relationship between socioeconomic status and lack of functional dentition/severe tooth loss and use a machine learning approach to predict those adults and elderly at higher risk of tooth loss. We analyzed data from a representative sample of 88,531 Brazilian individuals aged 18 and over. Tooth loss was the outcome by; (1) functional dentition and (2) severe tooth loss. Structural Equation models were used to find the time of last dental visit associated with the outcomes. Moreover, machine learning was used to train and test predictions to target individuals at higher risk for tooth loss. For 65,803 adults, more than two years of last dental visit was associated with lack of functional dentition. Age was the main contributor in the machine learning approach, with an AUC of 90%, accuracy of 90%, specificity of 97% and sensitivity of 38%. For elders, the last dental visit was associated with higher severe loss. Conclusions. More than two years of last dental visit appears to be associated with a severe loss and lack of functional dentition. The machine learning approach had a good performance to predict those individuals.

Identifying predictors of tooth loss using a rule-based machine learning approach: A retrospective study at university-setting clinics

BACKGROUND

This study aimed to identify predictors associated with tooth loss in a large periodontitis patient cohort in the university setting using the machine learning approach.

METHODS

Information on periodontitis patients and 18 factors identified at the initial visit was extracted from electronic health records. A two-step machine learning pipeline was proposed to develop the tooth loss prediction model. The primary outcome is tooth loss count. The prediction model was built on significant factors (single or combination) selected by the RuleFit algorithm, and these factors were further adopted by the count regression model. Model performance was evaluated by root-mean-squared error (RMSE). Associations between predictors and tooth loss were also assessed by a classical statistical approach to validate the performance of the machine learning model.

RESULTS

In total, 7840 patients were included. The machine learning model predicting tooth loss count achieved RMSE of 2.71. Age, smoking, frequency of brushing, frequency of flossing, periodontal diagnosis, bleeding on probing percentage, number of missing teeth at baseline, and tooth mobility were associated with tooth loss in both machine learning and classical statistical models.

CONCLUSION

The two-step machine learning pipeline is feasible to predict tooth loss in periodontitis patients. Compared to classical statistical methods, this rule-based machine learning approach improves model explainability. However, the model's generalizability needs to be further validated by external datasets.

Prediction Model Development and Validation of 12-Year Incident Edentulism of Older Adults in the United States

INTRODUCTION

Edentulism affects health and quality of life.

OBJECTIVES

Identify factors that predict older adults becoming edentulous over 12 y in the US Health and Retirement Study (HRS) by developing and validating a prediction model.

METHODS

The HRS includes data on a representative sample of US adults aged >50 y. Selection criteria included participants in 2006 and 2018 who answered, "Have you lost all of your upper and lower natural permanent teeth?" Persons who answered "no" in 2006 and "yes" in 2018 experienced incident edentulism. Excluding 2006 edentulous, the data set (n = 4,288) was split into selection (70%, n = 3,002) and test data (30%, n = 1,286), and Monte Carlo cross-validation was applied to 500 random partitions of the selection data into training (n = 1,716) and validation (n = 1,286) data sets. Fitted logistic models from the training data sets were applied to the validation data sets to obtain area under the curve (AUC) for 32 candidate models. Six variables were included in all models (age, race/ethnicity, gender, education, smoking, last dental visit) while all combinations of 5 variables (income, alcohol use, self-rated health, loneliness, cognitive status) were considered for inclusion. The best parsimonious model based on highest mean AUC was fitted to the selection data set to obtain a final prediction equation. It was applied to the test data to estimate AUC and 95% confidence interval using 1,000 bootstrap samples.

RESULTS

From 2006 to 2018, 9.7% of older adults became edentulous. The 2006 mean (SD) age was 66.7 (8.7) for newly edentulous and 66.3 (8.4) for dentate (P = 0.31). The baseline 6-variable model mean AUC was 0.740. The 7-variable model with cognition had AUC = 0.749 and test data AUC = 0.748 (95% confidence interval, 0.715-0.781), modestly improving prediction. Negligible improvement was gained from adding more variables.

