Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0847
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-08-22T06:03:15.408371Z
status: published
lens: p_space
sector: health
headline: Explainable artificial intelligence in medical imaging: how to interpret, evaluate, and use artificial intelligence explanations
dek: Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions. This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs…
gain_title: (none)
problem_title: Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust.
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust.
problem_evidence: (none)
quick_read: Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions.

This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs. We aim to make XAI easier for healthcare professionals to understand, as effective oversight of AI tools has become a core competency for the modern radiologist.
limitation: 
tag: Evidence-backed problem
key_points: To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions. | This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs. | In this educational and practical review, we provide an accessible overview of XAI tailored for practicing radiologists and physicians.
rundown: Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions.

This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs. In this educational and practical review, we provide an accessible overview of XAI tailored for practicing radiologists and physicians.
sources:
- peer_reviewed | Diagnostic and Interventional Radiology | https://doi.org/10.4274/dir.2026.264319 | 2026-08-21
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

740b593f8df3d9b138d54ccede3706e2e0463d8d8da1878e00f4aa6577063bff

previous

0000000000000000000000000000000000000000000000000000000000000000