The Potential of Artificial Intelligence in Prosthodontics: A Comprehensive Review.

Prosthodontics is a dental subspecialty that includes the preparation of dental prosthetics for missing or damaged teeth. It increasingly uses computer-assisted technologies for planning and preparing dental prosthetics. This study aims to present the findings from a systematic review of publications on artificial intelligence (AI) in prosthodontics to identify current trends and future opportunities. The review question was "What are the applications of AI in prosthodontics and how good is their performance in prosthodontics?" Electronic searching in the Web of Science, ScienceDirect, PubMed, and Cochrane Library was conducted. The search was limited to full text from January 2012 to January 2024. Quadas-2 was used for assessing quality and potential risk of bias for the selected studies. A total of 1925 studies were identified in the initial search. After removing the duplicates and applying exclusion criteria, a total of 30 studies were selected for this review. Results of the Quadas-2 assessment of included studies found that a total of 18.3% of studies were identified as low risk of bias studies, whereas 52.6% and 28.9% of included studies were identified as studies with high and unclear risk of bias, respectively. Although they are still developing, AI models have already shown promise in the areas of dental charting, tooth shade selection, automated restoration design, mapping the preparation finishing line, manufacturing casting optimization, predicting facial changes in patients wearing removable prostheses, and designing removable partial dentures.

Progress and limitations of current surface registration methods when measuring natural enamel wear.

OBJECTIVES: Our ability to detect dental wear on sequential scans is improving. This experiment aimed to determine if widely used surface registration methods were sufficiently accurate to distinguish differences between intervention groups on early wear lesions. METHODS: Baseline measurements were taken on human molar buccal enamel samples (n = 96) with a confocal scanning profilometer (Taicaan, UK). Samples were randomly assigned to subgroups of brushing (30 linear strokes 300 g force) before or after an acid challenge (10 min citric acid 0.3% immersion) for four test dentifrices (medium abrasivity NaF, medium abrasivity SnF2, low abrasivity NaF and a water control). Post-experimental profilometry was repeated. 3D step height was analysed using WearCompare (www.leedsdigitaldentistry.co.uk/wearcompare, UK). Percentage Sa change was calculated using Boddies (Taicaan Technologies, Southampton, UK). Data were analysed in SPSS (IBM, USA). RESULTS: The mean 3D step height (SD) observed when samples were brushed before the erosive challenge was -2.33 µm (3.46) and after was -3.5 µm (5.6). No significant differences were observed between timing of toothbrushing or dentifrice used. The mean % Sa change for the low abrasivity group (water control and low abrasivity NaF) was -10.7% (16.8%) and +28.0% (42.0%) for the medium abrasivity group (medium abrasivity NaF and SnF2). CONCLUSIONS: Detectable wear scars were observed at early stages of wear progression. However standard deviations were high and the experiment was underpowered to detect significant changes. Brushing with a low abrasivity dentifrice or water control produced a smoother surface whereas brushing with a high abrasivity dentifrice produced a rougher surface. CLINICAL SIGNIFICANCE: The methodology currently used to align sequential scans of teeth and measure change is too imprecise to measure early wear on natural enamel surfaces unless a large sample size is used. Further improvements are required before we can fully assess early wear processes on natural teeth using profilometry.