Publicação
A hybrid decision support system using rule-based and AI methods: the OnCATs knowledge-based framework
| authorProfile.email | biblioteca@isel.pt | |
| datacite.subject.fos | Engenharia e Tecnologia::Engenharia Mecânica | |
| dc.contributor.author | Soares Domingues, Nuno Alexandre | |
| dc.date.accessioned | 2026-05-04T12:51:00Z | |
| dc.date.available | 2026-05-04T12:51:00Z | |
| dc.date.issued | 2026-02 | |
| dc.description.abstract | Background and significance: Clinical decision support systems (CDSS) can improve evidence-based oncology care, but many rely on opaque AI models that limit transparency and reproducibility. Rule-based approaches provide interpretability but often lack adaptability, a critical issue in prostate cancer where decisions depend on tumor stage, PSA, Gleason score, comorbidities, and life expectancy. Bridging explainability and adaptability is essential for trustworthy decision support. Objective: To develop and evaluate OnCATs, a modular, explainable, hybrid-ready CDSS that encodes prostate cancer management guidelines in a machine-readable and auditable format. Materials and methods: Evidence from 23 international guidelines was formalized into a JSON-based rule base executed through a forward-chaining inference engine. OnCATs supports three decision layers: (1) risk stratification, (2) treatment-pathway recommendation, and (3) prescription-level assistance for radiotherapy, brachytherapy, androgen deprivation therapy, and surgery. Feasibility was tested using ten published case reports. Performance was assessed with precision, recall, F1 scores, and descriptive concordance. Results: OnCATs achieved perfect concordance for risk stratification (precision = 1.00, recall = 1.00, F1 = 1.00). Treatment-pathway concordance was 0.80 (F1 = 0.80). Prescription-level agreement ranged from 0.67 to 0.75 (mean F1 = 0.71). Divergences primarily reflected simplified life-expectancy modeling and incomplete case data. Discussion: OnCATs demonstrates that transparent, rule-based reasoning can reproduce guideline-defined prostate cancer decisions with traceability. Limitations include the small sample size and reliance on secondary data. Conclusion: OnCATs operationalizes multi-source guidelines into an explainable, modular CDSS, providing a reproducible foundation for future integration of probabilistic and machine-learning methods. | eng |
| dc.identifier.citation | Domingues, N. S. (2026). A hybrid decision support system using rule-based and AI methods: the OnCATs knowledge-based framework. International Journal of Medical Informatics, 206, 1-11. https://doi.org/10.1016/j.ijmedinf.2025.106144 | |
| dc.identifier.doi | 10.1016/j.ijmedinf.2025.106144 | |
| dc.identifier.eissn | 1872-8243 | |
| dc.identifier.issn | 1386-5056 | |
| dc.identifier.uri | http://hdl.handle.net/10400.21/22849 | |
| dc.language.iso | eng | |
| dc.peerreviewed | yes | |
| dc.publisher | Elsevier | |
| dc.relation.hasversion | https://www.sciencedirect.com/science/article/pii/S1386505625003612?pes=vor&utm_source=clarivate&getft_integrator=clarivate | |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.subject | Hybrid decision | |
| dc.subject | AI methods | |
| dc.subject | OnCATs knowledge | |
| dc.title | A hybrid decision support system using rule-based and AI methods: the OnCATs knowledge-based framework | eng |
| dc.type | research article | |
| dspace.entity.type | Publication | |
| oaire.citation.endPage | 11 | |
| oaire.citation.startPage | 1 | |
| oaire.citation.title | International Journal of Medical Informatics | |
| oaire.citation.volume | 206 | |
| oaire.version | http://purl.org/coar/version/c_be7fb7dd8ff6fe43 | |
| person.familyName | Soares Domingues | |
| person.givenName | Nuno Alexandre | |
| person.identifier.ciencia-id | B416-C3B2-2CBF | |
| person.identifier.orcid | 0000-0003-0763-8106 | |
| relation.isAuthorOfPublication | d9437ee3-91ad-4034-91f1-4dd3f097c16c | |
| relation.isAuthorOfPublication.latestForDiscovery | d9437ee3-91ad-4034-91f1-4dd3f097c16c |