RESUMO
INTRODUCTION: A growing number of studies on diagnostic imaging show superior efficiency and accuracy of computer-aided diagnostic systems compared to those of certified dentists. This methodological systematic review aimed to evaluate the different methodological approaches used by studies focusing on machine learning and deep learning that have used radiographic databases to classify, detect, and segment dental caries. METHODS: The protocol was registered in PROSPERO before data collection (CRD42022348097). Literature research was performed in MEDLINE, Embase, IEEE Xplore, and Web of Science until December 2022, without language restrictions. Studies and surveys using a dental radiographic database for the classification, detection, or segmentation of carious lesions were sought. Records deemed eligible were retrieved and further assessed for inclusion by two reviewers who resolved any discrepancies through consensus. A third reviewer was consulted when any disagreements or discrepancies persisted between the two reviewers. After data extraction, the same reviewers assessed the methodological quality using the CLAIM and QUADAS-AI checklists. RESULTS: After screening 325 articles, 35 studies were eligible and included. The bitewing was the most commonly used radiograph (n = 17) at the time when detection (n = 15) was the most explored computer vision task. The sample sizes used ranged from 95 to 38,437, while the augmented training set ranged from 300 to 315,786. Convolutional neural network was the most commonly used model. The mean completeness of CLAIM items was 49% (SD ± 34%). The applicability of the CLAIM checklist items revealed several weaknesses in the methodology of the selected studies: most of the studies were monocentric, and only 9% of them used an external test set when evaluating the model's performance. The QUADAS-AI tool revealed that only 43% of the studies included in this systematic review were at low risk of bias concerning the standard reference domain. CONCLUSION: This review demonstrates that the overall scientific quality of studies conducted to feed artificial intelligence algorithms is low. Some improvement in the design and validation of studies can be made with the development of a standardized guideline for the reproducibility and generalizability of results and, thus, their clinical applications.
Assuntos
Inteligência Artificial , Cárie Dentária , Humanos , Cárie Dentária/diagnóstico por imagem , Bases de Dados Factuais , Aprendizado Profundo , Aprendizado de Máquina , Radiografia Dentária/métodosRESUMO
OBJECTIVES: A national questionnaire study was performed to document knowledge and opinions of French dental students (FDSs) about minimal intervention (MI) in dentistry especially caries risk assessment (CRA) and dental sealants (DSs). MATERIALS AND METHODS: A questionnaire was administered to the fifth-year dental FDSs (n = 1370) from the 16 French dental schools. Descriptive and statistical analyses were performed. RESULTS: The response rate was 84.5%. A large majority of respondents (87.8%) linked MI with minimally invasive dentistry and 77.4% considered MI as a concept based on prevention. About 80% stated they use CRA in clinical practice, mostly without any specific form. If 80.4% of the respondents would base their treatment plans on CRA, only 55.1% would regularly plan preventive regimens according to individual risk level. However, while 96.6% declared they perform preventive DSs, only 44.3% considered therapeutic sealants as a routine treatment. Although 75.1% of FDSs stated that they had sufficient learning and training related to CRA, 55.9% thought that they need further education about preventive and therapeutic DSs. CONCLUSION: Although FDSs seem to be aware of the importance of CRA and preventive strategies, this study shows the need to harmonize the teaching in cariology according to the latest European recommendations. CLINICAL RELEVANCE: A national questionnaire study showed variability towards knowledge and opinions of FDSs related to MI in cariology. This may impact care provisions in their future professional life showing the urgent need to harmonize the teaching of MI in cariology in France.
