Enterprise AI Analysis
Artificial intelligence-enabled clinical decision support systems in preadmission testing: a scoping review of risk prediction, triage, and perioperative workflows (2020-2025)
Authors: Lawrence Willis Chinn¹, Isabelle Nemeh¹ Natasha R. Chinn²
Journal: Journal of Clinical Monitoring and Computing
Publication Date: Published online: 31 January 2026
DOI: https://doi.org/10.1007/s10877-025-01404-w
Executive Impact Summary
This scoping review highlights the transformative potential of AI-enabled Clinical Decision Support Systems (CDSS) in preadmission testing (PAT). By leveraging vast datasets, AI aims to improve risk stratification, streamline workflows, and enhance patient safety in perioperative care.
The review, covering studies from 2020 to 2025, identified 56 relevant studies that applied AI/ML to preoperative evaluation, risk prediction, triage, or decision support. While most applications are currently at the proof-of-concept stage, the consistent signal of improved predictive accuracy suggests a future where AI-enabled CDSS will significantly reduce unnecessary testing, day-of-surgery cancellations, and support safer perioperative monitoring.
Key findings show radiomics and deep learning dominating oncologic prediction, while NLP effectively predicts ASA-PS classification from text. The transition to prospective, multi-center validation is the critical next step for widespread clinical adoption.
0
Studies Included
0
Primary AI Approaches
0%
Retrospective Cohorts
0%
Prospective/Randomized
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
AI-Enabled CDSS Review Process (PRISMA Flow)
The study selection process followed PRISMA-ScR guidelines, moving from initial records identified to the final set of included studies.
Enterprise Process Flow
Records identified (151)
→
Duplicates removed (37)
→
Records screened (114)
→
Records excluded (54)
→
Full-text reports assessed (60)
→
Reports excluded (4)
→
Studies included (56)
56
Relevant Studies Analyzed (2020-2025)
AI-Enabled CDSS vs. Traditional PAT Methods
Compare the distinct advantages and current limitations of AI-enabled CDSS against traditional methods in preadmission testing.
| AI-Enabled CDSS for PAT | Traditional PAT Methods |
|---|---|
|
|
Case Study: LLM-based CDSS for Perioperative Workflows
Explore a concrete example of AI's successful application and its measured impact in a clinical setting.
LLM-based CDSS for Perioperative Workflows
A randomized crossover trial by Ke et al. (2025) demonstrated that incorporating an LLM-based Clinical Decision Support System (CDSS) into perioperative medicine workflows led to significant improvements in both clinical and economic outcomes. This highlights the practical value of AI in streamlining documentation, risk stratification, and supporting decision-making in real-world clinical settings, moving beyond proof-of-concept to quantifiable benefits.
Source: Ke et al., 2025
Advanced ROI Calculator
Estimate the potential return on investment for AI integration in your enterprise operations.
Estimated Annual Savings
$0
Annual Hours Reclaimed
0
Your AI Implementation Roadmap
A structured approach to integrating AI into your enterprise, ensuring sustainable growth and measurable results.
Phase 1: Discovery & Strategy
Identify key business challenges, evaluate AI readiness, and define a clear AI strategy aligned with enterprise goals. This includes data assessment, use case prioritization, and initial ROI modeling.
Phase 2: Pilot & Proof-of-Concept
Develop and deploy a pilot AI solution for a selected use case. Focus on demonstrating technical feasibility, internal validation, and early business impact. Gather feedback and iterate rapidly.
Phase 3: Integration & Scaling
Integrate validated AI solutions into existing enterprise systems and workflows. Establish robust MLOps practices, ensure data governance, and begin scaling across departments or functions. Conduct external validation if applicable.
Phase 4: Monitoring & Optimization
Continuously monitor AI model performance, detect drift, and retrain as necessary. Implement continuous feedback loops for optimization and explore new AI applications to maximize long-term value.
Ready to Transform with AI?
Book a complimentary 30-minute strategy session with our AI experts to discuss your specific needs and how AI can drive your business forward.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat