Mapping the “X” Debate: Water Fluoridation Sentiment Analysis With Advanced Machine Learning

OBJECTIVES: Community water fluoridation (CWF) is one of the greatest public health achievements of the 20th century. Despite this achievement, there are still misunderstandings about the safety of water fluoridation. Previous communication campaigns advocating CWF have been unsuccessful in combating these misunderstandings, suggesting a need for a new way to promote CWF. The goal of this article is to guide research for future campaigns by analyzing the digital conversation regarding community water fluoridation and other forms of fluoride in the state of Texas. METHODS: NUVI software extracted tweets from Twitter, and SAS Text Miner 12.1 software revealed topics related to water fluoridation. RESULTS: The results uncovered eight topics related to water fluoridation. Overall, the analysis showed mixed reactions toward water fluoridation, fluoride toothpaste, and children's dental health. CONCLUSIONS: The findings of the text analysis will guide future research, with the goal of building a pro-CWF effort in Texas.

To assess the effect of Community Water Fluoridation (CWF) in the prevalence of dental caries and dental fluorosis in 12-year-old children living in Israel. Considering that CWF is important in the prevention of dental caries. Between 2002 and 2014, the water in communities of at least 5000 individuals was fluoridated. In 2014 CWF in Israel stopped. Data on 12-year-old children from all areas in Israel from the national crosssectional epidemiological survey conducted in 2011-2012 were stratified by city water fluoridation and by city and school socio-economic status (SES). Two dependent variables were defined: (1) DMFT index -caries experience in the permanent dentition; (2) dental fluorosis in central incisors using the Thylstrup-Fejerskov (TF) classification of fluorosis. Data from 2181, 12-year-olds was analyzed. the average DMFT was 1.17+1.72 and 49% were caries free. Based on DMFT, the caries experience was significantly higher in nonfluoridated cities (1.38 vs. 0.98 in fluoridated cities) and there were more caries free children 56.4% in fluoridated cities vs. 40.6% in non-fluoridated. DMFT was higher in cities with lower SES than high SES (1.29 vs. 1.05 respectively, p<0.001) and there were less caries free children in low SES (44.5% vs. 53% in high SES cities, p<0.0001). Almost all the 10.3% of children with signs of fluorosis (scoring at least 1 in TF index), had questionable to mild fluorosis (9.3%). CWF is a cheap, simple method of dental health protection that reaches all socio-economic levels and cessation of water fluoridation reduced the health of Israel's children. Water fluoridation provides substantial caries prevention, by reaching a substantial number of people. The relevance of this work is for policymakers to consider CWF as clinically proven method for reducing health inequalities.

Promoting support for community water fluoridation: Testing message effects and the role of normative beliefs

We examined the association between area-level deprivation and dental ambulatory sensitive hospitalizations (ASH) and considered the moderating effect of community water fluoridation (CWF). The hypothesis was that higher levels of deprivation are associated with higher dental ASH rates and that CWF will moderate this association such that children living in the most deprived areas have greater health gain from CWF. Dental ASH conditions (dental caries and diseases of pulp/periapical tissues), age, gender and home address identifier (meshblock) were extracted from pooled cross-sectional data (Q3, 2011 to Q2, 2017) on children aged 0-4 and 5-12 years from the National Minimum Dataset, New Zealand (NZ) Ministry of Health. CWF was obtained for 2011 and 2016 from the NZ Institute of Environmental Science and Research. Dental ASH rates for children aged 0-4 and 5-12 years (/1000) were calculated for census area units (CAUs). Multilevel negative binomial models investigated associations between area-level deprivation, dental ASH rate and moderation by CWF status. Relative to CWF (2011 and 2016), no CWF (2011 and 2016) was associated with increased dental ASH rates in children aged 0-4 [incidence rate ratio (IRR) = 1.171 (95% confidence interval 1.064, 1.288)] and aged 5-12 years [IRR = 1.181 (1.084, 1.286)]. An interaction between area-level deprivation and CWF showed that the association between CWF and dental ASH rates was greatest within the most deprived quintile of children aged 0-4 years [IRR = 1.316 (1.052, 1.645)]. CWF was associated with a reduced dental ASH rate for children aged 0-4 and 5-12 years. Children living in the most deprived areas showed the greatest effect of CWF on dental ASH rates, indicating that the greater health gain from CWF occurred for those with the highest socio-economic disadvantage. Variation in CWF contributes to structural inequities in oral-health outcomes for children.

