Periodontal Management by Risk Assessment: A Pragmatic Approach

Developing and testing a prediction model for periodontal disease using machine learning and big electronic dental record data

Despite advances in periodontal disease (PD) research and periodontal treatments, 42% of the US population suffer from periodontitis. PD can be prevented if high-risk patients are identified early to provide preventive care. Prediction models can help assess risk for PD before initiation and progression; nevertheless, utilization of existing PD prediction models is seldom because of their suboptimal performance. This study aims to develop and test the PD prediction model using machine learning (ML) and electronic dental record (EDR) data that could provide large sample sizes and up-to-date information. A cohort of 27,138 dental patients and grouped PD diagnoses into: healthy control, mild PD, and severe PD was generated. The ML model (XGBoost) was trained (80% training data) and tested (20% testing data) with a total of 74 features extracted from the EDR. We used a five-fold cross-validation strategy to identify the optimal hyperparameters of the model for this one-vs.-all multi-class classification task. Our prediction model differentiated healthy patients vs. mild PD cases and mild PD vs. severe PD cases with an average area under the curve of 0.72. New associations and features compared to existing models were identified that include patient-level factors such as patient anxiety, chewing problems, speaking trouble, teeth grinding, alcohol consumption, injury to teeth, presence of removable partial dentures, self-image, recreational drugs (Heroin and Marijuana), medications affecting periodontium, and medical conditions such as osteoporosis, cancer, neurological conditions, infectious diseases, endocrine conditions, cardiovascular diseases, and gastroenterology conditions. This pilot study demonstrated promising results in predicting the risk of PD using ML and EDR data. The model may provide new information to the clinicians about the PD risks and the factors responsible for the disease progression to take preventive approaches. Further studies are warned to evaluate the prediction model's performance on the external dataset and determine its usability in clinical settings.

Translating periodontal data to knowledge in a learning health system

BACKGROUND

A learning health system (LHS) is a health system in which patients and clinicians work together to choose care on the basis of best evidence and to drive discovery as a natural outgrowth of every clinical encounter to ensure the right care at the right time. An LHS for dentistry is now feasible, as an increased number of oral health care encounters are captured in electronic health records (EHRs).

METHODS

The authors used EHRs data to track periodontal health outcomes at 3 large dental institutions. The 2 outcomes of interest were a new periodontitis case (for patients who had not received a diagnosis of periodontitis previously) and tooth loss due to progression of periodontal disease.

RESULTS

The authors assessed a total of 494,272 examinations (new periodontitis outcome: n = 168,442; new tooth loss outcome: n = 325,830), representing a total of 194,984 patients. Dynamic dashboards displaying performance on both measures over time allow users to compare demographic and risk factors for patients. The incidence of new periodontitis and tooth loss was 4.3% and 1.2%, respectively.

CONCLUSIONS

Periodontal disease, diagnosis, prevention, and treatment are particularly well suited for an LHS model. The results showed the feasibility of automated extraction and interpretation of critical data elements from the EHRs. The 2 outcome measures are being implemented as part of a dental LHS. The authors are using this knowledge to target the main drivers of poorer periodontal outcomes in a specific patient population, and they continue to use clinical health data for the purpose of learning and improvement.

PRACTICAL IMPLICATIONS

Dental institutions of any size can conduct contemporaneous self-evaluation and immediately implement targeted strategies to improve oral health outcomes.

Assessing the completeness of periodontal disease documentation in the EHR: a first step in measuring the quality of care

Background

Our objective was to measure the proportion of patients for which comprehensive periodontal charting, periodontal disease risk factors (diabetes status, tobacco use, and oral home care compliance), and periodontal diagnoses were documented in the electronic health record (EHR). We developed an EHR-based quality measure to assess how well four dental institutions documented periodontal disease-related information. An automated database script was developed and implemented in the EHR at each institution. The measure was validated by comparing the findings from the measure with a manual review of charts.

Results

The overall measure scores varied significantly across the four institutions (institution 1 = 20.47%, institution 2 = 0.97%, institution 3 = 22.27% institution 4 = 99.49%, p-value < 0.0001). The largest gaps in documentation were related to periodontal diagnoses and capturing oral homecare compliance. A random sample of 1224 charts were manually reviewed and showed excellent validity when compared with the data generated from the EHR-based measure (Sensitivity, Specificity, PPV, and NPV > 80%).

