AI-Enabled CDSS Predicts Personalized Surgical Blood Orders
In 2026, researchers at Asan Medical Center conducted a preimplementation qualitative study of pMSBOS-TS, an AI-enabled CDSS for personalized thoracic surgical blood ordering, using two semistructured focus groups with 14 multidisciplinary clinicians. Analysis identified 189 semantic units and 61 core ideas across seven domains, finding potential to reduce unwarranted ordering variation if algorithmic performance and tight EHR integration are ensured. Results highlight sociotechnical readiness, governance, and workflow fit as implementation determinants.
Key Points
- 1Identified 189 semantic units and 61 core ideas across 18 subdomains and seven domains
- 2Highlighted need for reliable algorithm performance and tight EHR integration to reduce ordering variation
- 3Warned increased verification burden and communication bottlenecks could raise workload and product waste
Scoring Rationale
Peer-reviewed, practice-focused sociotechnical insights support implementation planning; limited single-center qualitative design constrains generalizability and scalability to other settings.
Sources
Public references used for this report.
Practice with real Health & Insurance data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Health & Insurance problems
