Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection
Open accessAbstract
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 versus without AI. U-Net, a fully convolutional neural network, had been trained, validated, and tested on 3,293, 252, and 141 bitewing radiographs, respectively, on which 4 experienced dentists had marked carious lesions (reference test). Lesions were stratified for initial lesions (E1/E2/D1, presumed noncavitated, 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 true- and false-negative detections, as well as the subsequent decisions over the lifetime of patients. A German mixed-payers perspective was adopted. Our health outcome was tooth retention years. Costs were measured in 2020 euro. Monte-Carlo microsimulations and 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. AI showed an accuracy of 0.80; dentists’ mean accuracy was significantly lower at 0.71 (minimum–maximum: 0.61–0.78, P < 0.05). AI was significantly more sensitive than dentists (0.75 vs. 0.36 [0.19–0.65]; P = 0.006), while its specificity was not significantly lower (0.83 vs. 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%: 61–65] y) and less costly (298 [244–367] euro) than assessment without AI (62 [59–64] y; 322 [257–394] euro). The ICER was −13.9 euro/y (i.e., AI saved money at higher effectiveness). In the majority (>77%) of all cases, AI was less costly and more effective. 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 nonrestoratively.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Other effectiveness metrics reported across studies included DALYs averted, diagnostic yield improvements, clinical event prevention, and years of life gained.
“other effectiveness metrics reported across studies included DALYs averted31, diagnostic yield improvements38, clinical event prevention34, and years of life gained22”
From Systematic review of cost effectiveness and budget impact of artificial intelligence in healthcare (2025) · cites this paper as [38]
The Results (Study Parameters) report that AI-assisted caries detection was more sensitive than detection without AI, supporting a diagnostic improvement. But Methods (Health Outcomes, Costs, and Discounting) defines the study’s effectiveness metric as tooth-retention years, not diagnostic yield; diagnostic accuracy was an input to the analysis. (LLM, conf=0.85)
Experimental — accuracy not yet measuredSchwendicke et al. demonstrated that higher sensitivity (0.75 vs. 0.36 for traditional assessments) led to earlier interventions and a corresponding reduction in long-term treatment costs.
“Schwendicke et al.38 demonstrated that higher sensitivity (0.75 vs. 0.36 for traditional assessments) led to earlier interventions and a corresponding reduction in long-term treatment costs38.”
From Systematic review of cost effectiveness and budget impact of artificial intelligence in healthcare (2025) · cites this paper as Schwendicke et al.38
The Methods (Input Variables) report dentists’ sensitivity of 0.36 in a sensitivity analysis, and the paper reports AI sensitivity of 0.75. The Discussion and Results (Sensitivity Analyses) support lower modeled long-term costs through earlier detection and effective arresting therapy, but the claim omits a crucial condition: when early lesions were treated restoratively, AI was more costly and less effective. (LLM, conf=0.88)
Experimental — accuracy not yet measuredSchwendicke et al. reported that AI-assisted dental caries detection improved tooth retention (64 years vs. 62 years) and achieved an ICER of -€13.9 per additional year of tooth retention.
