AI-initiated second opinions: a framework for advanced caries treatment planning.

Integrating artificial intelligence (AI) into medical and dental applications can be challenging due to clinicians' distrust of computer predictions and the potential risks associated with erroneous outputs. We introduce the idea of using AI to trigger second opinions in cases where there is a disagreement between the clinician and the algorithm. By keeping the AI prediction hidden throughout the diagnostic process, we minimize the risks associated with distrust and erroneous predictions, relying solely on human predictions. The experiment involved 3 experienced dentists, 25 dental students, and 290 patients treated for advanced caries across 6 centers. We developed an AI model to predict pulp status following advanced caries treatment. Clinicians were asked to perform the same prediction without the assistance of the AI model. The second opinion framework was tested in a 1000-trial simulation. The average F1-score of the clinicians increased significantly from 0.586 to 0.645.

Access to personalised dementia care planning in primary care: a mixed methods evaluation of the PriDem intervention.

OBJECTIVES: Provision of personalised care planning is a national priority for people with dementia. Research suggests a lack of quality and consistency of care plans and reviews. The PriDem model of care was developed to deliver feasible and acceptable primary care-based postdiagnostic dementia care. We aimed to increase the adoption of personalised care planning for people with dementia, exploring implementation facilitators and barriers. DESIGN: Mixed-method feasibility and implementation study. SETTING: Seven general practices from four primary care networks (PCNs) in the Northeast and Southeast of England. PARTICIPANTS: A medical records audit collected data on 179 community-dwelling people with dementia preintervention, and 215 during the intervention year. The qualitative study recruited 26 health and social care professionals, 14 people with dementia and 16 carers linked to participating practices. INTERVENTION: Clinical dementia leads (CDL) delivered a 12-month, systems-level intervention in participating PCNs, to develop care systems, build staff capacity and capability, and deliver tailored care and support to people with dementia and their carers. PRIMARY AND SECONDARY OUTCOME MEASURES: Adoption of personalised care planning was assessed through a preintervention and postintervention audit of medical records. Implementation barriers and facilitators were explored through semistructured qualitative interviews and non-participant observation, analysed using codebook thematic analysis informed by Normalisation Process Theory. RESULTS: The proportion of personalised care plans increased from 37.4% (95% CI 30.3% to 44.5%) preintervention to 64.7% (95% CI 58.3% to 71.0%) in the intervention year. Qualitative findings suggest that the flexible nature of the PriDem intervention enabled staff to overcome contextual barriers through harnessing the skills of the wider multidisciplinary team, delivering increasingly holistic care to patients. CONCLUSIONS: Meaningful personalised care planning can be achieved through a team-based approach. Although improved guidelines for care planning are required, commissioners should consider the benefits of a CDL-led approach. TRIAL REGISTRATION NUMBER: ISRCTN11677384.

The Dental Practicality Index - to treat or not to treat.

The Dental Practicality Index (DPI) has been designed to describe, on a clinical level, the 'practicality' of restoring a tooth versus referring to secondary care or extraction.The systematic approach of DPI has been shown to improve decision-making and confidence in treatment planning when used by young dentists. In addition, there is good evidence demonstrating that it provides an accurate estimation of the outcome of treatment. The DPI enhances clinician-patient communication and ultimately the consent process.

The history of treatment planning the extraction of the first permanent molar in the UK.

This paper researches the history of treatment planning for extraction of the first permanent molars and the early influence of American orthodontists on dental practice in the UK. It also discusses the development of clinical guidelines for the enforced extraction of first permanent molars to the present day.

Demystify Treatment Planning With a Correct Functional Diagnosis.

Obtaining an accurate assessment of the causes of severe dental destruction is crucial when planning a clinical workflow for full-mouth rehabilitation cases. Some cases that initially appear extremely challenging may be surprisingly straightforward, especially if the patient presents with an acceptable functional occlusion. In the seemingly highly complex case presented, only a Lucia jig was required to obtain a reliable restorative reference point for the full-mouth rehabilitation. Increasing the vertical dimension of occlusion allowed for predictable restoration of function and esthetics. The treatment was completed in phases for patient comfort, and the final outcome provided the patient with regained confidence in his smile and comfort when eating.

Deep learning-based approach for 3D bone segmentation and prediction of missing tooth region for dental implant planning.

Recent studies have shown that dental implants have high long-term survival rates, indicating their effectiveness compared to other treatments. However, there is still a concern regarding treatment failure. Deep learning methods, specifically U-Net models, have been effectively applied to analyze medical and dental images. This study aims to utilize U-Net models to segment bone in regions where teeth are missing in cone-beam computerized tomography (CBCT) scans and predict the positions of implants. The proposed models were applied to a CBCT dataset of Taibah University Dental Hospital (TUDH) patients between 2018 and 2023. They were evaluated using different performance metrics and validated by a domain expert. The experimental results demonstrated outstanding performance in terms of dice, precision, and recall for bone segmentation (0.93, 0.94, and 0.93, respectively) with a low volume error (0.01). The proposed models offer promising automated dental implant planning for dental implantologists.

Increasing Provider Utilization of a Seizure Action Plan in the Outpatient Setting.

OBJECTIVES: A seizure action plan (SAP) is a powerful tool that provides actionable information for caregivers during seizures. Guidelines have expressed the need for individualized SAPs. Our quality improvement team aimed to increase implementation of an SAP within a pediatric tertiary center, initially among epilepsy providers and expanded to all neurology providers. METHODS: Process changes were implemented using Plan-Do-Study-Act cycles and data were evaluated monthly using control charts. The team focused on tracking patients who received SAPs and identified opportunities for improvement, including reminders within the electronic medical record, and standardizing clinic processes. A secondary analysis was performed to trend emergency department (ED) use among our patient population. RESULTS: The SAP utilization rate among epilepsy providers increased from a baseline of 39% to 78% by December 2019 and reached the goal of 85% by June 2020, with a further increase to 92% by February 2022 and maintained. The SAP utilization rate among general neurology providers increased from 43% in 2018 to 85% by July 2020, and further increased to 93% by February 2022 and maintained. ED visits of established patients with epilepsy decreased from a baseline of 10.2 per 1000 to 7.5 per 1000. CONCLUSIONS: Quality improvement methodologies increased the utilization of a standardized SAP within neurology outpatient care centers. The SAP is a simplified tool that allows patients and providers to navigate a complex health care system. The utility of an SAP may potentially extend to minimizing unnecessary ED visits.

A randomized controlled trial of shared decision-making treatment planning process to enhance shared decision-making in patients with MBC.

PURPOSE: Opportunities exist for patients with metastatic breast cancer (MBC) to engage in shared decision-making (SDM). Presenting patient-reported data, including patient treatment preferences, to oncologists before or during a treatment plan decision may improve patient engagement in treatment decisions. METHODS: This randomized controlled trial evaluated the standard-of-care treatment planning process vs. a novel treatment planning process focused on SDM, which included oncologist review of patient-reported treatment preferences, prior to or during treatment decisions among women with MBC. The primary outcome was patient perception of shared decision-making. Secondary outcomes included patient activation, treatment satisfaction, physician perception of treatment decision-making, and use of treatment plans. RESULTS: Among the 109 evaluable patients from December 2018 to June 2022, 28% were Black and 12% lived in a highly disadvantaged neighborhood. Although not reaching statistical significance, patients in the intervention arm perceived SDM more often than patients in the control arm (63% vs. 59%; Cramer's V = 0.05; OR 1.19; 95% CI 0.55-2.57). Among patients in the intervention arm, 31% were at the highest level of patient activation compared to 19% of those in the control arm (V = 0.18). In 82% of decisions, the oncologist agreed that the patient-reported data helped them engage in SDM. In 45% of decision, they reported changing management due to patient-reported data. CONCLUSIONS: Oncologist engagement in the treatment planning process, with oncologist review of patient-reported data, is a promising approach to improve patient participation in treatment decisions which should be tested in larger studies. TRIAL REGISTRATION: NCT03806738.

Outcomes-Based Treatment Planning in Endodontics: Applying the Latest Evidence.

A comprehensive understanding of the factors that influence treatment outcomes is crucial in endodontic diagnosis and treatment planning. Having knowledge that takes into account dental and patient-related conditions when choosing procedures can help clinicians maximize the prognosis of natural teeth and reduce postoperative complications. That being said, the landscape of outcome studies in endodontics is continually evolving, presenting a challenge for many clinicians trying to stay current with the latest literature. This article reviews factors that influence the outcomes of the following endodontic therapies: primary root canal treatment, nonsurgical retreatment, and surgical retreatment. An emphasis is placed on the importance of considering preoperative and treatment-related factors as prognostic indicators before developing a treatment plan, with the ultimate goal of enhancing tooth durability and ensuring patient satisfaction.

Patient-specific reference model estimation for orthognathic surgical planning.

PURPOSE: Accurate estimation of reference bony shape models is fundamental for orthognathic surgical planning. Existing methods to derive this model are of two types: one determines the reference model by estimating the deformation field to correct the patient's deformed jaw, often introducing distortions in the predicted reference model; The other derives the reference model using a linear combination of their landmarks/vertices but overlooks the intricate nonlinear relationship between the subjects, compromising the model's precision and quality. METHODS: We have created a self-supervised learning framework to estimate the reference model. The core of this framework is a deep query network, which estimates the similarity scores between the patient's midface and those of the normal subjects in a high-dimensional space. Subsequently, it aggregates high-dimensional features of these subjects and projects these features back to 3D structures, ultimately achieving a patient-specific reference model. RESULTS: Our approach was trained using a dataset of 51 normal subjects and tested on 30 patient subjects to estimate their reference models. Performance assessment against the actual post-operative bone revealed a mean Chamfer distance error of 2.25 mm and an average surface distance error of 2.30 mm across the patient subjects. CONCLUSION: Our proposed method emphasizes the correlation between the patients and the normal subjects in a high-dimensional space, facilitating the generation of the patient-specific reference model. Both qualitative and quantitative results demonstrate its superiority over current state-of-the-art methods in reference model estimation.

[The OMAGE comprehension interview: a method for building patient-centered care plans]. / Entretien de compréhension Omage : une méthode pour élaborer des plans de soins centrés sur le patient.

OMAGE comprehension interviews (CIs) use a card game as a vehicle for active listening. CIs performed by training professionals revealed new information for 92% of patients. CIs seem to be an effective method for building patient-centered management plans, can be used by a wide range of health professionals and as prerequisites for medication reconciliation and patient education.

Applying Implementation Science to Identify Primary Care Providers' Enablers and Barriers to Using Survivorship Care Plans.

Primary care providers (PCPs) have been given the responsibility of managing the follow-up care of low-risk cancer survivors after they are discharged from the oncology center. Survivorship Care Plans (SCPs) were developed to facilitate this transition, but research indicates inconsistencies in how they are implemented. A detailed examination of enablers and barriers that influence their use by PCPs is needed to understand how to improve SCPs and ultimately facilitate cancer survivors' transition to primary care. An interview guide was developed based on the second version of the Theoretical Domains Framework (TDF-2). PCPs participated in semi-structured interviews. Qualitative content analysis was used to develop a codebook to code text into each of the 14 TDF-2 domains. Thematic analysis was also used to generate themes and subthemes. Thirteen PCPs completed the interview and identified the following barriers to SCP use: unfamiliarity with the side effects of cancer treatment (Knowledge), lack of clarity on the roles of different healthcare professionals (Social Professional Role and Identity), follow-up tasks being outside of scope of practice (Social Professional Role and Identity), increased workload, lack of options for psychosocial support for survivors, managing different electronic medical records systems, logistical issues with liaising with oncology (Environmental Context and Resources), and patient factors (Social Influences). PCPs value the information provided in SCPs and found the follow-up guidance provided to be most helpful. However, SCP use could be improved through streamlining methods of communication and collaboration between oncology centres and community-based primary care settings.

Finding a care plan that suits everyone.

In a recent survey, Hannah Capon asked the owners of arthritic dogs what they would like vets to do differently. She'll be using her findings to help delegates at BVA Live better understand the owner experience of veterinary care and contextualise their approach accordingly.

Incorporating clinician insight and care plans into an audit and feedback initiative for antipsychotic prescribing to Medicaid-enrolled youth in Philadelphia.

