A Machine Learning Algorithm With an Oversampling Technique in Limited Data Scenarios for the Prediction of Present and Future Restorative Treatment Need: Development and Validation Study
On the basis of the performance metrics, the ML algorithm developed and tested in this study can be considered good. The ML algorithm could serve as a cost-effective screening tool for dental professionals to identify the risk of future restorative treatment needs. However, future studies with longitudinal cohorts and longitudinal data, along with external validation for generalizability, are needed to validate our model.
Authors
- Jaakko Suutala (ORCID: https://orcid.org/0000-0002-6605-0057)
- Vuokko Anttonen (ORCID: https://orcid.org/0000-0002-3804-1858)
- Katri Kukkola (ORCID: https://orcid.org/0000-0002-2589-7251)
- Saujanya Karki (ORCID: https://orcid.org/0000-0002-3160-8137)
- Marja‐Liisa Laitala (ORCID: https://orcid.org/0000-0001-7323-9862)
- Henna Tiensuu (ORCID: https://orcid.org/0000-0002-6026-9509)
- Elina Väyrynen (ORCID: https://orcid.org/0009-0000-6890-3810)
- Otso Tirkkonen (ORCID: https://orcid.org/0009-0005-9654-7100)
Institutions
- Oulu University Hospital (FI)
- University of Oulu (FI)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-07-16
- DOI
- https://doi.org/10.2196/75117
- Citations
- 2
- Primary Topic
- Dental Health and Care Utilization
- Type
- article
- Field-Weighted Citation Impact
- 2.93