Introduction: Open‐source generative artificial intelligence (AI) applications are fast‐transforming access to information and allow students to prepare assignments and offer quite accurate responses to a wide range of exam questions which are routinely used in assessments of students across the board including undergraduate dental students. This study aims to evaluate the performance of Chat Generative Pre‐trained Transformer (ChatGPT), a generative AI‐based application, on a wide range of assessments used in contemporary healthcare education and discusses the implications for undergraduate dental education.Materials and Methods: This was an exploratory study investigating the accuracy of ChatGPT to attempt a range of recognised assessments in healthcare education curricula. A total of 50 independent items encompassing 50 different learning outcomes (n = 10 per item) were developed by the research team. These included 10 separate items based on each of the five commonly used question formats including multiple‐choice questions (MCQs); short‐answer questions (SAQs); short essay questions (SEQs); single true/false questions; and fill in the blanks items. Chat GPT was used to attempt each of these 50 questions. In addition, ChatGPT was used to generate reflective reports based on multisource feedback; research methodology; and critical appraisal of the literature.Results: ChatGPT application provided accurate responses to majority of knowledge‐based assessments based on MCQs, SAQs, SEQs, true/false and fill in the blanks items. However, it was only able to answer text‐based questions and did not allow processing of questions based on images. Responses generated to written assignments were also satisfactory apart from those for critical appraisal of literature. Word count was the key limitation observed in outputs generated by the free version of ChatGPT.Conclusion: Notwithstanding their current limitations, generative AI‐based applications have the potential to revolutionise virtual learning. Instead of treating it as a threat, healthcare educators need to adapt teaching and assessments in medical and dental education to the benefits of the learners while mitigating against dishonest use of AI‐based technology.
Dentists could fail to notice periapical lesions (PLs) while examining panoramic radiographs. Accordingly, this study aimed to develop an artificial intelligence (AI) designed to address this problem. Materials and methods: a total of 18618 periapical root areas (PRA) on 713 panoramic radiographs were annotated and classified as having or not having PLs. An AI model consisting of two convolutional neural networks (CNNs), a detector and a classifier, was trained on the images. The detector localized PRAs using a bounding-box-based object detection model, while the classifier classified the extracted PRAs as PL or not-PL using a fine-tuned CNN. The classifier was trained and validated on a balanced subset of the original dataset that included 3249 PRAs, and tested on 707 PRAs. Results: the detector achieved an average precision of 74.95%, while the classifier accuracy, sensitivity and specificity were 84%, 81% and 86%, respectively. When integrating both detection and classification models, the proposed method accuracy, sensitivity, and specificity were 84.6%, 72.2%, and 85.6%, respectively. Conclusion: a two-stage CNN model consisting of a detector and a classifier can successfully detect periapical lesions on panoramic radiographs.
Background: In previous studies, COVID-19 complications were reported to be associated with periodontitis. Accordingly, this study was designed to test the hypothesis that a history of periodontal therapy could be associated with lower risk of COVID-19 complications. Methods: A case–control study was performed using the medical health records of COVID-19 patients in the State of Qatar between March 2020 and February 2021 and dental records between January 2017 and December 2021. Cases were defined as COVID-19 patients who suffered complications (death, ICU admissions and/or mechanical ventilation); controls were COVID-19 patients who recovered without major complications. Associations between a history of periodontal therapy and COVID-19 complications were analysed using logistic regression models adjusted for demographic and medical factors. Blood parameters were compared using Kruskal–Wallis test. Results: In total, 1,325 patients were included. Adjusted odds ratio (AOR) analysis revealed that non-treated periodontitis was associated with significant risk of need for mechanical ventilation (AOR = 3.91, 95% CI 1.21–12.57, p = 0.022) compared to periodontally healthy patients, while treated periodontitis was not (AOR = 1.28, 95% CI 0.25–6.58, p = 0.768). Blood analyses revealed that periodontitis patients with a history of periodontal therapy had significantly lower levels of D-dimer and Ferritin than non-treated periodontitis patients. Conclusion: Among COVID-19 patients with periodontal bone loss, only those that have not received periodontal therapy had higher risk of need for assisted ventilation. COVID-19 patients with a history of periodontal therapy were associated with significantly lower D-dimer levels than those without recent records of periodontal therapy. Clinical relevance: The fact that patients with treated periodontitis were less likely to suffer COVID-19 complications than non-treated ones further strengthen the hypothesis linking periodontitis to COVID-19 complications and suggests that managing periodontitis could help reduce the risk for COVID-19 complications, although future research is needed to verify this.
