Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 13, 2025Open Access

Cancer Type, Stage and Prognosis Assessment from Pathology Reports using LLMs

View Full Paper
Ask AI
Bookmark
Share

Authors

RSRachit SalujaJRJacob RosenthalYAYoav Artzi

Discussion

Loading...

Member takes

Overview

Analysis of cancer type identification and prognosis assessment using large language models shows promising results.

Key Points

  • LLMs achieved notable accuracy in identifying cancer types from pathology reports, enhancing diagnostic workflows.
  • The instruction-tuned models, Path-llama3.1-8B and Path-GPT-4o-mini-FT, outperformed traditional approaches in prognosis assessment.
  • Evaluation of the models in a zero-shot setting demonstrated their capability to handle unstructured medical texts efficiently.
  • Tailored approaches for information extraction from pathology reports can significantly impact clinical decision-making and patient outcomes.

Cite This Study

Saluja et al. (2025) studied this question.

synapsesocial.com/papers/68ece2abd1bb2827d12971d7https://doi.org/10.48550/arxiv.2503.01194
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Assessing Large Language Models for Oncology Data Inference from Radiology Reports2024 · 2 citations
  2. 2Toward Automating the Summarization of Cancer Pathology Reports Using Large Language Models to Improve Clinical Usability2026 · 2 citations
  3. 3Performance of large language models for extracting clinical data from breast cancer pathology reports: a systematic review2026 · 3 citations
  4. 4CancerLLM: A Large Language Model in Cancer Domain2024 · 12 citations
  5. 5Phenotyping Prostate Cancer in a National Health System Using Large Language Models2026