Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2502.15698 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915166364368896 |
|---|---|
| author | Mohammed, Abdul M. Mansoor, Iqtidar Blythe, Sarah Trujillo, Dennis |
| author_facet | Mohammed, Abdul M. Mansoor, Iqtidar Blythe, Sarah Trujillo, Dennis |
| contents | Cancer treatments require personalized approaches based on a patient's clinical condition, medical history, and evidence-based guidelines. The National Comprehensive Cancer Network (NCCN) provides frequently updated, complex guidelines through visuals like flowcharts and diagrams, which can be time consuming for oncologists to stay current with treatment protocols. This study presents an AI (Artificial Intelligence)-driven methodology to accurately automate treatment regimens following NCCN guidelines for breast cancer patients.
We proposed two AI-driven methods: Agentic-RAG (Retrieval-Augmented Generation) and Graph-RAG. Agentic-RAG used a three-step Large Language Model (LLM) process to select clinical titles from NCCN guidelines, retrieve matching JSON content, and iteratively refine recommendations based on insufficiency checks. Graph-RAG followed a Microsoft-developed framework with proprietary prompts, where JSON data was converted to text via an LLM, summarized, and mapped into graph structures representing key treatment relationships. Final recommendations were generated by querying relevant graph summaries. Both were evaluated using a set of patient descriptions, each with four associated questions.
As shown in Table 1, Agentic RAG achieved a 100% adherence (24/24) with no hallucinations or incorrect treatments. Graph-RAG had 95.8% adherence (23/24) with one incorrect treatment and no hallucinations. Chat GPT-4 showed 91.6% adherence (22/24) with two wrong treatments and no hallucinations. Both Agentic RAG and Graph-RAG provided detailed treatment recommendations with accurate references to relevant NCCN document page numbers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15698 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Developing an Artificial Intelligence Tool for Personalized Breast Cancer Treatment Plans based on the NCCN Guidelines Mohammed, Abdul M. Mansoor, Iqtidar Blythe, Sarah Trujillo, Dennis Information Retrieval Cancer treatments require personalized approaches based on a patient's clinical condition, medical history, and evidence-based guidelines. The National Comprehensive Cancer Network (NCCN) provides frequently updated, complex guidelines through visuals like flowcharts and diagrams, which can be time consuming for oncologists to stay current with treatment protocols. This study presents an AI (Artificial Intelligence)-driven methodology to accurately automate treatment regimens following NCCN guidelines for breast cancer patients. We proposed two AI-driven methods: Agentic-RAG (Retrieval-Augmented Generation) and Graph-RAG. Agentic-RAG used a three-step Large Language Model (LLM) process to select clinical titles from NCCN guidelines, retrieve matching JSON content, and iteratively refine recommendations based on insufficiency checks. Graph-RAG followed a Microsoft-developed framework with proprietary prompts, where JSON data was converted to text via an LLM, summarized, and mapped into graph structures representing key treatment relationships. Final recommendations were generated by querying relevant graph summaries. Both were evaluated using a set of patient descriptions, each with four associated questions. As shown in Table 1, Agentic RAG achieved a 100% adherence (24/24) with no hallucinations or incorrect treatments. Graph-RAG had 95.8% adherence (23/24) with one incorrect treatment and no hallucinations. Chat GPT-4 showed 91.6% adherence (22/24) with two wrong treatments and no hallucinations. Both Agentic RAG and Graph-RAG provided detailed treatment recommendations with accurate references to relevant NCCN document page numbers. |
| title | Developing an Artificial Intelligence Tool for Personalized Breast Cancer Treatment Plans based on the NCCN Guidelines |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2502.15698 |