Large language models for breast cancer treatment planning: a blinded real-world evaluation of DeepSeek, ChatGPT, and oncologist recommendations.
Source check: Source checked. Not independent scientific confirmation.
Finding: In a blinded review of 213 breast-cancer records, experts compared plans generated by DeepSeek V3.1 and ChatGPT-5 with the historical oncologist plans. DeepSeek received higher guideline-concordance scores, and agreement was weaker in advanced-stage cases.
Technology: LLMs generate treatment recommendations from de-identified records for blinded expert scoring.
Family DeepSeek: profile · models page
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- LLMs generate treatment recommendations from de-identified records for blinded expert scoring.
- Test and result
- Three expert reviewers rated plans from historical cases and compared concordance across cancer stages.
- Limitation / still unknown
- The study measured retrospective agreement with guidelines and clinicians. Patient outcomes were outside its design.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2026.1862730/full
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.