Ask any radiology question. Every claim links to the guideline, paper or licensed case it came from, with its evidence tier shown. Built by clinicians, for the whole imaging team.
We asked both the same question. Both answers are shown word for word. One example, not a benchmark.
THE QUESTIONFleischner 2017 guidelines for an incidental 8 mm solid pulmonary nodule
ChatGPTPro, default model, temporary chat
For an incidentally detected solitary solid pulmonary nodule measuring exactly 8 mm, the 2017 Fleischner Society places it in the 6–8 mm category rather than the ">8 mm" category. RSNA Publications +1
RiskFleischner 2017 recommendation
Low riskCT at 6–12 months, then consider CT at 18–24 months if morphology is suspicious or stability is uncertain.
High riskCT at 6–12 months AND CT at 18–24 months.
If the nodule is larger than 8 mm, management changes to considering CT at ~3 months, PET/CT, tissue sampling, or a combination, guided by morphology and clinical risk. RSNA Publications
A useful exam distinction is therefore: 8 mm → 6–8 mm pathway 9 mm (or >8 mm) → >8 mm pathway
These recommendations apply to incidentally detected nodules in adults, and not to lung cancer screening, immunocompromised patients, or patients with a known primary malignancy. RSNA Publications
MyRadAssistantClinical style
KEY POINTS
•An 8 mm solid nodule falls in the Fleischner 2017 6–8 mm category, not the >8 mm category. For low-risk patients: CT at 6-12 months, then consider CT at 18-24 months; for high-risk patients: CT at 6-12 months, then CT at 18-24 months 1.
•In UK practice, BTS guidance, which iRefer follows, treats 8 mm as the threshold for Brock risk assessment. This is a material difference from Fleischner.
•Check the patient is eligible before applying Fleischner. The guideline does not apply to lung cancer screening, patients younger than 35 years, or patients with a history of primary cancer or immunosuppression. 2
Full answer continues with the size bands, follow up by risk group and matching cases:From the same answer: licensed cases with full CT stacks you can scroll through. Case courtesy of Lam Van Le, Radiopaedia.org.
Both placed the 8 mm nodule in the right Fleischner category.
Only MyRadAssistant flagged that UK BTS guidance uses 8 mm as the threshold for Brock risk assessment.
Only MyRadAssistant returned real licensed cases you can scroll through.
Both answers are each the first run, shown word for word; MyRadAssistant's is shortened to its key points and its case viewer. ChatGPT was used on a Pro plan with default settings in a temporary chat, and its answers can vary between runs. ChatGPT is a trademark of OpenAI. MyRadAssistant is not affiliated with or endorsed by OpenAI.
Full content licences for the RCR iRefer referral guidelines and Radiopaedia.
Licence on file
FAQ: Everything about MyRadAssistant
MyRadAssistant uses retrieval-augmented generation (RAG). Before answering anything, it searches a curated radiology and clinical evidence base for relevant source material, then asks a language model to synthesise an answer using only that retrieved text, with citations linking each claim back to the source. General-purpose assistants like ChatGPT answer any topic from their training data and the public web, and don't grade the evidence. RAG anchors every answer to text we actually have. If we don't have it, the system says so rather than guessing. See the full comparison.
Case images: Radiopaedia.org, credited to each author in the app.
