Evidence Hub

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

Nuno Domingues

Artificial Intelligence in Health, 2026

1 citation

Abstract

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…

Read the paper

Related studies

Go deeper in Evidence Hub

Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.

Open this study Sign up free