CONCLUSION

Cognition information improved the 12-y prediction of becoming edentulous beyond the modifiable risk factors of smoking and dental care use, as well as nonmodifiable demographic factors.

KNOWLEDGE TRANSFER STATEMENT

This prediction modeling and validation study identifies cognition as well as modifiable (dental care use, smoking) and nonmodifiable factors (race, ethnicity, gender, age, education) associated with incident complete tooth loss in the United States. This information is useful for the public, dental care providers, and health policy makers in improving approaches to preventive care, oral and general health, and quality of life for older adults.

Using machine learning to study the association of sociodemographic indicators, biomarkers, and oral condition in older adults in Colombia

BACKGROUND

Chronic health conditions and socioeconomic problems that affect the well-being and life expectancy of older adults are common. The objective of this cross-sectional study was to analyze the association between sociodemographic variables, oral conditions, and general health and the biomarkers of older adults using machine learning (ML).

METHODS

A total of 15,068 surveys from the national study of Health, Well-Being and Aging (Salud, Bienestar y Envejecimiento) data set were used for this secondary analysis. Of these, 3,128 people provided blood samples for the analysis of blood biomarkers. Sociodemographic, oral health, and general health variables were analyzed using ML and logistic regression.

RESULTS

The results of clustering analysis showed that dyslipidemia was associated with poor oral condition, lower socioeconomic status, being female, and low education. The self-perception of oral health in older adults was not associated with the presence of teeth, blood biomarkers, or socioeconomic variables. However, the necessity of replacing a dental prosthesis was associated with the lowest self-perception of oral health. Edentulism was associated with being female, increased age, and smoking.

CONCLUSIONS

Socioeconomic and educational disparities, sex, and smoking are important factors for tooth loss and suboptimal blood biomarkers in older adults. ML is a powerful tool for identifying potential variables that may aid in the prevention of systemic and oral diseases in older adults, which would improve geriatric dentistry.

PRACTICAL IMPLICATIONS

These findings can help the academic community identify critical sociodemographic and clinical factors that influence the process of healthy aging and serve as a useful guide to enhance health care policies and geriatric oral health care services.

Demand prediction of medical services in home and community-based services for older adults in China using machine learning

Background

Home and community-based services are considered an appropriate and crucial caring method for older adults in China. However, the research examining demand for medical services in HCBS through machine learning techniques and national representative data has not yet been carried out. This study aimed to address the absence of a complete and unified demand assessment system for home and community-based services.

Methods

This was a cross-sectional study conducted on 15,312 older adults based on the Chinese Longitudinal Healthy Longevity Survey 2018. Models predicting demand were constructed using five machine-learning methods: Logistic regression, Logistic regression with LASSO regularization, Support Vector Machine, Random Forest, and Extreme Gradient Boosting (XGboost), and based on Andersen's behavioral model of health services use. Methods utilized 60% of older adults to develop the model, 20% of the samples to examine the performance of models, and the remaining 20% of cases to evaluate the robustness of the models. To investigate demand for medical services in HCBS, individual characteristics such as predisposing, enabling, need, and behavior factors constituted four combinations to determine the best model.

Results

Random Forest and XGboost models produced the best results, in which both models were over 80% at specificity and produced robust results in the validation set. Andersen's behavioral model allowed for combining odds ratio and estimating the contribution of each variable of Random Forest and XGboost models. The three most critical features that affected older adults required medical services in HCBS were self-rated health, exercise, and education.

Conclusion

Andersen's behavioral model combined with machine learning techniques successfully constructed a model with reasonable predictors to predict older adults who may have a higher demand for medical services in HCBS. Furthermore, the model captured their critical characteristics. This method predicting demands could be valuable for the community and managers in arranging limited primary medical resources to promote healthy aging.