Background and Purpose: Open-source Artificial intelligence (AI) applications are fast transforming access to information and allow students to prepare assignments and offer quite accurate responses to a wide range of exam questions which are routinely used in assessments of students across the board including undergraduate dental students. This study aims to evaluate the performance ChatGPT, an AI-based application, on a wide range of dental assessments and discusses the implications for undergraduate dental education. Methods: This was an exploratory study investigating the accuracy of ChatGPT to attempt a range of recognized assessments in undergraduate dental curricula. ChatGPT was used to attempt ten items based on each of the five commonly used question formats including single-best answer (SBA) multiple-choice questions (MCQs); short answer questions (SAQs); short essay questions (SEQs); True/False questions and fill in the blanks items. In addition, ChatGPT was used to generate reflective reports based on multisource feedback (MSF); research methodology; critical appraisal of the literature. Results: ChatGPT application provided accurate responses to majority of knowledge-based assessments based on MCQs, SAQs, SEQs, Tue/False and fill in the blanks items. However, it was only able to answer text-based questions and did not allow processing of questions based on images. Responses generated to written assignments were also of good quality apart from those for critical appraisal of literature. Word count was the key limitation observed in outputs by ChatGPT as it was only able to produce reports limited to approximately 650 words. Conclusion: Notwithstanding their current limitations, AI-based applications have the potential to revolutionize virtual learning. Instead of treating it as a threat, dental educators need to adapt teaching and assessments in dental education to the benefits of the learners whilst mitigating against dishonest use of AI-based applications.
10 May 2022 in European Journal of Dental Education
Aims: Web‐based digital assessment platforms offer several benefits for educational providers. The aims of this study were to evaluate digital assessment platforms suitable for design, delivery and quality assurance of assessments in dental education to facilitate informed choices by educational providers.Methods: The study was based on an online cross‐sectional survey. A questionnaire was designed to include relevant details of providers, types of assessments offered, post‐assessment psychometrics, remote proctoring, integration with digital learning platforms faculty training, and indicative costs of services. Following a google search, 25 potential providers of digital assessment software were identified and contacted by email.Results: Ten companies responded to the questionnaire. All providers, except one, reported extensive experience in delivering high‐stake assessments for programs in dentistry, medicine and allied health professions. All companies confirmed availability of a wide variety of assessment formats and also offer remote proctoring either directly or through third parties. Indicative costs of different assessment platforms were also provided.Conclusion: This paper underscores the need for dental institutions to make informed decisions when choosing the most appropriate digital assessment platforms to suit their educational needs. It also provides a snapshot of services offered by commercial providers of assessment platforms. The Association for Dental Education in Europe can serve as a central hub to guide dental institutions on making informed choices for suitable assessment platforms to address their needs.
Cephalometric analysis is essential for the diagnosis and treatment planning of orthodontics. In lateral cephalograms, however, the manual detection of anatomical landmarks is a time-consuming procedure. Deep learning solutions hold the potential to address the time constraints associated with certain tasks; however, concerns regarding their performances have been observed. To address this critical issue, we propose an end-to-end cascaded deep learning framework (Self-CephaloNet) for the task, which demonstrates benchmark performance over the ISBI 2015 dataset in predicting 19 cephalometric landmarks. Due to their adaptive nodal capabilities, Self-ONN (self-operational neural networks) demonstrates superior learning performance for complex feature spaces over conventional convolutional neural networks. To leverage this attribute, we introduce a novel self-bottleneck in the HRNetV2 (high-resolution network) backbone, which has exhibited benchmark performance on our landmark detection task. Our first-stage result surpasses previous studies, showcasing the efficacy of our singular end-to-end deep learning model, which achieves a remarkable 70.95% success rate in detecting cephalometric landmarks within a 2-mm range for the Test1 and Test2 datasets which are part of ISBI 2015 dataset. Moreover, the second stage significantly improves overall performance, yielding an impressive 82.25% average success rate for the datasets above within the same 2-mm distance. Furthermore, external validation has been conducted using the PKU cephalogram dataset. Our model demonstrates a commendable success rate of 75.95% within the 2-mm range.