Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.06602 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914032462594048 |
|---|---|
| author | Blondeel, Matthias Codella, Noel Preston, