Article
Cost-effectiveness of artificial intelligence for proximal caries detection
Search Medline for
Authors
Published: | February 23, 2021 |
---|
Outline
Text
Background/research question: Artificial intelligence (AI) can assist dentists in image assessment, for example caries detection. The wider health and cost impact of employing AI for dental diagnostics has not yet been evaluated.
We compared the cost-effectiveness of proximal caries detection on bitewing radiographs with vs. without AI.
Methods: U-Net, a fully convolutional neural network had been trained, validated and tested on 3,293, 252 and 141 bitewing radiographs, respectively, on which four experienced dentists had marked carious lesions. The union of all pixels was defined as reference test. The data was divided into a training (3,293), validation (252) and test dataset (141). The performance of the trained neural network on the test dataset was compared against that of seven independent dentists using tooth-level accuracy metrics. Lesions were stratified for initial lesions (E1/E2/D1, presumed non-cavitated, receiving caries infiltration if detected) and advanced lesions (D2/D3, presumed cavitated, receiving restorative care if detected). A Markov model was used to simulate the consequences of true and false positive and negative detections and the subsequent decisions over the lifetime of the patients. A German mixed-payers’ perspective was adopted. Our health outcome was tooth retention years. Costs were measured in Euro 2020. Monte-Carlo-microsimulations, univariate and probabilistic sensitivity analyses were conducted. The incremental cost-effectiveness ratio (ICER) and the cost-effectiveness-acceptability at different willingness-to-pay-thresholds were quantified.
Results: AI showed an accuracy of 0.80; dentists’ mean accuracy was significantly lower at 0.71 (min-max: 0.61-0.78, p<0.05). AI was significantly more sensitive than dentists (0.75 versus 0.36 (0.19-0.65; p=0.006), while its specificity was not significantly lower (0.83 versus 0.91 (0.69-0.98; p>0.05)). In the base-case scenario, AI was more effective (tooth retention for a mean 64 (2.5-97.5%: 61-69 (65) years) and less costly (298 (244-367) Euro) than assessment without AI (62 (59-64) years; 322 (257-394 Euro). The ICER was -13.9 Euro/year, i.e. AI saved money at higher effectiveness. In the majority (>77%) of all cases AI was less costly and more effective.
Conclusion: Applying AI for caries detection is likely to be cost-effective, mainly as fewer lesions remain undetected. Notably, this cost-effectiveness requires dentists to manage detected early lesions non-restoratively.
Competing interests: FS, RG and JK are co-founders of a Charité startup on dental image analysis. The conduct, analysis and interpretation of this study and its findings was unrelated to this.