Predictors of tooth loss: A machine learning approach

Development of a Predictive Model for Chewing Difficulty Using EuroQol-5 Dimension Among Korean Older Adults

OBJECTIVES

We aimed to develop a predictive model for chewing difficulty using the EuroQol-5 dimension measure (EQ-5D).

METHODS

We included 6643 individuals aged ≥ 65 years (mean age: 72.6 ± 4.96 years; women: 3761 [56.6%]) who had completed the sixth (2013-2015) and seventh (2016-2018) Korea National Health and Nutrition Examination Survey (KNHANES). The participants were further divided into young-old (65-74 years) and old-old (≥ 75 years) adults. Data from the sixth KNHANES were used to establish an internal validation model (overall, young-old and old-old adult populations were 3472, 2271 and 1201, respectively). Data from the seventh KNHANES were used to establish an external validation model (overall, young-old and old-old adult populations were 3171, 1879 and 1292 participants, respectively). We evaluated chewing difficulty using the EQ-5D (Model 1) and comparative models, subjective oral health status indicators (SOHSI) and objective oral health status indicators (OOHSI).

RESULTS

Compared with SOHSI and OOHSI, EQ-5D showed similar predictive utility for chewing difficulty in both the internal and external validation models.

CONCLUSIONS

Effect sizes, quantified using Cohen's d, indicated that EQ-5D parameters had a moderate impact on the prediction accuracy for chewing difficulties.

Development of an artificial intelligence model for optimizing periodontal therapy decision-making: a retrospective longitudinal cohort study

OBJECTIVES

This study aims to develop and validate an artificial intelligence (AI) - driven model to assist periodontal therapy decision-making and minimize tooth loss.

METHODS

A retrospective longitudinal cohort study was conducted using clinical and radiographic data from 3,347 teeth treated and followed up for at least 10 years. The parameters included in the machine learning training and testing processes included: probing pocket depth (PPD), bone loss (BL), systemic diseases, therapy type, and others. Various machine learning models were developed and evaluated for accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC-ROC).

RESULTS

The Random Forest model demonstrated superior performance and was selected as the final predictive model achieving an AUC score of 0.91 and an accuracy of 0.93. Significant associations were found between tooth loss and variables such as age, PPD, bone loss, and furcation involvement.

CONCLUSION

This AI-driven platform may provide a reliable tool for stratifying periodontal therapy decisions and predicting tooth loss risk, offering clinicians a supportive approach to personalize treatment plans. However, the study's retrospective design and reliance on traditional clinical metrics highlight the need for future prospective studies.

CLINICAL SIGNIFICANCE

This study introduces and validates a novel AI-driven predictive model for periodontal therapy, utilizing data from treatment cases. Unlike previous models, this approach integrates multiple clinical and radiographic parameters, demonstrating high predictive accuracy (AUC=0.91, accuracy=0.93). The use of the Random Forest algorithm allows for robust predictions, offering an innovative, data-driven approach to periodontal treatment planning. Implementing AI in periodontal therapy decision-making may have the potential to improve patient outcomes by guiding clinicians toward optimal treatment strategies, enhancing therapeutic precision, and reducing the likelihood of unnecessary interventions.

Artificial Intelligence-Related Dental Research: Bibliometric and Altmetric Analysis

BACKGROUND

Recent years have witnessed an explosive surge in dental research related to artificial intelligence (AI). These applications have optimised dental workflows, demonstrating significant clinical importance. Understanding the current landscape and trends of this topic is crucial for both clinicians and researchers to utilise and advance this technology. However, a comprehensive scientometric study regarding this field had yet to be performed.

METHODS

A literature search was conducted in the Web of Science Core Collection database to identify eligible "research articles" and "reviews." Literature screening and exclusion were performed by 2 investigators. Thereafter, VOSviewer was utilised in co-occurrence analysis and CiteSpace in co-citation analysis. R package Bibliometrix was employed to automatically calculate scientific impacts, determining the core authors and journals. Altmetric data were described narratively and supplemented with Spearman correlation analysis.

RESULTS

A total of 1558 research publications were included. During the past 5 years, AI-related dental publications drastically increased in number, from 36 to 581. Diagnostics and Scientific Reports published the most articles, whereas Journal of Dental Research received the highest number of citations per article. China, the US, and South Korea emerged as the most prolific countries, whilst Germany received the highest number of citations per article (23.29). Charité Universitätsmedizin Berlin was the institution with the highest number of publications and citations per article (29.16). Altmetric Attention Score was correlated with News Mentions (P < .001), and significant associations were observed amongst Dimension Citations, Mendeley Readers, and Web of Science Citations (P < .001).

