No abstract

Background Smoking is an established risk factor for oral diseases and, therefore, dental clinicians routinely assess and record their patients' detailed smoking status. Researchers have successfully extracted smoking history from electronic health records (EHRs) using text mining methods. However, they could not retrieve patients' smoking intensity due to its limited availability in the EHR. The presence of detailed smoking information in the electronic dental record (EDR) often under a separate section allows retrieving this information with less preprocessing. Objective To determine patients' detailed smoking status based on smoking intensity from the EDR. Methods First, the authors created a reference standard of 3,296 unique patients’ smoking histories from the EDR that classified patients based on their smoking intensity. Next, they trained three machine learning classifiers (support vector machine, random forest, and naïve Bayes) using the training set (2,176) and evaluated performances on test set (1,120) using precision (P), recall (R), and F-measure (F). Finally, they applied the best classifier to classify smoking status from an additional 3,114 patients’ smoking histories. Results Support vector machine performed best to classify patients into smokers, nonsmokers, and unknowns (P, R, F: 98%); intermittent smoker (P: 95%, R: 98%, F: 96%); past smoker (P, R, F: 89%); light smoker (P, R, F: 87%); smokers with unknown intensity (P: 76%, R: 86%, F: 81%), and intermediate smoker (P: 90%, R: 88%, F: 89%). It performed moderately to differentiate heavy smokers (P: 90%, R: 44%, F: 60%). EDR could be a valuable source for obtaining patients’ detailed smoking information. Conclusion EDR data could serve as a valuable source for obtaining patients' detailed smoking information based on their smoking intensity that may not be readily available in the EHR.

a We note some informaticians do provide direct care as trained and licensed physicians, nurses, dentists, pharmacists, therapists, social workers, midwives, etc. Further, as the scope of health professionalism changes, some informaticians who practice in public health, care coordination, or wellness coaching may be thought to provide care. However, our main point is a team member in the domains of health and healthcare can impart value without providing direct care.

BACKGROUND: Limited studies have investigated the medication profile of young adult dental patients despite the high prevalence of prescription opioid abuse in this population. OBJECTIVE: This study investigated the extent and differences in medication usage of dental patients older than 18 years by age, race/ethnicity, gender, insurance status and mechanism of action in an academic dental clinic setting. METHODS: Using an automated approach, medication names in the Electronic Dental Record were retrieved and classified according to the National Drug Code directory. Descriptive statistics, multivariable ANOVA and Post hoc tests were performed to detect differences in the number of medications by patient demographics. RESULTS: Of the 11,220 adult patients, 53 percent reported taking at least one medication with significant differences in medication usage by demographics. Hydroxymethylglutaryl-coenzyme A reductase inhibitors (21–36%), and angiotensin-converting enzyme inhibitors (19–23%) ranked the top two medication classes among patients 55 years and older. Opioid agonists (7–14%), and Selective Serotonin Reuptake Inhibitors (SSRIs) (5–12%) ranked the top two medication classes among patients aged 18–54 years. CONCLUSIONS: The results underscore the importance of dental providers to review medical and medication histories of patients regardless of their age to avoid adverse events and to determine patient’s risk for opioid abuse.

SUMMARY Objective: The objective of this study was to determine the survival time of crown margin repairs (CMRs) with glass ionomer and resin-modified glass ionomer cements on permanent teeth using electronic dental record (EDR) data. Methods: We queried a database of EDR (axiUm; Exan Group, Coquitlam, BC, Canada) in the Indiana University School of Dentistry (IUSD), Indianapolis, IN, USA, for records of patients who underwent CMRs of permanent teeth at the Graduate Operative Dentistry Clinic. Two examiners developed guidelines for reviewing the records and manually reviewed the clinical notes of patient records to confirm for CMRs. Only records that were confirmed with the presence of CMRs were retained in the final dataset for survival analysis. Survival time was calculated by Kaplan-Meier statistics, and a Cox proportional hazards model was performed to assess the influence of age, gender, and tooth type on survival time (a<0.05). Results: A total of 214 teeth (115 patients) with CMR were evaluated. Patient average age was 69.4 ± 11.7 years old. Posterior teeth accounted for 78.5% (n=168) of teeth treated. CMRs using glass ionomer cements had a 5-year survival rate of 62.9% and an annual failure rate (AFR) of 8.9%. Cox proportional-hazards model revealed that none of the factors examined (age, gender, tooth type) affected time to failure. Conclusion: The results indicate the potential of CMRs for extending the functional life of crowns with defective margins, thus reducing provider and patient burden of replacing an indirect restoration. We recommend future studies with a larger population who received CMR to extend the generalizability of our findings and to determine the influence of factors such as caries risk and severity of defects on survival time.