Assuntos
Cárie Dentária , Selantes de Fossas e Fissuras , Cárie Dentária/prevenção & controle , Educação em Odontologia , Humanos , Medição de Risco , Estudantes de OdontologiaRESUMO
BACKGROUND: During interventions for deep caries lesions without severe symptoms, preserving pulpal vitality is important to ensure treatment success, improve organ prognosis, and decrease cost-effectiveness. Current pre-operative radiographs allow visual estimation but not accurate measurement of lesion depth. PURPOSE: Investigate the ability of ratio 'remaining/total dentin thickness' (RDT/TDT, as determined on pre-operative radiographs) to predict pulp exposure during excavation. METHODS: This retrospective study (January 2018-June 2020) analyzed data on 360 patients. Four independent raters examined standard pre-operative radiographs and their contrasted versions. Lines put at the dentino-enamel junction, the floor of the carious lesion, and the pulp chamber wall allowed deriving RDT/TDT. Inter-rater agreements and concordance were assessed. A logistic regression accounting for measurement errors provided odds ratios that estimated the ability of the RDT/TDT to predict pulp exposure. RESULTS: The median RDT/TDT ratio ranges were 16.8-26.5% on standard and 16.2-24.6% on contrasted radiographs. Inter-rater agreements on RDT/TDT were rather poor and inter-rater reliability was low and similar in standard and contrasted radiographs: the concordance correlation coefficients (95% CIs) were estimated at 0.46 (0.40; 0.51) and 0.46 (0.40; 0.52), respectively. The risk of pulp exposure increased by 2.5 times [odds ratio (95% CI) 2.57 (2.06; 3.20)] per 10-point decrease of the ratio on standard radiographs vs. 4.15 (3.15; 5.46) on contrasted radiographs. CONCLUSION: RDT/TDT ratio is potentially helpful in predicting pulp exposure. However, the measurement errors on RDT and TDT being non-negligible and the interrater agreements poor, there is still place for advances through development of an automated process that will improve reliability and reproducibility of pulp exposure risk assessment. CLINICAL TRIAL: Trial registration number. ClinicalTrials.gov NCT04607395, October 29, 2020.
Assuntos
Cárie Dentária , Dentina , Cárie Dentária/diagnóstico por imagem , Cárie Dentária/terapia , Humanos , Radiografia , Reprodutibilidade dos Testes , Estudos RetrospectivosRESUMO
PURPOSE: To investigate the practices, knowledge and opinions of French dental students (FDSs) in various domains of minimal intervention (MI) in cariology. MATERIALS AND METHODS: A cross-sectional, questionnaire-based study was conducted in spring 2018 among all fifth-year French dental students (FDSs) from the 16 French dental schools. The present article focuses on restorative management. Statistical analyses (descriptive, chi-squared) were performed. RESULTS: The response rate was 84.5%. Overall, 97.4% of respondents would have operatively intervened for proximal and 83% for occlusal carious lesions, respectively, while non-or micro-invasive intervention would have been possible. Interestingly, 15% would completely open the occlusal fissures. For both occlusal and proximal lesions requiring a restoration, composite resin was indicated by over 95% of the respondents. In a clinical case, 51.6% of FDSs who rightly diagnosed an enamel carious lesion would operatively intervene. When FDSs could not diagnose the type of carious lesions, a high proportion of invasive actions were also reported (40%). FDSs who read scientific articles were more likely to consider the high importance of not filling sound teeth unnecessarily (p = 0.033). CONCLUSION: FDSs do not have sufficient awareness of MI guidelines regarding occlusal and proximal restorative thresholds. Efforts are required in dental schools to teach FDSs to postpone invasive/restorative strategies to later stages of carious progression. There is a need to strengthen prevention techniques and non-invasive options in the teaching of MI in cariology.
Assuntos
Cárie Dentária , Restauração Dentária Permanente , Estudos Transversais , Cárie Dentária/prevenção & controle , Dentina , Humanos , Estudantes de OdontologiaRESUMO
PURPOSE: A questionnaire survey was recently undertaken among French dental students (FDSs) to investigate their practices, knowledge and opinions in various domains of minimal intervention (MI) in cariology. The present work focuses on management of deep carious lesions (DCLs). MATERIALS AND METHODS: The questionnaire was administered (Spring 2018) to all the fifth-year students of the 16 French dental schools. Descriptive analyses were performed. RESULTS: Among 1370 FDSs (response rate: 84.5%), hardness was the most commonly reported criterion for assessing the endpoint of carious tissue removal (53.9%), followed by firm dentin (40.0%). Regarding FDSs' opinion of leaving carious dentine under a restoration, 41.9% of the respondents agreed that carious tissues should always be removed completely. For an asymptomatic tooth with DCLs and exposed pulp, direct pulp capping was mainly chosen (93.9%). In a clinical case correctly diagnosed as a reversible pulpitis by 79.7% of respondents, nearly half of FDSs chose a one-step complete excavation (48.3%) followed by selective excavation (25.1%), then two-step complete excavation (20.9%) and a minority (5.7%) opted for pulpal therapy (biopulpotomy or endodontic treatment). CONCLUSION: The present results suggest an inadequate dissemination of MI concepts among FDSs towards DCL management. The present results show the need for a harmonisation and a reinforcement of teaching evidence-based MI according to the latest European recommendations.