Conclusion

Our results demonstrate the feasibility of developing automated data extraction scripts using structured data from EHRs, and successfully implementing these to identify and measure the periodontal documentation completeness within and across different dental institutions.

Implementing care coordination in a large dental care organization in the United States by upskilling front office personnel

BACKGROUND

Care coordination is a key strategy used to improve health outcomes and efficiency, yet there are limited examples in dentistry. A large dental accountable care organization piloted care coordination by retraining existing administrative staff to coordinate the care of high-risk patients. Following the pilot's success, a formal "dental care advocate" (DCA) role was integrated system-wide. The goal of this new role is to improve care, patient engagement, and health outcomes while integrating staff into the clinical care team. We aim to describe the process of DCA role implementation and assess staff and clinician perceptions about the role pre- and post-implementation.

METHODS

Guided by the Consolidated Framework for Implementation Research, semi-structured interviews with clinical and operational administrative staff and observation at the company-wide training session were combined with pre- and post-implementation electronic surveys. Descriptive statistics and mean scores were tested for significance between each survey sample (t-tests), and qualitative data were thematically analyzed.

RESULTS

With preliminary evidence from the pilot and strong executive support, a dedicated leadership team executed a stepwise rollout of the DCA role over 6 months. Success was facilitated by an organizational culture of frequent interventions deployed rapidly through a centralized system, along with supportive buy-in from managerial teams and high staff acceptance and enthusiasm for the DCA role before implementation. Following implementation, significant changes in attitudes and beliefs about the role were measured, though managers held stronger positive impressions than DCAs. DCAs reported high confidence in new skills and dental knowledge post-implementation, including motivational interviewing and the ability to confidently answer patients' questions about their oral health. Overall, the fast-paced implementation of this new role was well received, although consistent and significant differences in mean attitudes between managers and DCAs indicate more work to fine-tune the role is needed.

CONCLUSIONS

Successful implementation of the new DCA role was facilitated by a strong organizational commitment to team-based dentistry and positive impressions of care coordination among staff and managers. Upskilling existing administrative staff with the necessary training to manage some high-risk patient needs is one method that can be used to implement care coordination efforts in dentistry.

Association of chairside salivary aMMP-8 findings with periodontal risk assessment parameters in patients receiving supportive periodontal therapy

Purpose

The aim of this retrospective cross-sectional study was to evaluate whether salivary findings of active matrix-metalloproteinase 8 (aMMP-8) chairside (point of care; POC) tests were associated with periodontal risk assessment parameters in patients receiving supportive periodontal therapy (SPT).

Methods

A total of 125 patients receiving regular SPT were included, and their records were examined. The following inclusion criteria were used: a diagnosis of chronic periodontitis, at least 1 non-surgical periodontal treatment (scaling and root planning) with following regular SPT (minimum once a year), at least 6 remaining teeth, and clinical and aMMP-8 findings that were obtained at the same appointment. In addition to anamnestic factors (e.g., smoking and diabetes), oral hygiene indices (modified sulcus bleeding index [mSBI] and approximal plaque index), periodontal probing depth simultaneously with bleeding on probing, and dental findings (number of decayed, missing, and filled teeth) were recorded. Salivary aMMP-8 levels were tested using a commercial POC test system (Periomarker, Hager & Werken, Duisburg, Germany). Statistical analysis was performed using the t-test, Mann-Whitney U test, Fisher's exact test, and χ² test, as appropriate (P<0.05).

Results

Only the mSBI was significantly associated with positive salivary aMMP-8 findings (aMMP-8 positive: 27.8%±20.9% vs. aMMP-8 negative: 18.0%±14.5%; P=0.017). No significant associations were found between aMMP-8 and smoking, diabetes, periodontal parameters, or parameters related to the maintenance interval (P>0.05).

Conclusions

Salivary aMMP-8 chairside findings were not associated with common parameters used for periodontal risk assessment in patients receiving SPT. The diagnostic benefit of POC salivary aMMP-8 testing in risk assessment and maintenance interval adjustment during SPT remains unclear.