We sought to estimate the association between community water fluoridation (CWF) exposure at various stages of life and adult tooth loss. We used data from the 1995 through 1999 Behavioral Risk Factor Surveillance System, merged with data from the 1992 Water Fluoridation Census, to estimate interval regression models that relate CWF exposure with tooth loss. Our results indicate that CWF levels in the county of residence at the time of the respondent's birth are significantly related to tooth loss but current CWF levels are not. In addition, the impact of CWF exposure is larger for individuals of lower socioeconomic status. This study suggests that the benefits of CWF may be larger than previously believed and that CWF has a lasting improvement in racial/ethnic and economic disparities in oral health.

Aim: The majority of machine learning (ML) models in healthcare are built on retrospective data, much of which is collected without explicit patient consent for use in artificial intelligence (AI) and ML applications. The primary aim of this study was to evaluate whether clinicians and scientific researchers themselves consent to provide their own data for the training of ML models. Materials and Methods: This survey was conducted through an anonymous online survey, utilizing platforms such as Telegram, LinkedIn, and Viber. The target audience comprised specific international groups, primarily Russian, German, and English-speaking, of clinicians and scientific researchers. These participants ranged in their levels of expertise and experience, from beginners to veterans. The survey centered on a singular, pivotal question: “Do You Consent to the Use of Your Biological and Private Data for Training Machine Learning and AI Models?” Respondents had the option to choose from three responses: “Yes” and “No”. Results: The survey was conducted in January 2024. A total of 119 unique and verified individuals participated in the survey. The results revealed that only 50% of respondents (63 persons) expressed consent to provide their own data for the training of ML and AI models. Conclusion: In the development of ML and AI models, particularly open-source ones, it is crucial to ascertain whether participants are willing to provide their private data. While ML algorithms can transform the nature of data, it is important to remember that the primary owner of this data is the individual. Our findings show that in 50% of the cases, even participants from scientific research and clinical backgrounds – individuals typically accountable for ensuring data quality in AI and ML model development – do not consent to the use of their data in AI and ML settings. This highlights the need for more stringent consent processes and ethical considerations in the utilization of personal data in AI and ML research.

BackgroundCommunity water fluoridation began in the 1945 as a public health measure to prevent and control caries and was implemented in Israel in 1981. Community water fluoridation reduced caries significantly, but in 2014, the Ministry of Health decided to stop Community water fluoridation in Israel. The aim of our study was to examine the effect of fluoridation cessation on the dental health of children aged 3–5, treated in “Assuta Tel Aviv” dental clinics, under general anesthesia or deep sedation.MethodsThe computerized Maccabi-Dent database provided data for this retrospective study. Records from the years 2014–2019 including treatment codes for procedures relevant to the study, the number of stainless-steel crowns and restorations of all types were examined. Kruskal-Wallis test was performed to compare the results from before and after fluoridation cessation.ResultsA statistically significant increase in the mean number of treatments in the years after fluoridation cessation (P < 0.05) was found. There was approximately a two-fold increase in the number of all treatments for all ages.ConclusionThe results of the study emphasize the advantages of water fluoridation and are further proof of the need to restore community water fluoridation in Israel.

Machine learning-based water quality prediction using octennial in-situ Daphnia magna biological early warning system data

Machine Learning Can Accurately Predict Overnight Stay, Readmission, and 30-Day Complications Following Anterior Cruciate Ligament Reconstruction

