Translational Potential and Explainability of Artificial Intelligence-Based Clinical Decision Support for…

AI / informaticsJournal of multidisciplinary healthcare· 2026

Translational Potential and Explainability of Artificial Intelligence-Based Clinical Decision Support for Adults in Intensive Care: A Scoping Review.

Yodha Pranata, Ristina Mirwanti, Yusuf Achmad Bahtiar, Hesti Purwanti

Clinical Decision SupportAI / informaticsQ2IF 3.0

Only 17.2% of artificial intelligence intensive care unit decision-support tools integrated with hospital systems.

Translational Potential and Explainability of Artificial Intelligence-Based Clinical Decision Support for Adults in Intensive Care: A Scoping Review.

Yodha Pranata … Hesti Purwanti

Journal of multidisciplinary healthcare · 2026 · Q2 in General Medicine

Background

Intensive care units require rapid, high-stakes decision-making.

Purpose

This scoping review systematically mapped the translational potential and characteristics of explainable artificial intelligence (XAI) strategies in artificial intelligence/ML-based clinical decision support tools for adult intensive care unit (intensive care unit) settings.

Methods

Following PRISMA-ScR guidelines, we searched Web of Science, PubMed, Scopus, and EBSCOhost up to January 2026.

n = 808 records

17.2%

Results

17.2%

most tools still don't plug into hospital systems, limiting real-world use

n = 808 records

More results

A total of 808 records were identified, of which 29 studies met the inclusion criteria.

The findings revealed a marked retrospective predominance (86.2%) and reliance on North American data, predominantly Medical Information Mart for Intensive Care (Medical Information Mart for Intensive Care).

More results

Tree-based ensembles (82.8%) and post-hoc SHAP explanations (86.2%) were dominant, with proposed clinical utility spanning three domains: therapeutic guidance, resource-allocation optimisation, and user-centric design.

Only one study claimed clinical maturity (Technology Readiness Level 9), although its validation remained retrospective.

“

Conclusion · 1 of 3

Accuracy is no longer the primary bottleneck; the constraint has shifted to "last-mile" integration and external validity.

Conclusion · 2 of 3

Current XAI relies almost entirely on post-hoc methods that risk an "illusion of clarity", while inherently interpretable, glass-box models remain a rare but promising alternative.

Conclusion · 3 of 3

Future research should prioritise external validation in independent settings, prospective evaluation of clinical impact, and explicit comparison between post-hoc and interpretable approaches.

Translational Potential and Explainability of Artificial Intelligence-Based Clinical Decision Support for Adults in Intensive Care: A Scoping Review.

Translational Potential and Explainability of Artificial Intelligence-Based Clinical Decision Support for Adults in Intensive Care: A Scoping Review.

Related papers