Effects of Artificial Intelligence (AI)-Assisted Dental Monitoring Intervention in Patients with Periodontitis: A Randomized Controlled Trial

Familiarity with ChatGPT Features Modifies Expectations and Learning Outcomes of Dental Students

OBJECTIVES

The number of approvals for AI-based systems is increasing rapidly, although AI clinical trial designs lack consideration of the impact of human-AI interaction. Aim of this work was to investigate how reading of an AI system (ChatGPT) features/descriptions could influence the willingness and expectations for use of this technology as well as dental students' learning performance.

METHODS

Dental students (N = 104) were asked to learn about side effects of drugs used in dental practice via reading recommended literature or ChatGPT. Expectations towards ChatGPT were measured by survey, before and after reading of a system features description, whilst learning outcomes were evaluated via pharmacology quiz.

RESULTS

Students who used ChatGPT (YG group) showed better results on the pharmacology quiz than students who neither read the description nor employed ChatGPT for learning (NN condition). Moreover, students who read the description of ChatGPT features yet did not use it (NG) showed better results on the pharmacology quiz compared with the NN condition, although none of them employed ChatGPT for learning. The NG students compared to the YG students had less trust in AI system assistance in learning, and after the AI system description reading, their expectations changed significantly, showing an association with quiz scores.

CONCLUSIONS

A majority of students in our cohort was reluctant to use ChatGPT. Furthermore, familarity (reading) with ChatGPT features appear to alter the expectations and enhance learning performance of students.suggesting an AI description-related cognitive bias. Hence the content description of ChatGPTshould be reviewed and verified prior to AI system use for educational purposes.

Effectiveness of dental monitoring system in orthodontics: A systematic review

BACKGROUND

Dental monitoring (DM) constitutes a recent technological advance for the remote monitoring of patients undergoing an orthodontic therapy. Especially in times of health emergency crisis, the possibility of relying on remote monitoring could be particularly useful.

OBJECTIVES

To assess the effectiveness of DM in orthodontic care.

ELIGIBILITY

Studies conducted on healthy patients undergoing orthodontic care where DM was applied, assessing a change in treatment duration, emergency appointments, in-office visits, orthodontic relapse, early detection of orthodontic emergencies and improvement of oral health status.

INFORMATION SOURCES

PubMed, Web of Science and Scopus were searched for publications until November 2022.

RISK OF BIAS

Quality assessment was performed with the STROBE Checklist.

DATA EXTRACTION

Data were extracted independently by two reviewers, and discrepancies were resolved with a third reviewer.

INCLUDED STUDIES

Out of 6887 records screened, 11 studies were included.

SYNTHESIS OF RESULTS

DM implemented to the standard orthodontic care was found to significantly decrease the number of in-office visits by 1.68-3.5 visits and showed a possible trend towards improvement of aligner fit. Conversely, evidence does not support a reduction of treatment duration and emergency appointments. The assessment of the remaining variables did not allow any qualitative synthesis.

CONCLUSIONS

This review highlighted that DM implemented to standard orthodontic care can significantly decrease the number of in-office visits and may potentially result in an improved aligner fit. Due to the low quality of most of the included studies and the heterogeneity of the orthodontic system where DM was applied, studies with different investigation team and rigorous methodology are advocated.

Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines

The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77-94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

Utilizing decision tree machine model to map dental students' preferred learning styles with suitable instructional strategies

BACKGROUND

Growing demand for student-centered learning (SCL) has been observed in higher education settings including dentistry. However, application of SCL in dental education is limited. Hence, this study aimed to facilitate SCL application in dentistry utilising a decision tree machine learning (ML) technique to map dental students' preferred learning styles (LS) with suitable instructional strategies (IS) as a promising approach to develop an IS recommender tool for dental students.

METHODS

A total of 255 dental students in Universiti Malaya completed the modified Index of Learning Styles (m-ILS) questionnaire containing 44 items which classified them into their respective LS. The collected data, referred to as dataset, was used in a decision tree supervised learning to automate the mapping of students' learning styles with the most suitable IS. The accuracy of the ML-empowered IS recommender tool was then evaluated.

RESULTS

The application of a decision tree model in the automation process of the mapping between LS (input) and IS (target output) was able to instantly generate the list of suitable instructional strategies for each dental student. The IS recommender tool demonstrated perfect precision and recall for overall model accuracy, suggesting a good sensitivity and specificity in mapping LS with IS.

CONCLUSION

The decision tree ML empowered IS recommender tool was proven to be accurate at matching dental students' learning styles with the relevant instructional strategies. This tool provides a workable path to planning student-centered lessons or modules that potentially will enhance the learning experience of the students.

DIGITAL DENTISTRY AND ITS IMPACT ON ORAL HEALTH-RELATED QUALITY OF LIFE

Over the past 50 years, digitization has gradually taken root in dentistry, starting with computer tomography in the 1970s. The most disruptive events in digital dentistry were the introduction of digital workflow and computer-aided manufacturing, which made new procedures and materials available for dental use. While the conventional lab-based workflow requires light or chemical curing under inconsistent and suboptimal conditions, computer-aided manufacturing allows for industrial-grade material, ensuring consistently high material quality. In addition, many other innovative, less disruptive, but relevant approaches have been developed in digital dentistry. These will have or already impact prevention, diagnosis, and therapy, thus impacting patients' oral health and, consequently, their oral health-related quality of life. Both software and hardware approaches attempt to maintain, restore, or optimize a patient's perceived oral health. This article outlines innovations in dentistry and their potential impact on patients' oral health-related quality of life in prevention and therapy. Furthermore, possible future developments and their potential implications are characterized.

Integrated Machine Learning and Bioinformatic Analyses Constructed a Network Between Mitochondrial Dysfunction and Immune Microenvironment of Periodontitis

Periodontitis is a prevalent and persistent inflammatory condition that impacts the supporting tissues of the teeth, including the gums and bone. Recent research indicates that mitochondrial dysfunction may be involved in the onset and advancement of periodontitis. The current work sought to reveal the interaction between mitochondrial dysfunction and the immune microenvironment in periodontitis. Public data were acquired from MitoCarta 3.0, Mitomap, and GEO databases. Hub markers were screened out by five integrated machine learning algorithms and verified by laboratory experiments. Single-cell sequencing data were utilized to unravel cell-type specific expression levels of hub genes. An artificial neural network model was constructed to discriminate periodontitis from healthy controls. An unsupervised consensus clustering algorithm revealed mitochondrial dysfunction-related periodontitis subtypes. The immune and mitochondrial characteristics were calculated using CIBERSORTx and ssGSEA algorithms. Two hub mitochondria-related markers (CYP24A1 and HINT3) were identified. Single-cell sequencing data revealed that HINT3 was primarily expressed in dendritic cells, while CYP24A1 was mainly expressed in monocytes. The hub genes based artificial neural network model showed robust diagnostic performance. The unsupervised consensus clustering algorithm revealed two distinct mitochondrial phenotypes. The hub genes exhibited a strong correlation with the immune cell infiltration and mitochondrial respiratory chain complexes. The study identified two hub markers that may serve as potential targets for immunotherapy and provided a novel reference for future investigations into the function of mitochondria in periodontitis.

A Systematic Review of the Use of mHealth in Oral Health Education among Older Adults

Oral diseases are largely preventable. However, as the number of older adults is expected to increase, along with the high cost and various barriers to seeking continuous professional care, a sustainable approach is needed to assist older adults in maintaining their oral health. Mobile health (mHealth) technologies may facilitate oral disease prevention and management through oral health education. This review aims to provide an overview of existing evidence on using mHealth to promote oral health through education among older adults. A literature search was performed across five electronic databases. A total of five studies were identified, which provided low to moderate evidence to support using mHealth among older adults. The selected studies showed that mHealth could improve oral health management, oral health behavior, and oral health knowledge among older adults. However, more quality studies regarding using mHealth technologies in oral health management, oral health behavior, and oral health knowledge among older adults are needed.

Artificial Intelligence Systems Assisting in the Assessment of the Course and Retention of Orthodontic Treatment

This scoping review examines the contemporary applications of advanced artificial intelligence (AI) software in orthodontics, focusing on its potential to improve daily working protocols, but also highlighting its limitations. The aim of the review was to evaluate the accuracy and efficiency of current AI-based systems compared to conventional methods in diagnosing, assessing the progress of patients' treatment and follow-up stability. The researchers used various online databases and identified diagnostic software and dental monitoring software as the most studied software in contemporary orthodontics. The former can accurately identify anatomical landmarks used for cephalometric analysis, while the latter enables orthodontists to thoroughly monitor each patient, determine specific desired outcomes, track progress, and warn of potential changes in pre-existing pathology. However, there is limited evidence to assess the stability of treatment outcomes and relapse detection. The study concludes that AI is an effective tool for managing orthodontic treatment from diagnosis to retention, benefiting both patients and clinicians. Patients find the software easy to use and feel better cared for, while clinicians can make diagnoses more easily and assess compliance and damage to braces or aligners more quickly and frequently.