Education-related inequalities in oral health among older adults: Comparing Singapore and Japan

OBJECTIVES

Oral health inequalities exist worldwide, and cross-country comparisons can provide valuable insights into country-level characteristics contributing to such inequalities. However, comparative studies in Asian countries are limited. This study examined the magnitude of education-related oral health inequalities in older adults in Singapore and Japan.

METHODS

Longitudinal data for older adults, aged ≥65 years, from the Panel on Health and Ageing of Singaporean Elderly (PHASE; 2009, 2011-2012, and 2015) and Japan Gerontological Evaluation Study (JAGES; 2010, 2013, and 2016) were used. Dependent variables were being edentate and having a minimal functional dentition (MFD; i.e. ≥20 teeth). The absolute and relative inequalities were calculated using the slope index of inequality (SII) and relative index of inequality (RII) for educational level [low (<6 years); middle (6-12 years); high (>12 years)] in each country.

RESULTS

A total of 1032 PHASE participants and 35 717 JAGES participants were included. At baseline among PHASE participants, 35.9% were edentate and 24.4% had MFD, while among JAGES participants, 8.5% were edentate and 42.4% had MFD. The prevalence of low, middle and high educational levels for PHASE was 76.5%, 18.0% and 5.5%, and for JAGES were 0.9%, 78.1% and 19.7%, respectively. Older adults in Japan had lower education-related inequalities for being edentate [for both SII (-0.53, 95% CI = -0.55 to -0.50) and RII (0.40, 95% CI = 0.33-0.48)] and for not having MFD for both SII (-0.24, 95% CI = -0.27 to -0.20) and RII (0.83, 95% CI = 0.79-0.87) compared to Singapore.

CONCLUSIONS

Education-related inequalities for being edentate and not having MFD were higher among older adults in Singapore compared to Japan.

Finite element analysis of stress in oral mucosa and titanium mesh interface

BACKGROUND

The stiffness of titanium mesh is a double-blade sword to repair larger alveolar ridges defect with excellent space maintenance ability, while invade the surrounding soft tissue and lead to higher mesh exposure rates. Understanding the mechanical of oral mucosa/titanium mesh/bone interface is clinically meaningful. In this study, the above relationship was analyzed by finite elements and verified by setting different keratinized tissue width in oral mucosa.

METHODS

Two three-dimensional finite element models were constructed with 5 mm keratinized tissue in labial mucosa (KM cases) and 0 mm keratinized tissue in labial mucosa (LM cases). Each model was composed of titanium mesh, titanium screws, graft materials, bone, teeth and oral mucosa. After that, a vertical (30 N) loadings were applied from both alveolar ridges direction and labial mucosa direction to stimulate the force from masticatory system. The displacements and von Mises stress of each element at the interfaces were analyzed.

RESULTS

Little displacements were found for titanium mesh, titanium screws, graft materials, bone and teeth in both LM and KM cases under different loading conditions. The maximum von Mises stress was found around the lingual titanium screw insertion place for those elements in all cases. The keratinized tissue decreased the displacement of oral mucosa, decreased the maximum von Mises stress generated by an alveolar ridges direction load, while increased those stress from labial mucosa direction load. Only the von Mises stress of the KM cases was all lower than the tensile strength of the oral mucosa.

CONCLUSION

The mucosa was vulnerable under the increasing stress generated by the force from masticatory system. The adequate buccal keratinized mucosa width are critical factors in reducing the stress beyond the titanium mesh, which might reduce the titanium exposure rate.