“Schwendicke et al.38 reported that AI-assisted dental caries detection improved tooth retention (64 years vs. 62 years) and achieved an ICER of –€13.9 per additional year of tooth retention”
From Systematic review of cost effectiveness and budget impact of artificial intelligence in healthcare (2025) · cites this paper as Schwendicke et al.38
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 25
- Baelum V Hintze H Wenzel A Danielsen B Nyvad B. 2012. Implications of caries diagnostic strategies for clinical management decisions. Community Dent Oral Epidemiol. 40(3): 257– 266. 22103270
- Briggs AH O’Brien BJ Blackhouse G. 2002. Thinking outside the box: recent advances in the analysis and presentation of uncertainty in cost-effectiveness studies. Annu Rev Public Health. 23(1): 377– 401. 11910068
- Burke FJT Lucarotti PSK. 2009. Ten-year outcome of crowns placed within the General Dental Services in England and Wales. J Dent. 37(1): 12– 24. 18487003
- Ferrari M Vichi A Fadda GM Cagidiaco MC Tay FR Breschi L Polimeni A Goracci C. 2012. A randomized controlled trial of endodontically treated and restored premolars. J Dent Res. 91(7 suppl): S72– S78. 22699672
- Frencken JE Innes NP Schwendicke F. 2016. Managing carious lesions: why do we need consensus on terminology and clinical recommendations on carious tissue removal? Adv Dent Res. 28(2): 46– 48. 27099356
- Garcia Cantu A Gehrung S Krois J Chaurasia A Gomez Rossi J Gaudin R Elhennawy K Schwendicke F. 2020. Detecting caries lesions of different radiographic extension on bitewings using deep learning. J Dent. 100: 103425. 32634466
- Gimenez T Piovesan C Braga MM Raggio DP Deery C Ricketts DN Ekstrand KR Mendes FM. 2015. Visual inspection for caries detection: a systematic review and meta-analysis. J Dent Res. 94(7): 895– 904. 25994176
- Husereau D Drummond M Petrou S Carswell C Moher D Greenberg D Augustovski F Briggs AH Mauskopf J Loder E. 2013. Consolidated Health Economic Evaluation Reporting Standards (CHEERS)–explanation and elaboration: a report of the ISPOR Health Economic Evaluation Publication Guidelines Good Reporting Practices Task Force. Value Health. 16(2): 231– 250. 23538175
- Kassebaum NJ Smith AGC Bernabé E Fleming TD Reynolds AE Vos T Murray CJL Marcenes W Abyu GY Alsharif U, et al.; GBD 2015 Oral Health Collaborators. 2017. Global, regional, and national prevalence, incidence, and disability-adjusted life years for oral conditions for 195 countries, 1990–2015: a systematic analysis for the global burden of diseases, injuries, and risk factors. J Dent Res. 96(4): 380– 387. 28792274 PMC5912207
- LeCun Y Bengio Y Hinton G. 2015. Deep learning. Nature. 521(7553): 436– 444. 26017442
- Lumley PJ Lucarotti PSK Burke FJT. 2008. Ten-year outcome of root fillings in the General Dental Services in England and Wales. Int Endod J. 41(7): 577– 585. 18479376
- Ng YL Mann V Gulabivala K. 2008. Outcome of secondary root canal treatment: a systematic review of the literature. Int Endod J. 41(12): 1026– 1046. 19133093
- Pallesen U van Dijken JWV Halken J Hallonsten A-L Höigaard R. 2013. Longevity of posterior resin composite restorations in permanent teeth in public dental health service: a prospective 8 years follow up. J Dent. 41(4): 297– 306. 23228499
- Schwendicke F Engel AS Graetz C. 2018. Long-term treatment costs of chronic periodontitis patients in Germany. J Clin Periodontol. 45(9): 1069– 1077. 29981185
- Schwendicke F Golla T Dreher M Krois J. 2019. Convolutional neural networks for dental image diagnostics: a scoping review. J Dent. 91: 103226. 31704386
- Schwendicke F Graetz C Stolpe M Dorfer CE. 2014. Retaining or replacing molars with furcation involvement: a cost-effectiveness comparison of different strategies. J Clin Periodontol. 41(11): 1090– 1097. 25255893
- Schwendicke F Meyer-Lueckel H Stolpe M Dörfer CE Paris S. 2014. Costs and effectiveness of treatment alternatives for proximal caries lesions. PLoS One. 9(1): e86992. 24475208 PMC3903601
- Schwendicke F Paris S Stolpe M. 2015. Detection and treatment of proximal caries lesions: milieu-specific cost-effectiveness analysis. J Dent. 43(6): 647– 655. 25862278
- Schwendicke F Splieth C Breschi L Banerjee A Fontana M Paris S Burrow MF Crombie F Page LF Gaton-Hernandez P, et al. 2019. When to intervene in the caries process? An expert Delphi consensus statement. Clin Oral Investig. 23(10): 3691– 3703. 31444695