Perceptions and attitudes toward performing risk assessment for periodontal disease: a focus group exploration

Background

Currently, many risk assessment tools are available for clinicians to assess a patient’s periodontal disease risk. Numerous studies demonstrate the potential of these tools to promote preventive management and reduce morbidity due to periodontal disease. Despite these promising results, solo and small group dental practices, where most people receive care, have not adopted risk assessment tools widely, primarily due to lack of studies in these settings. The objective of this study was to explore the knowledge, attitudes, and beliefs of dental providers in these settings toward risk-based care through focus groups.

Methods

We conducted six focus group sessions with 52 dentists and dental hygienists practicing in solo and small group practices in Pittsburgh, PA and New York City (NYC), NY. An experienced moderator and a note-taker conducted the six sessions, each including 8–10 participants and lasting approximately 90 min. All sessions were audio-recorded and transcribed verbatim. Two researchers coded the focus group transcripts. Using a thematic analysis approach, they reviewed the coding results to identify important themes and selected representative excerpts that best described each theme.

Results

Providers strongly believed identifying risk factors could predict periodontal disease and use this information to change their patients’ behavior. A successful risk assessment tool could assist them in educating and changing their patient’s behaviors to adopt a healthy lifestyle, thus enabling them to play a major role in their patients’ overall health. However, to achieve this goal, it is essential to educate all dental providers and not just dentists on performing risk assessment and translating the results into actionable recommendations for patients. According to study participants, the research community has focused more on translating research findings into a risk assessment tool, and less on how clinicians would use these tools during patient encounters and if it affects a patients’ risk or outcome.

Conclusions

Dental practitioners were open to performing risk assessment as routine care and playing a bigger role in their patients’ overall health. Recommendations to overcome major barriers included educating dental providers at all levels, conducting more research about their adoption and use in real-world settings and developing appropriate reimbursement models.

Electronic supplementary material

The online version of this article (10.1186/s12903-018-0550-2) contains supplementary material, which is available to authorized users.

Clinician attitudes, skills, motivations and experience following the implementation of clinical decision support tools in a large dental practice

OBJECTIVE

This study assesses dental clinicians' pre- and post-implementation attitudes, skills, and experiences with three clinical decision support (CDS) tools built into the electronic health record (EHR) of a multi-specialty group dental practice.

METHODS

Electronic surveys designed to examine factors for acceptance of EHR-based CDS tools including caries management by risk assessment (CAMBRA), periodontal disease management by risk assessment (PEMBRA) and a risk assessment-based Proactive Dental Care Plan (PDCP) were distributed to all Willamette Dental Group employees at 2 time points; 3 months pre-implementation (Fall 2013) and 15 months after implementation (winter 2015). The surveys collected demographics, measures of job experience and satisfaction, and attitudes toward each CDS tool. The baseline survey response rate among clinicians was 83.1% (n = 567) and follow-up survey response rate was 63.2% (n = 508). Among the 344 clinicians who responded to both before and after surveys, 27% were general and specialist dentists, 32% were dental hygienists, and 41% were dental assistants.

RESULTS

Adherence to the CDS tools has been sustained at 98%+ since roll-out. Between baseline and follow-up, the change in mean attitude scores regarding CAMBRA reflect statistically significant improvement in formal training, knowing how to use the tools, belief in the science supporting the tools, and the usefulness of the tool to motivate patients. For PEMBRA, statistically significant improvement was found in formal training, knowing how to use the tools, belief in the science supporting the tools, with improvement also found in belief that the format and process worked well. Finally, for the PDCP, significant and positive changes were seen for every attitude and skill item scored. A strong and positive correlation with post-implementation attitudes was found with positive experiences in the work environment, whereas a negative correlation was found with workload and stress. Clinicians highly ranked a commitment to evidence-based care and sense that the tools were helping to improve patient care, health, and experience as motivations to use the tools. Peer pressure, fears about malpractice, and incentive pay were rated the lowest among the motivation factors.

CONCLUSION

This study shows that CDS tools built into the EHR can be successfully implemented in a dental practice and widely accepted by the entire clinical team. Achieving a high level of adherence to use of CDS can be done through adequate training, alignment with the mission and purpose of the organization, and is compatible with an improved work environment and clinician satisfaction.