EUVIMEDEUVIMED entdecken
Crossref

Design and implementation of the DmgCDSS framework: Toward transparent benign prostatic hyperplasia clinical decision support

Nuno Soares Domingues

Artificial Intelligence in Health · 17.03.2026 · 3 (3) · 025440094

DOI: 10.36922/aih025440094 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence in Health, online erschienen am 17.03.2026. Verfasst von Nuno Soares Domingues. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transparent and guideline-compliant clinical decision support systems (CDSSs) are essential for trustworthy digital health. However, numerous rule-based systems lack explicit provenance, interoperability, and explainability. This study aims to design and evaluate DmgCDSS, a transparent, modular CDSS framework for benign prostatic hyperplasia (BPH) that supports guideline-based reasoning, provenance tracking, and interoperability through structured data and open standards. Clinical recommendations from major BPH guidelines (European Association of Urology, American Urological Association, National Institute for Health and Care Excellence) were encoded as modular JavaScript Object Notation rule objects with versioning and metadata. A forward-chaining inference engine, implemented in C#, processes patient data mapped to standard terminologies (Systematized Nomenclature of Medicine–Clinical Terms, Logical Observation Identifiers Names and Codes, International Classification of Diseases, 10th Revision). System outputs include actionable recommendations with traceable rule sources. Performance was evaluated through case-based concordance testing on ten published BPH case reports. Agreement between DmgCDSS and reference recommendations was assessed across diagnosis, risk stratification, investigation, and treatment domains. DmgCDSS achieved an overall concordance of 80% (32/40 domain-level decisions) with guideline-based reference outputs. Discrepancies were mainly due to missing clinical details or evolving recommendations. Rule evaluation completed within 1 s per case. The framework supports interoperability through Fast Healthcare Interoperability Resources-compatible data structures and explainable output logs. DmgCDSS demonstrates the technical feasibility of a transparent, guideline-based CDSS for BPH. The framework enables reproducible rule management, traceable recommendations, and standards-based interoperability. Broader validation using electronic health records and clinician usability testing is planned to confirm clinical utility.

Zitieren

APA

Domingues, N. S. (2026). Design and implementation of the DmgCDSS framework: Toward transparent benign prostatic hyperplasia clinical decision support. Artificial Intelligence in Health, 3(3), 025440094. https://doi.org/10.36922/aih025440094

Vancouver

Domingues NS. Design and implementation of the DmgCDSS framework: Toward transparent benign prostatic hyperplasia clinical decision support. Artificial Intelligence in Health. 2026;3(3):025440094. doi:10.36922/aih025440094

BibTeX
@article{Domingues2026,
  author = {Domingues, Nuno Soares},
  title = {Design and implementation of the DmgCDSS framework: Toward transparent benign prostatic hyperplasia clinical decision support},
  journal = {Artificial Intelligence in Health},
  year = {2026},
  volume = {3},
  number = {3},
  pages = {025440094},
  doi = {10.36922/aih025440094}
}
Kostenlos starten →