Study question Can a machine learning (ML) model, developed using modern neural network architecture produce comparable annotation data; utilisable for algorithmic outcome prediction, to manual time-lapse annotations? Summary answer The model automatically annotated unseen embryos with comparable results to manual methods, generating morphokinetic data to enable comparably predictive outputs from an embryo selection algorithm. What is known already The application of artificial intelligence across healthcare industries, including fertility, is increasing. Several ML models are available that seek to generate or analyse embryo images and morphokinetic data, and to determine embryo viability potential. Along with photographic images, the use of time-lapse in IVF laboratories has amassed numeric data, resulting predominantly from annotated manual assessment of images over time. Embryo annotation practice is variable in quality, can be subjective and is time-consuming; commonly taking several minutes per embryo. The development of rapid, accurate automatic annotation would represent a significant time-saving as well as an increase in reproducibility and accuracy. Study design, size, duration Multicentre quality assured annotation data from 63,383 time-lapse monitored embryos (EmbryoScope®), comprising over 400 million individual images, were used to train a ML model to automatically generate morphokinetic annotations. Data was derived from 8 UK clinics within a cohesive group between 2012-2021. Accuracy was assessed using 900 unseen embryos (with live birth outcome) by comparing the output of an established in-house, prospectively validated embryo selection model when the input was either ML-automated, or manual annotations. Participants/materials, setting, methods Multi-focal plane images were processed on the Azure cloud (Microsoft) and resampled to 300x300 pixels. A Laplacian-based focal stacking algorithm merged frames into a single image. The model consisted of an EfficientNetB4 Convolutional Neural Network classifier to extract features and classify the stage of embryo images. A Temporal Convolutional Network interpreted a time-series of image features; producing annotations from pronuclear fading through to blastocyst. Soft localisation loss function used QA data to integrate annotation subjectivities. Main results and the role of chance The ML model rapidly and automatically generated annotations. Efficacy and comparability of the ML model to automate reliable, utilisable annotations was demonstrated by comparison with manual annotation data and the ML model’s ability to auto-generate annotations which could be used to predict live birth by providing annotation data to an established, validated in house embryo selection model. Live birth-predictive capability was measured, and benchmarked against manual annotation, using the area under the receiver operating characteristic curve (AUC). When tested on time-lapse images, collected from pronuclear fading to full blastulation, representing 900 previously unseen, transferred blastocysts where live birth outcomes were blinded, the in-house developed auto-annotation ML model resulted in an AUC of 0.686 compared with 0.661 for manual annotations, for live birth prediction. Auto annotation using the developed model took only milliseconds to complete per embryo. The developed auto-annotation model, built and tested on large data, is considered suitable for productionisation with the aim of being validated and integrated into an application to support IVF laboratory practice. Limitations, reasons for caution Whilst this model was trained to recognise key morphokinetic events, there are other morphokinetic variables that may be useful in the prediction of live birth and further improve embryo selection, or deselection, ability. Akin to manual interpretation, some embryos may fail to be annotated or need second opinion. Wider implications of the findings There is increasing evidence supporting the application of ML to utilise big data from time-lapse imaging and fertility care generally. Whilst promising benefits to IVF clinics and patients, responsible use of data is required alongside large high-quality datasets, and rigorous validation, to ensure safe and robust applications. Trial registration number N/A

The objective of this document is to identify the most accurate machine learning (ML) models for predicting the value of a real estate property, based on a systematic literature review (SLR). It was conducted on research published between 2022 and 2023 that analyzed the accuracy of ML models in real estate valuation. Information was extracted regarding the ML models used, the databases employed, and the models highlighted for their accuracy. A variety of ML models used in real estate valuation were identified, including Random Forest (RF), XGBoost, Gradient Boosting Machine (GBM), Linear Regression (LR), and Lasso Regression. RF and LR models stood out as the most accurate in the analyzed research, showing that the accuracy of ML models varies depending on the database, property characteristics, and valuation context. It was concluded that ML models like RF and LR are promising tools for improving the accuracy of real estate valuation. Additionally, the choice of the best ML model depends on factors such as the database, property characteristics, and specific valuation objectives. Further research is needed on the application of ML in real estate valuation, considering aspects such as model interpretability and the real estate market context.