CONCLUSIONS

The publication numbers regarding AI-related dental research have been rising rapidly and may continue their upwards trend. China, the US, South Korea, and Germany had promoted the progress of AI-related dental research. Disease diagnosis, orthodontic applications, and morphology segmentation were current hotspots. Attention mechanism, explainable AI, multimodal data fusion, and AI-generated text assistants necessitate future research and exploration.

Low-cost and scalable machine learning model for identifying children and adolescents with poor oral health using survey data: An empirical study in Portugal

This empirical study assessed the potential of developing a machine-learning model to identify children and adolescents with poor oral health using only self-reported survey data. Such a model could enable scalable and cost-effective screening and targeted interventions, optimizing limited resources to improve oral health outcomes. To train and test the model, we used data from 2,133 students attending schools in a Portuguese municipality. Poor oral health (the dependent variable) was defined as having a Decayed, Missing, and Filled Teeth index for deciduous teeth (dmft) or permanent teeth (DMFT) above expert-defined thresholds (dmft/DMFT ≥ 3 or 4). The survey provided information about the students' oral health habits, knowledge, beliefs, and food and physical activity habits, which served as independent variables. Logistic regression models with variables selected through low-variance filtering and recursive feature elimination outperformed various others trained with complex machine learning algorithms based on precision@k metric, outperforming also random selection and expert rule-based models in identifying students with poor oral health. The proposed models are inherently explainable, broadly applicable, which given the context, could compensate their lower performance (Area Under the Curve = 0.64-0.70) compared to similar approaches and models. This study is one of the few in oral health care that includes bias auditing of classification models. The audit surfaced potential biases related to demographic factors such as age and social assistance status. Addressing these biases without significantly compromising model performance remains a challenge. The results confirm the feasibility of survey-based machine learning models for identifying individuals with poor oral health, but further validation of this approach and pilot testing in field trials are necessary.

Tooth loss in breast cancer patients: A comparison between tamoxifen-treated and non-treated patients

BACKGROUND

Tooth loss (TL) affects quality of life and general health. The literature suggesting that tamoxifen treatment in patients with breast cancer (BC) could be associated with alterations in oral health, increasing the risk of TL, is still scarce. This work aimed to determine the relationship between TL and tamoxifen consumption in patients with BC.

MATERIAL AND METHODS

This cross-sectional observational study was carried out from July to September 2023 in the medical oncology services of the "Virgen de la Puerta" - ESSALUD High Complexity Hospital and "Dr. Luis Pinillos Ganoza" - IREN Norte - Regional Institute of Neoplastic Diseases, in Trujillo - Peru. Overall, 200 adult patients diagnosed with BC were evaluated, of which 100 consumed tamoxifen and 100 did not. Inter- and intra-rater reliability was determined with respect to TL, resulting in intra-class correlation values RHO = 0.971 and interclass RHO = 0.938. The oncologist of the corresponding service performed BC diagnosis and stage. Poisson regression was used to analyze results with a significance level of p<0.05.

RESULTS

No relationship was found between TL and tamoxifen consumption in patients with breast cancer (p= 0.221); however, greater TL was observed in women who consumed tamoxifen for more than one year compared to those who did not use it (p=0.025) and in older adult women compared to young women (p=0.030).

CONCLUSIONS

There is a relationship between TL and time of use of tamoxifen in patients with BC, concluding that patients who consumed tamoxifen for more than one year had greater TL than those who did not. Furthermore, no relationship was found between TL and cancer stages, but there was greater TL in older adult patients and also in those who consumed tamoxifen and did not receive chemotherapy or radiotherapy.

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.

Utilization of machine learning models in predicting caries risk groups and oral health-related risk factors in adults

BACKGROUND

The aim of this study was to analyse the risk factors that affect oral health in adults and to evaluate the success of different machine learning algorithms in predicting these risk factors.

METHODS

This study included 2000 patients aged 18 years and older who were admitted to the Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Gaziantep University, between September and December 2023. In this study, patients completed a 30-item questionnaire designed to assess the factors that affect the decayed, missing, and filled teeth (DMFT). Clinical and radiological examinations were performed, and DMFT scores were calculated after completion of the questionnaire. The obtained data were randomly divided into a 75% training group and a 25% test group. The preprocessed dataset was analysed using various machine learning algorithms, including naive Bayes, logistic regression, support vector machine, decision tree, random forest and Multilayer Perceptron algorithms. Pearson's correlation test was also conducted to assess the correlation between participants' DMFT scores and oral health risk factors. The performance of each algorithm was evaluated to determine the most appropriate algorithm, and model performance was assessed using accuracy, precision, recall and F1 score on the test dataset.

