Bibliographic record
Abstract
Цитуйте українською у Ванкувер стилі: Кузик ІМ, Котельбан АВ. Використання штучного інтелекту в ортодонтії. Експериментальна і клінічна медицина. 2023;92(4):70-80. https://doi.org/10.35339/ekm.2023.92.4.kuk Архівовано: https://doi.org/10.5281/zenodo.15534372 Резюме Застосування штучного інтелекту (ШІ) в ортодонтії є дуже різноманітним й варіюється від ідентифікації анатомічних та патологічних структур зубо-щелепного апарату людини до підтримки прийняття складних рішень у плануванні ортодонтичного лікування. Метою даної роботи було проаналізувати сучасні погляди на використання методик та моделей штучного інтелекту в ортодонтії на основі проведення огляду літератури. Було опрацьовано наукові публікації різних наукометричних баз даних (PubMed, Scopus, Google Scolar та Web of Science) протягом останніх 5 років. Штучний інтелект є одним із найперспективніших інструментів завдяки високій точності та ефективності роботи. Практикуючі стоматологи зможуть використовувати його як додатковий інструмент для зменшення робочого навантаження. Однак для цього потрібна тісна кооперація комерційних продуктів ШІ з науковим співтовариством, подальші дослідження, включаючи рандомізовані клінічні випробування, з метою апробації та інтеграції цієї концепції в стоматологічній практиці. Ключові слова: стоматологія, діагностика, машинне навчання, цефалометрія. Cite in English in Vancouver style: Kuzyk IM, Kotelban AV. The use of artificial intelligence in orthodontics. Experimental and Clinical Medicine. 2023;92(4):70-80. https://doi.org/10.35339/ekm.2023.92.4.kuk [in Ukrainian]. Archived: https://doi.org/10.5281/zenodo.15534372 Abstract The application of Artificial Intelligence (AI) in orthodontics is very diverse and ranges from the identification of anatomical and pathological structures of the human dentition to support complex decision-making in orthodontic treatment planning. Its application has grown significantly in recent years, as reflected by the exponential increase in the number of scientific publications on the integration of artificial intelligence into everyday clinical practice. In many cases, AI can be seen as a valuable tool whose algorithms help dentists and clinicians analyze data from multiple sources of information. The purpose of this paper was to analyze current views on the use of artificial intelligence techniques and models in orthodontics based on a literature review. The scientific publications of various scientometric databases (PubMed, Scopus, Google Scolar, Web of Science, etc.) over the past 5 years were processed. Artificial intelligence is one of the most promising tools due to its high accuracy and efficiency. Given the current scientific dynamics in the field of AI, it can be assumed that AI will become an integral part of diagnostics and treatment planning in the near future. Practicing dentists will be able to use it as an additional tool to reduce their workload. However, this requires close cooperation of commercial AI products with the scientific community, further research, including randomized clinical trials, to test and integrate this concept in dental practice. Modern artificial intelligence is excellent at utilizing structured knowledge and gaining insights from huge amounts of data. However, it is not able to create associations like the human brain and is only partially capable of making complex decisions in a clinical situation. In turn, the efficiency of AI is achieved only when unbiased training data and a properly designed and trained algorithm are used. Keywords: dentistry, diagnostic, machine learning, cephalometry.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.006 | 0.012 |
| Scholarly communication | 0.016 | 0.010 |
| Open science | 0.001 | 0.005 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.028 | 0.013 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".