⚡ Quick Summary
This scoping review examined 1,506 studies on the application of machine learning (ML) in dentistry, identifying 280 relevant articles from 2018 to 2023. The findings highlight significant gaps in methodological rigor, particularly in model validation and bias assessment, which are crucial for the real-world adoption of ML technologies in dental care.
🔍 Key Details
- 📊 Dataset: 1,506 studies reviewed, 280 included
- 🧩 Specialties: Oral and maxillofacial radiology (27.5%), surgery (15.0%), general dentistry (14.3%)
- ⚙️ Focus: Majority on classification tasks (59.6%)
- 🏆 Key Gaps: 22.9% lacked clinical reference comparisons
🔑 Key Takeaways
- 🤖 Machine learning is increasingly utilized in dental diagnosis and treatment.
- 📉 Significant gaps exist in model validation and bias assessment.
- 🔍 Only 1.4% of studies focused on generative applications.
- ⚖️ Equity evaluation is essential for the adoption of ML in clinical settings.
- 🔄 Future research should emphasize reproducibility and error explainability.
- 📈 Calibration assessment is critical for real-world application.
- 🌐 Study published in PLOS Digital Health.
- 🆔 PMID: 40700462.
📚 Background
The integration of artificial intelligence (AI) and machine learning (ML) in healthcare has shown promising potential, particularly in enhancing decision-making processes. In dentistry, these technologies can aid in diagnosis, prognosis, and treatment planning. However, the effectiveness of these models is contingent upon their methodological rigor and transparency, which necessitates thorough evaluation.
🗒️ Study
This scoping review aimed to assess the methodological completeness of ML applications in dentistry by analyzing PubMed-indexed articles published between January 2018 and December 2023. Each study was evaluated using the TRIPOD + AI rubric, focusing on essential reporting elements such as data preprocessing, model validation, and clinical performance.
📈 Results
Out of the 1,506 studies identified, 280 met the inclusion criteria. The most represented specialties were oral and maxillofacial radiology (27.5%), surgery (15.0%), and general dentistry (14.3%). Alarmingly, 22.9% of the studies did not compare their models with a clinical reference standard or existing models, indicating a significant gap in validation practices.
🌍 Impact and Implications
The findings of this review underscore the transformative potential of machine learning in dental care. However, for these technologies to be effectively integrated into clinical practice, it is imperative to address the identified gaps in methodological rigor. Ensuring robust calibration assessments and equity evaluations will be crucial for the successful adoption of ML in dentistry, ultimately enhancing patient care and outcomes.
🔮 Conclusion
This scoping review highlights the critical role of machine learning in advancing dental practices while also revealing significant methodological shortcomings that must be addressed. As the field evolves, prioritizing rigorous validation and transparency will be essential for harnessing the full potential of AI technologies in dentistry. Continued research and collaboration will pave the way for a future where ML can significantly improve dental care delivery.
💬 Your comments
What are your thoughts on the integration of machine learning in dentistry? We would love to hear your insights! 💬 Share your comments below or connect with us on social media:
Machine learning in dentistry: a scoping review.
Abstract
Artificial intelligence (AI), specifically machine learning (ML), is increasingly applied in decision-making for dental diagnosis, prognosis, and treatment. However, the methodological completeness of published models has not been rigorously assessed. We performed a scoping review of PubMed-indexed articles (English, 1 January 2018‒31 December 2023) that used ML in any dental specialty. Each study was evaluated with the TRIPOD + AI rubric for key reporting elements such as data preprocessing, model validation, and clinical performance. Out of 1,506 identified studies, 280 met the inclusion criteria. Oral and maxillofacial radiology (27.5%), oral and maxillofacial surgery (15.0%), and general dentistry (14.3%) were the most represented specialties. Sixty-four studies (22.9%) lacked comparison with a clinical reference standard or existing model performing the same task. Most models focused on classification (59.6%), whereas generative applications were relatively rare (1.4%). Key gaps included limited assessment of model bias, poor outlier reporting, scarce calibration evaluation, low reproducibility, and restricted data access. ML could transform dental care, but robust calibration assessment and equity evaluation are critical for real-world adoption. Future research should prioritize error explainability, outlier reporting, reproducibility, fairness, and prospective validation.
Author: [‘Lakhotia S’, ‘Godrej H’, ‘Kaur A’, ‘Nutakki CS’, ‘Mun M’, ‘Eber P’, ‘Anthony Celi L’]
Journal: PLOS Digit Health
Citation: Lakhotia S, et al. Machine learning in dentistry: a scoping review. Machine learning in dentistry: a scoping review. 2025; 4:e0000940. doi: 10.1371/journal.pdig.0000940