RESULTS

A statistically significant difference was found between various factors and DMFT-based risk groups (p < 0.05), including age, sex, body mass index, tooth brushing frequency, socioeconomic status, employment status, education level, marital status, hypertension, diabetes status, renal disease status, consumption of sugary snacks, dry mouth status and screen time. When considering machine learning algorithms for risk group assessments, the Multilayer Perceptron model demonstrated the highest level of success, achieving an accuracy of 95.8%, an F1-score of 96%, and precision and recall rates of 96%.

CONCLUSIONS

Caries risk assessment using a simple questionnaire can identify individuals at risk of dental caries, determine the key risk factors, provide information to help reduce the risk of dental caries over time and ensure follow-up. In addition, it is extremely important to apply effective preventive treatments and to prevent the general health problems that are caused by the deterioration of oral health. The results of this study show the potential of machine learning algorithms for predicting caries risk groups, and these algorithms are promising for future studies.

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.

Prediction of wear of dental composite materials using machine learning algorithms

Since dental materials are worn down over time and eventually need to be replaced. Resin composites are frequently employed as dental restorative materials. By employing the in-vitro test findings of the pin-on-disc tribometer [ASTM G99-04], the goal of this study is to evaluate the capability of three different machine learning (ML) models in analyzing the wear of dental composite materials when immersed in chewable tobacco solution. Four distinct dental composite material samples are used in this investigation, and after being dipped in a chewing tobacco solution for a few days, the samples are taken out and subjected to a wear test. Three different ML models (MLP, KNN, XGBoost) have been chosen for predicting the wear of dental composite specimens. XGBoost ML model yields an R2 value of 0.9996 and it performs noticeably better than the other approaches.

Patterns and predictors of tooth loss among partially dentate individuals in Jordan: A cross-sectional study

Aim

This study aimed to examine the patterns of partial edentulism and the associated risk factors in Jordan.

Methods

A cross-sectional, epidemiological study was carried out across Jordan, and data was collected from adult partially dentate patients in various healthcare facilities. The data collected included sociodemographic data, dental and social history, and clinical examination findings for the jaw and teeth. Multivariate regression models were used to determine the predictors for the number of missing teeth.

Results

The sample consisted of 467 partially dentate participants. The leading cause of tooth loss was dental caries (85.4 %), followed by periodontal disease (13.7 %), and trauma (7.5 %). The mean number of missing teeth was significantly higher in the upper jaw (2.5 ± 3.1) compared to the lower jaw (2.2 ± 2.6, p = 0.02). In both jaws, the most prevalent Kennedy classification was Class 3, followed by Class 3/Modification 1 and Class 2/Modification 1. Increased age, smoking, lack of daily tooth brushing, and low education level were significantly associated with high tooth loss.

Conclusions

This study contributes to the understanding of partial edentulism in Jordan, reflecting broader oral health concerns and the factors influencing tooth loss. The findings, vital for future research and interventions, offer insights applicable to global oral health challenges, particularly for at-risk groups.

Modelling time-varying risk factors of tooth loss: Results from joint model compared with extended Cox regression model

AIM

To illustrate the use of joint models (JMs) for longitudinal and survival data in estimating risk factors of tooth loss as a function of time-varying endogenous periodontal biomarkers (probing pocket depth [PPD], alveolar bone loss [ABL] and mobility [MOB]).

MATERIALS AND METHODS

We used data from the Veterans Affairs Dental Longitudinal Study, a longitudinal cohort study of over 30 years of follow-up. We compared the results from the JM with those from the extended Cox regression model which assumes that the time-varying covariates are exogenous.

RESULTS

Our results showed that PPD is an important risk factor of tooth loss, but each model produced different estimates of the hazard. In the tooth-level analysis, based on the JM, the hazard of tooth loss increased by 4.57 (95% confidence interval [CI]: 2.13-8.50) times for a 1-mm increase in maximum PPD, whereas based on the extended Cox model, the hazard of tooth loss increased by 1.60 (95% CI: 1.37-1.87) times.