BACKGROUND: Audit and feedback (A/F), which include initiatives like report cards, have an inconsistent impact on clinicians' prescribing behavior. This may be attributable to their focus on aggregate prescribing measures, a one-size-fits-all approach, and the fact that A/F initiatives rarely engage with the clinicians they target. METHODS: In this study, we describe the development and delivery of a report card that summarized antipsychotic prescribing to publicly-insured youth in Philadelphia, which was introduced by a Medicaid managed care organization in 2020. In addition to measuring aggregate prescribing behavior, the report card included different elements of care plans, including whether youth were receiving polypharmacy, proper medication management, and the concurrent use of behavioral health outpatient services. The A/F initiative elicited feedback from clinicians, which we refer to as an "audit and feedback loop." We also evaluate the impact of the report card by comparing pre-post differences in prescribing measures for clinicians who received the report card with a group of clinicians who did not receive the report card. RESULTS: Report cards indicated that many youth who were prescribed antipsychotics were not receiving proper medication management or using behavioral health outpatient services alongside the antipsychotic prescription, but that polypharmacy was rare. In their feedback, clinicians who received report cards cited several challenges related to antipsychotic prescribing, such as the logistical difficulties of entering lab orders and family members' hesitancy to change care plans. The impact of the report card was mixed: there was a modest reduction in the share of youth receiving polypharmacy following the receipt of the report card, while other measures did not change. However, we documented a large reduction in the number of youth with one or more antipsychotic prescription fill among clinicians who received a report card. CONCLUSIONS: A/F initiatives are a common approach to improving the quality of care, and often target specific practices such as antipsychotic prescribing. Report cards are a low-cost and feasible intervention but there is room for quality improvement, such as adding measures that track medication management or eliciting feedback from clinicians who receive report cards. To ensure that the benefits of antipsychotic prescribing outweigh its risks, it is important to promote quality and safety of antipsychotic prescribing within a broader care plan.

Accuracy of implant placement using a mixed reality-based dynamic navigation system versus static computer-assisted and freehand surgery: An in Vitro study.

PURPOSE: This in vitro study aimed to compare the accuracy of dental implant placement in partially edentulous maxillary models using a mixed reality-based dynamic navigation (MR-DN) system to conventional static computer-assisted implant surgery (s-CAIS) and a freehand (FH) method. METHODS: Forty-five partially edentulous models (with teeth missing in positions #15, #16 and #25) were assigned to three groups (15 per group). The same experienced operator performed the model surgeries using an MR-DN system (group 1), s-CAIS (group 2) and FH (group 3). In total, 135 dental implants were placed (45 per group). The primary outcomes were the linear coronal deviation (entry error; En), apical deviation (apex error; Ap), XY and Z deviations, and angular deviation (An) between the planned and actual (post-surgery) position of the implants in the models. These deviations were computed as the distances between the stereolithographic (STL) files for the planned implants and placed implants captured with an intraoral scanner. RESULTS: Across the three implant sites, the MR-DN system was significantly more accurate than the FH method (in XY, Z, En, Ap and An) and s-CAIS (in Z, Ap and An), respectively. However, S-CAIS was more accurate than MR-DN in XY, and no difference was found between MR-DN and s-CAIS in En. CONCLUSIONS: Within the limits of this study (in vitro design, only partially edentulous models), implant placement accuracy with MR-DN was superior to that of FH and similar to that of s-CAIS. STATEMENT OF CLINICAL RELEVANCE: In vitro, MR-DN showed greater accuracy in implant positioning than FH, and similar accuracy to s-CAIS: it could, therefore, represent a new option for the surgeon. However, clinical studies are needed to determine the feasibility of MR-DN.

Older people's goals of care in relation to frailty status-the COOP-study.

BACKGROUND: Literature relating older people's goals of care to their varying frailty status is scarce. OBJECTIVE: To investigate goals of care in case of acute and/or severe disease in relationship to frailty status among the general older population. METHOD: Older people aged ≥70 in the Netherlands completed a questionnaire. They were divided into three subgroups based on a self-reported Clinical Frailty Scale: fit (CFS 1-3), mildly frail (CFS 4-5) and severely frail (CFS 6-8). Seven goals were graded as unimportant (1-5), somewhat important (6-7) or very important (8-10): extending life, preserving quality of life (QoL), staying independent, relieving symptoms, supporting others, preventing hospital admission and preventing nursing home admission. RESULTS: Of the 1,278 participants (median age 76 years, 63% female), 57% was fit, 32% mildly frail and 12% severely frail. Overall, participants most frequently considered preventing nursing home admission as very important (87%), followed by staying independent (84%) and preserving QoL (83%), and least frequently considered extending life as very important (31%). All frailty subgroups reported similar preferences out of the surveyed goals as the overall study population. However, participants with a higher frailty status attached slightly less importance to each individual goal compared with fit participants (Ptrend-values ≤ 0.037). CONCLUSION: Preferred goals of care are not related to frailty status, while the importance ascribed to individual goals is slightly lower with higher frailty status. Future research should prioritise outcomes related to the shared goals of fit, mildly frail and severely frail older people to improve personalised medicine for older patients.