- Schwendicke F Stolpe M Innes N. 2016. Conventional treatment, hall technique or immediate pulpotomy for carious primary molars: a cost-effectiveness analysis. Int Endod J. 49(9): 817– 826. 26331379
- Schwendicke F Stolpe M Meyer-Lückel H Paris S Dörfer C. 2013. Cost-effectiveness of one- and two-step incomplete and complete excavation. J Dent Res. 92(10): 880– 887. 23945975
- Schwendicke F Stolpe M Meyer-Lueckel H Paris S. 2015. Detecting and treating occlusal caries lesions: a cost-effectiveness analysis. J Dent Res. 94(2): 272– 280. 25503613 PMC4438735
- Schwendicke F Tzschoppe M Paris S. 2015. Radiographic caries detection: a systematic review and meta-analysis. J Dent. 43(8): 924– 933. 25724114
- Torabinejad M Anderson P Bader J Brown LJ Chen LH Goodacre CJ Kattadiyil MT Kutsenko D Lozada J Patel R, et al. 2007. Outcomes of root canal treatment and restoration, implant-supported single crowns, fixed partial dentures, and extraction without replacement: a systematic review. J Prosthet Dent. 98(4): 285– 311. 17936128
- Torabinejad M Corr R Handysides R Shabahang S. 2009. Outcomes of nonsurgical retreatment and endodontic surgery: a systematic review. J Endod. 35(7): 930– 937. 19567310
Cited by
Sorted by citations
Lekadir, K., Frangi, A. F., Porras, A. R., Glocker, B., Cintas, C., Langlotz, C. P., Weicken, E., Asselbergs, F. W., Prior, F., Collins, G. S., et al. (2025) · BMJ · doi:10.1136/bmj-2024-081554 · Cited by 957 · see citing works
Artificial intelligence in dentistry-a review
Ding, H., Wu, J., Zhao, W., Matinlinna, J. P., Burrow, M. F., & Tsoi, J. K. H. (2023) · Frontiers in Dental Medicine · doi:10.3389/fdmed.2023.1085251 · Cited by 297 · see citing works
Gomez Rossi, J., Rojas-Perilla, N., Krois, J., & Schwendicke, F. (2022) · JAMA Network Open · doi:10.1001/jamanetworkopen.2022.0269 · Cited by 141 · see citing works
Self-citationSystematic review of cost effectiveness and budget impact of artificial intelligence in healthcare
El Arab, R. A., & Al Moosa, O. A. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01722-y · Cited by 149 · see citing works
Artificial intelligence for diagnostics in radiology practice: a rapid systematic scoping review
Lawrence, R., Dodsworth, E., Massou, E., Sherlaw-Johnson, C., Ramsay, A. I. G., Walton, H., O'Regan, T., Gleeson, F., Crellin, N., Herbert, K., et al. (2025) · eClinicalMedicine · doi:10.1016/j.eclinm.2025.103228 · Cited by 69 · see citing works
Machine Learning for Health: Algorithm Auditing & Quality Control
Oala, L., Murchison, A. G., Balachandran, P., Choudhary, S., Fehr, J., Leite, A. W., Goldschmidt, P. G., Johner, C., Schörverth, E. D. M., Nakasi, R., et al. (2021) · Journal of Medical Systems · doi:10.1007/s10916-021-01783-y · Cited by 48 · see citing works
Self-citation
- Authors
- Schwendicke, F., Rossi, J. G., Göstemeyer, G., Elhennawy, K., Cantu, A. G., Gaudin, R., Chaurasia, A., Gehrung, S., & Krois, J.
- Affiliations
- Charité – Universitätsmedizin Berlin (DE)
- King George's Medical University (IN)
- Corresponding author
- Schwendicke, F.
- Venue
- Journal of Dental Research
- Publisher
- SAGE Publications
- Published
- 2020-11-16
- Volume
- 100
- Issue
- 4
- Pages
- 369-376
- ISSN
- 0022-0345 (ISSN-L)
- 1544-0591
- PMC
- PMC7985854
- OpenAlex
- W3100431970
- Cited by
- 152
- References
- 0
- Citations by year
- 2026: 27 · 2025: 33 · 2024: 30 · 2023: 22 · 2022: 26 · 2021: 14
- FWCI
- 16.13
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Journal of Dental Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Dentistry › Oral Surgery › Dental Radiography and Imaging
- Health Sciences › Dentistry › Periodontics › Dental Health and Care Utilization
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Health Systems, Economic Evaluations, Quality of Life
- Keywords
- artificial intelligence, bitewing radiography, U-Net, convolutional neural networks, dental diagnosis, cost-effectiveness, tooth preservation, Markov model, sensitivity analysis, caries infiltration, German health insurance, incremental cost-effectiveness ratio, willingness-to-pay threshold, microsimulation
- MeSH terms
- Artificial Intelligence, Cost-Benefit Analysis, Dental Caries, Dental Caries Susceptibility, Humans, Monte Carlo Method
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
