Pragmatic RCT of AI-Assisted Reading for Malignant Hepatic Lesions on CE-CT

Condition(s) studied

Investigational drug(s) / intervention(s)

AI-assisted abdominal CE-CT reporting: After the unaided initial assessment is saved, the locked AI system will display lesion localization, patient-level and lesion-level malignancy probabilities, prespecified lesion-class suggestions, and uncertainty or technical-failure warnings. The first-line radiologist may revise or retain the initial assessment and must record acceptance, rejection, or uncertainty for clinically important AI suggestions. The senior reviewer may view the initial assessment, AI output, and revision history. AI may not autonomously authorize reports, prescribe management, or communicate diagnoses directly to participants.

Standard abdominal CE-CT reporting without AI assistance: Eligible multiphasic abdominal CE-CT examinations will be interpreted and reported according to the site's standard radiology workflow, including routine senior review where applicable. AI system outputs will not be available to radiologists or clinical staff, and no AI-triggered safety-net review will be performed. Routine report addenda, urgent communication, multidisciplinary review, additional imaging, and subsequent clinical management will remain available according to standard clinical practice.

Study summary

The purpose of this multicenter pragmatic randomized controlled trial is to determine whether AI-assisted interpretation of multiphasic liver contrast-enhanced computed tomography (CE-CT) is non-inferior to standard radiology reporting with respect to missed clinically significant malignant focal liver lesions, \*\*with the non-inferiority margin prespecified in the statistical analysis plan before enrollment\*\*, and whether it improves lesion detection, diagnostic characterization, downstream clinical management, and reporting efficiency. On AI-assisted center-days, AI results will be revealed only after the first-line radiologist has saved an unaided initial assessment and may be used to revise the final report. On control center-days, examinations will be interpreted using the standard radiology workflow without access to AI tools.

Eligibility

Primary outcome measure(s)

• Per-participant rate of missed clinically significant liver malignancy — From the index CE-CT examination through 12 months
  Proportion of all enrolled participants with at least one reference-standard-confirmed clinically significant liver malignancy, including hepatocellular carcinoma, liver metastasis, or another primary hepatic malignancy, that was not identified or appropriately characterized in the final index CE-CT report. The reference standard will comprise histopathology when available; otherwise, 12-month imaging and clinical follow-up and relevant record linkage, adjudicated by an independent committee masked to allocation. Non-inferiority will be assessed against a margin prespecified before enrollment.

Trial sites (1)

More Shengjing Hospital trials in China

Other trials for the same condition