CONCLUSIONS

JMs can incorporate time-varying periodontal biomarkers to estimate the hazard of tooth loss. As JMs are not commonly used in oral health research, we provide a comprehensive set of R codes and an example dataset to implement the method.

Using machine learning algorithms to investigate factors associated with complete edentulism among older adults in the United States

AIMS

Edentulism is an incapacitating condition, and its prevalence is unequal among different population groups in the United States (US) despite its declining prevalence. This study aimed to investigate the current prevalence, apply Machine Learning (ML) Algorithms to investigate factors associated with complete tooth loss among older US adults, and compare the performance of the models.

METHODS

The cross-sectional 2020 Behavioral Risk Factor Surveillance System (BRFSS) data was used to evaluate the prevalence and factors associated with edentulism. ML models were developed to identify factors associated with edentulism utilizing seven ML algorithms. The performance of these models was compared using the area under the receiver operating characteristic curve (AUC).

RESULTS

An overall prevalence of 11.9% was reported. The AdaBoost algorithm (AUC = 84.9%) showed the best performance. Analysis showed that the last dental visit, educational attainment, smoking, difficulty walking, and general health status were among the top factors associated with complete edentulism.

CONCLUSION

Findings from our study support the declining prevalence of complete edentulism in older adults in the US and show that it is possible to develop a high-performing ML model to investigate the most important factors associated with edentulism using nationally representative data.

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.

Second Opinion for Non-Surgical Root Canal Treatment Prognosis Using Machine Learning Models

Although the association between risk factors and non-surgical root canal treatment (NSRCT) failure has been extensively studied, methods to predict the outcomes of NSRCT are in an early stage, and dentists currently make the treatment prognosis based mainly on their clinical experience. Since this involves different sources of error, we investigated the use of machine learning (ML) models as a second opinion to support the clinical decision on whether to perform NSRCT. We undertook a retrospective study of 119 confirmed and not previously treated Apical Periodontitis cases that received the same treatment by the same specialist. For each patient, we recorded the variables from a newly proposed data collection template and defined a binary outcome: Success if the lesion clears and failure otherwise. We conducted tests for detecting the association between the variables and the outcome and selected a set of variables as the initial inputs into four ML algorithms: Logistic Regression (LR), Random Forest (RF), Naive-Bayes (NB), and K Nearest Neighbors (KNN). According to our results, RF and KNN significantly improve (p-values < 0.05) the sensitivity and accuracy of the dentist's treatment prognosis. Taking our results as a proof of concept, we conclude that future randomized clinical trials are worth designing to test the clinical utility of ML models as a second opinion for NSRCT prognosis.

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.

Candidate loci shared among periodontal disease, diabetes and bone density

Introduction

While periodontal disease (PD) has been associated with type 2 diabetes (T2D) and osteoporosis, the underlying genetic mechanisms for these associations remain largely unknown. The aim of this study is to apply cross-trait genetic analyses to investigate the potentially shared biology among PD, T2D, and bone mineral density (BMD) by assessing pairwise genetic correlations and searching for shared polymorphisms.

Methods

We applied cross-trait genetic analyses leveraging genome-wide association study (GWAS) summary statistics for: Periodontitis/loose teeth from the UKBB/GLIDE consortium (PerioLT, N=506594), T2D from the DIAGRAM consortium (Neff=228825), and BMD from the GEFOS consortium (N=426824). Among all three, pair-wise genetic correlations were estimated with linkage disequilibrium (LD) score regression. Multi-trait meta-analysis of GWAS (MTAG) and colocalization analyses were performed to discover shared genome-wide significant variants (pMTAG <5x10-8). For replication, we conducted independent genetic analyses in the Women's Genome Health Study (WGHS), a prospective cohort study of middle-aged women of whom 14711 provided self-reported periodontal disease diagnosis, oral health measures, and periodontal risk factor data including incident T2D.

Results

Significant genetic correlations were identified between PerioLT/T2D (Rg=0.23; SE=0.04; p=7.4e-09) and T2D/BMD (Rg=0.09; SE=0.02; p=9.8e-06). Twenty-one independent pleiotropic variants were identified via MTAG (pMTAG<5x10-8 across all traits). Of these variants, genetic signals for PerioLT and T2D colocalized at one candidate variant (rs17522122; ProbH4 = 0.58), a 3'UTR variant of AKAP6. Colocalization between T2D/BMD and the original PerioLT GWAS p-values suggested 14 additional loci. In the independent WGHS sample, which includes responses to a validated oral health questionnaire for PD surveillance, the primary shared candidate (rs17522122) was associated with less frequent dental flossing [OR(95%CI)= 0.92 (0.87-0.98), p=0.007], a response that is correlated with worse PD status. Moreover, 4 additional candidate variants were indirectly supported by associations with less frequent dental flossing [rs75933965, 1.17(1.04-1.31), p=0.008], less frequent dental visits [rs77464186, 0.82(0.75-0.91), p=0.0002], less frequent dental prophylaxis [rs67111375, 0.91(0.83-0.99), p=0.03; rs77464186, 0.80(0.72-0.89), p=3.8e-05], or having bone loss around teeth [rs8047395, 1.09(1.03-1.15), p=0.005].

