ChatGPT helps review MRI literature on intravascular lymphoma

AI system

System: ChatGPT. [1]
Model: GPT-4o. [1]
Release: Exact release not established.
Application developer: OpenAI
Role: GPT-4o summarized MRI findings from published papers for the authors’ literature review. [1]
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Clinician-authors prompting ChatGPT during a literature review.
Human oversight: Not assessed
Relation to AI: ChatGPT assisted the authors' literature review for the published case. The patient's diagnosis and care did not involve the model. Source is a non-vendor peer-reviewed case report.
AI contribution: ChatGPT assisted the authors' literature review for the published case. The patient's diagnosis and care did not involve the model. Source is a non-vendor peer-reviewed case report.

Outcome identifiers: Not assessed
Benefit: Chinese neurologists used ChatGPT to help review published MRI findings of cerebral intravascular large B-cell lymphoma for a 59-year-old's case report; the diagnosis came from biopsy, not the model.
Category: Improved Knowledge Discovery
Status: Not assessed
Beneficiary groups: People. Organizations. Society.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Participants: Developer: OpenAI. Operator: Affiliated Yuebei People's Hospital of Shantou University Medical College.
Jurisdictions: Benefit: Shaoguan, Guangdong, China. Developer: United States. Operator: China.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Authors verify model-suggested literature against sources.
Replication attempts: Not assessed
Later findings: The case report is a single retrospective literature review aid; no follow-up, correction or later use was found in the cited source, and the authors note the model could not summarize specific MRI features for accurate diagnosis.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Source numbers: AIBD-0270-source-0001
Citations: Numbered references below.
Language: Not assessed
Source relationships: Operator
Original evidence: The researchers describe their own use of GPT-4o in section 4 of the paper. [1]
Access and versions: The full article was accessible. Its supplementary files have not been inspected. [1]
Supported findings: Not assessed
Evidence links: Not assessed
Evidence strength: Not assessed
Missing evidence: Not assessed

Assessed benefits: People. Organizations. Society.
Depth: Not assessed
Reasons: People: The model did not contribute to diagnosis or treatment. Organizations: No organizational outcome. Society: No attributable event.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: The deployer's account

Kind: Not assessed
Related entries: Not assessed
Field: Health; neurology and medical publishing. Clinician-authors.
Purpose: Assist clinicians in reviewing published imaging literature for a case report
Dates: Date basis unassessed: 2024 (precision unassessed). Updated: 25 October 2026.
Stage: Not assessed
Version: SHA-256: df5e6ccaabce…