Machine Learning in Predicting Tooth Loss: A Systematic Review and Risk of Bias Assessment

Predicting tooth loss is a persistent clinical challenge in the 21st century. While an emerging field in dentistry, computational solutions that employ machine learning are promising for enhancing clinical outcomes, including the chairside prognostication of tooth loss. We aimed to evaluate the risk of bias in prognostic prediction models of tooth loss that use machine learning. To do this, literature was searched in two electronic databases (MEDLINE via PubMed; Google Scholar) for studies that reported the accuracy or area under the curve (AUC) of prediction models. AUC measures the entire two-dimensional area underneath the entire receiver operating characteristic (ROC) curves. AUC provides an aggregate measure of performance across all possible classification thresholds. Although both development and validation were included in this review, studies that did not assess the accuracy or validation of boosting models (AdaBoosting, Gradient-boosting decision tree, XGBoost, LightGBM, CatBoost) were excluded. Five studies met criteria for inclusion and revealed high accuracy; however, models displayed a high risk of bias. Importantly, patient-level assessments combined with socioeconomic predictors performed better than clinical predictors alone. While there are current limitations, machine-learning-assisted models for tooth loss may enhance prognostication accuracy in combination with clinical and patient metadata in the future.

Prediction of mortality risk of health checkup participants using machine learning-based models: the J-SHC study

Early detection and treatment of diseases through health checkups are effective in improving life expectancy. In this study, we compared the predictive ability for 5-year mortality between two machine learning-based models (gradient boosting decision tree [XGBoost] and neural network) and a conventional logistic regression model in 116,749 health checkup participants. We built prediction models using a training dataset consisting of 85,361 participants in 2008 and evaluated the models using a test dataset consisting of 31,388 participants from 2009 to 2014. The predictive ability was evaluated by the values of the area under the receiver operating characteristic curve (AUC) in the test dataset. The AUC values were 0.811 for XGBoost, 0.774 for neural network, and 0.772 for logistic regression models, indicating that the predictive ability of XGBoost was the highest. The importance rating of each explanatory variable was evaluated using the SHapley Additive exPlanations (SHAP) values, which were similar among these models. This study showed that the machine learning-based model has a higher predictive ability than the conventional logistic regression model and may be useful for risk assessment and health guidance for health checkup participants.

An Application of Machine Learning Techniques to Analyze Patient Information to Improve Oral Health Outcomes

Objective

Various health-related fields have applied Machine learning (ML) techniques such as text mining, topic modeling (TM), and artificial neural networks (ANN) to automate tasks otherwise completed by humans to enhance patient care. However, research in dentistry on the integration of these techniques into the clinic arena has yet to exist. Thus, the purpose of this study was to: introduce a method of automating the reviewing patient chart information using ML, provide a step-by-step description of how it was conducted, and demonstrate this method's potential to identify predictive relationships between patient chart information and important oral health-related contributors.

Methods

A secondary data analysis was conducted to demonstrate the approach on a set of anonymized patient charts collected from a dental clinic. Two ML applications for patient chart review were demonstrated: (1) text mining and Latent Dirichlet Allocation (LDA) were used to preprocess, model, and cluster data in a narrative format and extract common topics for further analysis, (2) Ordinal logistic regression (OLR) and ANN were used to determine predictive relationships between the extracted patient chart data topics and oral health-related contributors. All analysis was conducted in R and SPSS (IBM, SPSS, statistics 22).

Results

Data from 785 patient charts were analyzed. Preprocessing of raw data (data cleaning and categorizing) identified 66 variables, of which 45 were included for analysis. Using LDA, 10 radiographic findings topics and 8 treatment planning topics were extracted from the data. OLR showed that caries risk, occlusal risk, biomechanical risk, gingival recession, periodontitis, gingivitis, assisted mouth opening, and muscle tenderness were highly predictable using the extracted radiographic and treatment planning topics and chart information. Using the statistically significant predictors obtained from OLR, ANN analysis showed that the model can correctly predict &gt;72% of all variables except for bruxism and tooth crowding (63.1 and 68.9%, respectively).

Conclusion

Our study presents a novel approach to address the need for data-enabled innovations in the field of dentistry and creates new areas of research in dental analytics. Utilizing ML methods and its application in dental practice has the potential to improve clinicians' and patients' understanding of the major factors that contribute to oral health diseases/conditions.