Discussion

This integrative approach identified one colocalized locus and 14 additional candidate loci that are shared between T2D and PD/oral health by comparing effects across PD, T2D and BMD. Future research is needed to independently validate our findings.

Developing an AI-assisted clinical decision support system to enhance in-patient holistic health care

Holistic health care (HHC) is a synonym for complete patient care, and as such an efficient clinical decision support system (CDSS) for HHC is critical to support the judgement of physician’s decision in response of patient’s physical, emotional, social, economic, and spiritual needs. The field of artificial intelligence (AI) has evolved considerably in the past decades and many AI applications have been deployed in various contexts. Therefore, this study aims to propose an AI-assisted CDSS model that predicts patients in need of HHC and applies an improved recurrent neural network (RNN) model, long short-term memory (LSTM) for the prediction. The data sources include in-patient’s comorbidity status and daily vital sign attributes such as blood pressure, heart rate, oxygen prescription, etc. A two-year dataset consisting of 121 thousand anonymized patient cases with 890 thousand physiological medical records was obtained from a medical center in Taiwan for system evaluation. Comparing with the rule-based expert system, the proposed AI-assisted CDSS improves sensitivity from 26.44% to 80.84% and specificity from 99.23% to 99.95%. The experimental results demonstrate that an AI-assisted CDSS could efficiently predict HHC patients.

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.

The effect of denture-wearing on physical activity is associated with cognitive impairment in the elderly: A cross-sectional study based on the CHARLS database

BACKGROUND

Currently, only a few studies have examined the link between dental health, cognitive impairment, and physical activity. The current study examined the relationship between denture use and physical activity in elderly patients with different cognitive abilities.

METHODS

The study data was sourced from the 2018 China Health and Retirement Longitudinal Study (CHARLS) database, which included information on denture use and amount of daily physical activity undertaken by older persons. Physical activity was categorized into three levels using the International Physical Activity General Questionnaire and the International Physical Activity Scale (IPAQ) rubric. The relationship between denture use and physical activity in middle-aged and older persons with varying degrees of cognitive functioning was studied using logistic regression models.

RESULTS

A total of 5,892 older people with varying cognitive abilities were included. Denture use was linked to physical activity in the cognitively healthy 60 + age group (p = 0.004). Denture use was positively related with moderate physical activity in the population (odds ratio, OR: 1.336, 95% confidence interval: 1.173-1.520, p < 0.001), according to a multivariate logistic regression analysis, a finding that was supported by the calibration curve. Furthermore, the moderate physical activity group was more likely to wear dentures than the mild physical activity group among age-adjusted cognitively unimpaired middle-aged and older persons (OR: 1.213, 95% CI: 1.053-1.397, p < 0.01). In a fully adjusted logistic regression model, moderate physical activity population had increased ORs of 1.163 (95% CI: 1.008-1.341, p < 0.05) of dentures and vigorous physical activity population had not increased ORs of 1.016 (95% CI: 0.853-1.210, p > 0.05), compared with mild physical activity population.

CONCLUSION

This findings revealed that wearing dentures affects physical activity differently in older persons with different cognitive conditions. In cognitively unimpaired older adults, wearing dentures was associated with an active and appropriate physical activity status.

