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

OBJECTIVES: Evaluating children's oral health status and treatment needs is challenging. We aim to build oral health assessment toolkits to predict Children's Oral Health Status Index (COHSI) score and referral for treatment needs (RFTN) of oral health. Parent and Child toolkits consist of short-form survey items (12 for children and 8 for parents) with and without children's demographic information (7 questions) to predict the child's oral health status and need for treatment. METHODS: Data were collected from 12 dental practices in Los Angeles County from 2015 to 2016. We predicted COHSI score and RFTN using random Bootstrap samples with manually introduced Gaussian noise together with machine learning algorithms, such as Extreme Gradient Boosting and Naive Bayesian algorithms (using R). The toolkits predicted the probability of treatment needs and the COHSI score with percentile (ranking). The performance of the toolkits was evaluated internally and externally by residual mean square error (RMSE), correlation, sensitivity and specificity. RESULTS: The toolkits were developed based on survey responses from 545 families with children aged 2 to 17 y. The sensitivity and specificity for predicting RFTN were 93% and 49% respectively with the external data. The correlation(s) between predicted and clinically determined COHSI was 0.88 (and 0.91 for its percentile). The RMSEs of the COHSI toolkit were 4.2 for COHSI (and 1.3 for its percentile). CONCLUSIONS: Survey responses from children and their parents/guardians are predictive for clinical outcomes. The toolkits can be used by oral health programs at baseline among school populations. The toolkits can also be used to quantify differences between pre- and post-dental care program implementation. The toolkits' predicted oral health scores can be used to stratify samples in oral health research. KNOWLEDGE TRANSFER STATEMENT: This study creates the oral health toolkits that combine self- and proxy- reported short forms with children's demographic characteristics to predict children's oral health and treatment needs using Machine Learning algorithms. The toolkits can be used by oral health programs at baseline among school populations to quantify differences between pre and post dental care program implementation. The toolkits can also be used to stratify samples according to the treatment needs and oral health status.

Er:Yag Laser application on titanium implant surfaces contaminated by Porphyromonas gingivalis: an histomorphometric evaluation.

AIM: The aim of this study was to evaluate the in-vitro application of Erbium Yag Laser (ERL) on implant surfaces contaminated by Porphyromonas gingivalis (Pg.). Moreover, this study evaluated the surface characteristics of irradiated implants. METHODS: A total of 60 implants was evaluated (20 for each surface group). Each group was divided in two subgroups composed of 10 implants (test and a control). Implants were contaminated by Pg. reference strains. After proper incubation, test implants were irradiated with ERL. Laser parameters were the following: 2 940 nm wavelength, 20 mus pulse duration, 10 Hz frequency and 30 MJ pulse energy. A periodontal fiber was used to irradiate the implant threads on the axial surface with a 45 degrees angle of incidence and performing apex-crown motions for 16 s. Histomorphometric evaluation of implant surfaces (test and control) was made at different magnifications (1 000x, 6 000x,11 000x). Pg. counts were calculated on a 4 800-mm2 surface utilizing a 10-mm grid. Statistical evaluation was made with Fisher and Student's t test (P<0.05). RESULTS: No surface alterations on test implants were observed. Counting results showed the following decontamination values: 76.2% for machined test implants, 90.9% for titanium plasma spray implants and 98.3% for sandblasted and etched implants. A minimal residual bacterial presence was observed in all groups. CONCLUSION: The results of the following study showed that ERL application has decontamination effectiveness on different implant surfaces. The modification of laser time application and working parameters could easily determine complete bacterial removal from all the implant surfaces analyzed.

Periodontal disease and preterm birth relationship: a review of the literature.

Despite medical care improves consistently, the rate of preterm birth has risen in recent years. In Italy the rate of preterm birth between the XXXIII and the XXXVI week is 13.5%, while it amounts to 1.3% for preterm birth between XXIV and the XXXII week. Consequently, the identification of risk factors for preterm birth that might be modified would have far-reaching and long-lasting effects. A significant number of preterm birth may be attributed to infections of the urogenital tract, such as bacterial vaginosis. In the last decade, great interest has been generated to support the hypothesis that sub-clinical infection at sites that are also distant from the genito-urinary tract may be an important cause of preterm labour, probably through the activation of abnormal inflammatory responses within the uterus and intrauterine tissues. There is emerging evidence of a possible relationship between maternal periodontal diseases as a potential risk factor of adverse pregnancy outcomes, like preterm low birth weight even though not all of the actual data support such hypothesis. Further studies are clearly required to clarify the causes and/or relationships linking pathologic oral conditions and adverse pregnancy outcomes. So far, from a clinical standpoint, it would appear that the assessment of the periodontal status of pregnant women during an early pregnancy might be useful in providing an important indicator of risk for future obstetric complications.

Child and Parent Demographic Characteristics and Oral Health Perceptions Associated with Clinically Measured Oral Health.

