Abstract
Background. The digital transformation of dentistry involves not only the digitization of patient records but also the integration of intelligent Decision Support Systems (DSS), which can enhance diagnostic accuracy, standardize treatment protocols, and optimize clinician – patient interaction. With the rapid development of artificial intelligence (АІ) technologies, DSS are gaining increasing importance in both clinical and educational contexts within dentistry.Purpose – to systematize existing approaches to the classification, design, and implementation of DSS in dentistry, with a focus on their functional capabilities, archi-tectural models, and preconditions for successful clinical deployment.
Materials and Methods. The study is based on the analysis of peer-reviewed scien-tific literature published between 2020 and 2024 from Scopus, PubMed, and IEEE databases, as well as technical documentation of existing DSS solutions. Methods of systems analysis, descriptive classification, comparative evaluation, and synthesis of preconditions for implementation were applied. Two summary tables were develo-ped: one on the advantages and limitations of different DSS types, and another on implementation preconditions. Results. Two primary classification axes of DSS were identified: functional (diagnostic, prognostic, therapeutic planning, administrative, educational, AI-based) and architec-tural (rule-based, case-based, AI-based, fuzzy logic, hybrid systems). Rule-based systems remain the most widely used due to their transparency and alignment with clinical protocols, while AI-driven systems demonstrate potential but require further validation and explainability. A set of key preconditions for effective implementation was formulated, including structured clinical data, interoperability with electronic health records, appropriate infrastructure, and clinical staff readiness.Conclusions. DSS has demonstrated high potential for improving the quality, safety, and personalization of dental care. Promising directions for future development include hybrid DSS models that combine rule-based and AI approaches, as well as the creation of unified standards for integration and legal compliance.
Materials and Methods. The study is based on the analysis of peer-reviewed scien-tific literature published between 2020 and 2024 from Scopus, PubMed, and IEEE databases, as well as technical documentation of existing DSS solutions. Methods of systems analysis, descriptive classification, comparative evaluation, and synthesis of preconditions for implementation were applied. Two summary tables were develo-ped: one on the advantages and limitations of different DSS types, and another on implementation preconditions. Results. Two primary classification axes of DSS were identified: functional (diagnostic, prognostic, therapeutic planning, administrative, educational, AI-based) and architec-tural (rule-based, case-based, AI-based, fuzzy logic, hybrid systems). Rule-based systems remain the most widely used due to their transparency and alignment with clinical protocols, while AI-driven systems demonstrate potential but require further validation and explainability. A set of key preconditions for effective implementation was formulated, including structured clinical data, interoperability with electronic health records, appropriate infrastructure, and clinical staff readiness.Conclusions. DSS has demonstrated high potential for improving the quality, safety, and personalization of dental care. Promising directions for future development include hybrid DSS models that combine rule-based and AI approaches, as well as the creation of unified standards for integration and legal compliance.
| Original language | English |
|---|---|
| Pages (from-to) | 107–114 |
| Number of pages | 8 |
| Journal | Kharkiv Dental Journal |
| Volume | 2 |
| Issue number | 1(3) |
| DOIs | |
| Publication status | Published - 30 Jun 2025 |
| MoE publication type | A1 Journal article-refereed |
Keywords
- decision support systems
- dentistry
- rule-based DSS
- diagnosis
- digital medicine
- explainable artificial intelligence
- interoperability