Diagnosis of Tooth Prognosis Using Artificial Intelligence

The accurate diagnosis of individual tooth prognosis has to be determined comprehensively in consideration of the broader treatment plan. The objective of this study was to establish an effective artificial intelligence (AI)-based module for an accurate tooth prognosis decision based on the Harvard School of Dental Medicine (HSDM) comprehensive treatment planning curriculum (CTPC). The tooth prognosis of 2359 teeth from 94 cases was evaluated with 1 to 5 levels (1—Hopeless, 5—Good condition for long term) by two groups (Model-A with 16, and Model-B with 13 examiners) based on 17 clinical determining factors selected from the HSDM-CTPC. Three AI machine-learning methods including gradient boosting classifier, decision tree classifier, and random forest classifier were used to create an algorithm. These three methods were evaluated against the gold standard data determined by consensus of three experienced prosthodontists, and their accuracy was analyzed. The decision tree classifier indicated the highest accuracy at 0.8413 (Model-A) and 0.7523 (Model-B). Accuracy with the gradient boosting classifier and the random forest classifier was 0.6896, 0.6687, and 0.8413, 0.7523, respectively. Overall, the decision tree classifier had the best accuracy among the three methods. The study contributes to the implementation of AI in the decision-making process of tooth prognosis in consideration of the treatment plan.

Number of teeth is associated with all-cause and disease-specific mortality

BACKGROUND

Tooth loss has been shown to correlate with multiple systemic comorbidities. However, the associations between the number of remaining natural teeth (NoT) and all-cause mortality have not been explored extensively. We aimed to investigate whether having fewer NoT imposes a higher risk in mortality. We tested such hypotheses using three groups of NoT (20-28,10-19, and 0-9), edentulism and without functional dentition (NoT < 19).

METHODS

The National Health and Nutrition Examination Survey in the United States (NHANES) (1999-2014) conducted dental examinations and provided linkage of mortality data. NHANES participants aged 20 years and older, without missing information of dental examination, age, gender, race, education, income, body-mass-index, smoking, physical activities, and existing systemic conditions [hypertension, total cardiovascular disease, diabetes, and stroke (N = 33,071; death = 3978), or with femoral neck bone mineral density measurement (N = 13,131; death = 1091)] were analyzed. Cox proportional hazard survival analyses were used to investigate risks of all-cause, heart disease, diabetes and cancer mortality associated with NoT in 3 groups, edentulism, or without functional dentition.

RESULTS

Participants having fewer number of teeth had higher all-cause and disease-specific mortality. In fully-adjusted models, participants with NoT0-9 had the highest hazard ratio (HR) for all-cause mortality [HR(95%CI) = 1.46(1.25-1.71); p < .001], mortality from heart diseases [HR(95%CI) = 1.92(1.33-2.77); p < .001], from diabetes [HR(95%CI) = 1.67(1.05-2.66); p = 0.03], or cancer-related mortality [HR(95%CI) = 1.80(1.34-2.43); p < .001]. Risks for all-cause mortality were also higher among the edentulous [HR(95%CI) = 1.35(1.17-1.57); p < .001] or those without functional dentition [HR(95%CI) = 1.34(1.17-1.55); p < .001].

CONCLUSIONS

Having fewer NoT were associated with higher risks for all-cause mortality. More research is needed to explore possible biological implications and validate our findings.

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

Prevalence of tooth loss has increased due to population aging. Tooth loss negatively affects the overall physical and social well-being of older adults. Understanding the role of socio-demographic and other predictors associated with tooth loss that are measured in non-clinical settings can be useful in community-level prevention. We used high-dimensional epidemiological data to investigate important factors in predicting tooth loss among older adults over a 6-year period of follow-up. Data was from participants of 2010 and 2016 waves of the Japan Gerontological Evaluation Study (JAGES). A total of 19,407 community-dwelling functionally independent older adults aged 65 and older were included in the analysis. Tooth loss was measured as moving from a higher number of teeth category at the baseline to a lower number of teeth category at the follow-up. Out of 119 potential predictors, age, sex, number of teeth, denture use, chewing difficulty, household income, employment, education, smoking, fruit and vegetable consumption, community participation, time since last health check-up, having a hobby, and feeling worthless were selected using Boruta algorithm. Within the 6-year follow-up, 3013 individuals (15.5%) reported incidence of tooth loss. People who experienced tooth loss were older (72.9 ± 5.2 vs 71.8 ± 4.7), and predominantly men (18.3% vs 13.1%). Extreme gradient boosting (XGBoost) machine learning prediction model had a mean accuracy of 90.5% (±0.9%). A visual analysis of machine learning predictions revealed that the prediction of tooth loss was mainly driven by demographic (older age), baseline oral health (having 10-19 teeth, wearing dentures), and socioeconomic (lower household income, manual occupations) variables. Predictors related to wide a range of determinants contribute towards tooth loss among older adults. In addition to oral health related and demographic factors, socioeconomic factors were important in predicting future tooth loss. Understanding the behaviour of these predictors can thus be useful in developing prevention strategies for tooth loss among older adults.