OBJECTIVE: To examine child and parent reports about the child's oral health and assess the associations of these reports with clinical assessments of oral health status by dental examiners. METHODS: Surveys with 139 items for children and 133 items for parents were administered by Audio Computer-Assisted Self-Interview Software. In addition, the Children's Oral Health Status Index (COHSI) was computed from a dental examination. RESULTS: A total of 334 families with children ages 8 to 17 y participated at 12 dental practices in Los Angeles County. Ordinary least squares regression models were estimated separately for child and parent surveys to identify items uniquely associated with the COHSI. Ten of 139 items the children reported regarding their oral health were associated with the COHSI. The strongest associations were found for child's age, aesthetic factors (straight teeth and pleased with teeth), and cognitive factors related to perception of dental appearance (pleased/happy with the look of the child's mouth, teeth, and jaws). Nine of 133 parent items about the child's oral health were associated with the COHSI in the parent model, notably being a single parent, parent's gender, parent born in the United States, pleased or happy with the look of their child's teeth, and accessing the Internet. CONCLUSION: These child and parent survey items have potential to be used to assess oral health status for groups of children in programs and practices in lieu of dental screenings. KNOWLEDGE TRANSLATION STATEMENT: The paper's results inform the development of a toolkit that can be used by schools, public health agencies, and dental programs to identify children with low oral health status based on parents' and children's responses to survey items across demographic, physical, mental, and social domains. These survey items can be used to inform parents of the desirability of proactively addressing inadequacies in their child's oral health status, enabling them to more rationally address dental needs.

Determinants of ECC in Sardinian preschool children.

OBJECTIVE: The aim of the study was to assess the influence of determinants on the presence of caries in pre-school children. BASIC RESEARCH DESIGN: A matched case-control study (1:2) was designed: 55 children (32 males, 23 females) with at least one buccal or lingual caries lesion on one primary maxillary incisor were selected (caries affected=1) and compared to randomly selected controls (no caries=0) paired for age and gender. Several variables concerning oral hygiene habits, use of fluoride supplementation, dietary habits, socio-economic status of the family and lifestyle factors were considered as risk predictors for early childhood caries (ECC). A conditional logistic regression model was used to perform matched case-control analysis. RESULTS: Bottle feeding at night (OR=1.90; 95%CI=1.03-3.50) and socio-economic level (OR=1.69; 95%CI=1.01-2.81) were positively associated with case status. CONCLUSIONS: We conclude that ECC seemed to be associated with bottle feeding at night and a low socio-economic level.

Caries experience and status in school-age children residing in four North Italian communities.

PURPOSE: The aim of this paper was to describe the caries experience in four North Italian areas. The areas selected were four North Italian medium-sized cities: San Remo located in western Liguria, Ferrara in Emilia, and Varese and Melegnano (Milan suburbs). MATERIALS AND METHODS: 1104 subjects (560 males and 544 females) were examined. Several dental outcomes were used: DMFT Index and SiC index following WHO recommendations; and the caries experience ratio; the percentage of children with high caries disease and with rampant caries was calculated as the percentage of subjects with DMFT > 0, DMFT > or = 4 and DMFT > or = 7. RESULTS: Mean DMFT ranged from 1.21 +/- 1.65 in the Ferrara group to 1.83 +/- 2.49 in San Remo. Among the groups, statistically significant differences were observed for DT and DMFT (p = 0.04 and p = 0.01 respectively). The SiC index was 3.75 +/- 1.87, 3 (2-5) in all samples, with significant differences among the four areas (p = 0.04). No statistical differences were observed among the four areas regarding caries experience and the proportion of children with high and rampant caries. An elevated proportion of subjects with high caries (DMFT > or = 4) was noted in the San Remo group (22.9%). The distribution of children by gender according to DMFT levels was not statistically significant either. The F/DMFT ratio was similar in the survey areas, from 0.30 in San Remo, 0.38 in Varese and Ferrara, to 0.40 in the Milan suburbs. CONCLUSION: Information drawn from this study can be helpful to describe and plan future dental prevention programmes aimed at reducing caries experience and promoting better oral health level.

Periodontal status in an Italian young adult population. Prevalence and relationship with periodontopathic bacteria.

To determine the prevalence of periodontitis in an Italian young adult population and the relationship with Actinobacillus actinomycetemcomitans, Porphyromonas gingivalis and Prevotella intermedia in subgingival plaque. A full-mouth periodontal and oral examination was performed in 70 subjects. Dental and behaviour habits were assessed with a standardised questionnaire. Subgingival plaque samples were collected from the deepest pocket of the first molars in each quadrant with a sterile curette. A. actinomycetemcomitans, P. gingivalis and P. intermedia were detected using a multiplex polymerase chain reaction. At subject level, the prevalence of bleeding on probing, calculus, normal pocket depth (PD), PD > 5mm and bacterial positivity were 44.8%, 43.3%, 22.9%, 11.4% and 95.7%, respectively. At quadrant level bacterial prevalence was 79.4%; P. intermedia was the most common bacteria (79.0%); A. actinomycetemcomitans had a prevalence of 40.8%. A significant linear trend across categories of gingival conditions (healthy, bleeding on probing, calculus presence) was detected for P. intermedia (p = 0.0038) and A. actinomycetemcomitans (p = 0.00005) proportions. No significant association was observed between pathogenic bacteria and PD, nor with behavioural attitudes. Gingival conditions are found to be a good predictors (VPP = 85%) for periodontopathic bacteria. For the Italian population, as no data are present, prospective longitudinal studies are needed to examine the relationship between PD and bacteria presence with periodontal disease onset and/or progression.