Science, Politics, and Communication: The Case of Community Water Fluoridation in the US

Community water fluoridation is a well-recognized public health initiative known for its efficacy in preventing dental cavities. The positive effects of fluoride on tooth enamel have led to widespread implementation of water fluoridation programs. This cross-sectional study involved 1,000 participants from diverse age groups, spanning children, adolescents, adults, and older adults, residing in both fluoridated and non-fluoridated communities. Comprehensive periodontal assessments included measurements of probing depth (PD), clinical attachment level (CAL), and the presence of gingival inflammation. Participants were categorized into "fluoridated" or "non-fluoridated" groups based on their residential history. Fluoridated communities consistently displayed lower mean PDs, CALs, and rates of gingival inflammation across all age groups. Notably, the reduction in PD and CAL reached approximately 0.5 millimeters and 0.3 millimeters, respectively, while the decrease in gingival inflammation ranged from 3% to 5. This study suggests a potential link between community water fluoridation and enhanced periodontal health, as evidenced by improved PDs, CALs, and reduced gingival inflammation.

Metabolic dysfunction-associated steatotic liver disease (MASLD) can progress to metabolic dysfunction-associated steatohepatitis (MASH) and liver fibrosis, contributing to a heavier global health burden. Non-invasive diagnostic tools developed using machine learning (ML) and deep learning (DL), two representative artificial intelligence algorithms, are increasingly being explored for MASH and its related fibrosis assessment. This study aimed to compare the diagnostic performance of different ML and DL models and identify the top-performing models for diagnosing MASH and associated liver fibrosis. A systematic review and meta-analysis were conducted across PubMed, Web of Science, Embase and Cochrane Library from inception to May 18, 2025. Pooled area under the receiver operator characteristic curve (AUROC) values with 95 % confidence interval (CI) were calculated. Accuracy, specificity, sensitivity, positive predictive values, and negative predictive values were also recorded. Of 4,314 studies initially identified, 106 met the inclusion criteria, with 35 studies (ML: n=28; DL: n=7) providing data for analysis. Logistic Regression and Neural Network are the most commonly algorithms applied in ML and DL, respectively. The pooled AUROCs for diagnosing MASH were 0.833 (95 %CI: 0.806-0.860) for ML models and 0.841 (95 %CI: 0.782-0.900) for DL models. Light Gradient Boosting Machine (LightGBM) and ResNet50 were the best-performing models for diagnosing MASH within ML and DL algorithms, respectively, achieving corresponding AUROCs of 0.920 (95 %CI: 0.916-0.924) and 0.960 (95 %CI: 0.951-0.969). For fibrosis diagnosis, ML models had a pooled AUROC of 0.826 (95 %CI: 0.792-0.860), with Categorical Boosting (CatBoost) achieving the highest AUROC of 0.960 (95 %CI: 0.950-0.970). DL models yielded the pooled AUROC of 0.875 (95 %CI: 0.816-0.934) for fibrosis diagnosis. Both ML and DL models demonstrated strong diagnostic performance for MASH and liver fibrosis, with DL achieving marginally higher AUROCs. AI-driven approaches show promise in MASLD management.

COVID-19 has transitioned from a pandemic to an endemic state, but the emergence of novel variants continues to pose significant public health challenges. In this study, the application of spatial and spatiotemporal machine learning (ML) models in understanding the dynamics of COVID-19 was systematically reviewed, as were contextual local-level comprehensive socio-environmental drivers. A systematic search was conducted across the Scopus, Web of Science, PubMed, Emcare (via Ovid), and the World Health Organization COVID-19 databases, and gray literature, adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Data extraction was conducted according to the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies checklist, and study quality was assessed using a validated scoring system. A total of 42 studies met the inclusion criteria. The review Findings indicate that global-scale spatial and spatiotemporal ML models dominate the field. Long-standing standalone factors in the demographic, environmental, and socioeconomic domains are frequently used as local-level drivers. However, the integration of composite indicators, aggregating multiple standalone factors into a single score, is notably lacking. Such composite indicators have the potential to reduce model complexity, improve interpretability, and enhance performance by capturing multidimensional aspects of vulnerability or risk in a more simplified form. This review highlights critical gaps in the current use of spatial and spatiotemporal ML models to understand the spatial epidemiology of COVID-19. Addressing these gaps could significantly enhance the understanding of COVID-19 dynamics and inform the development of effective public health strategies to mitigate future threats.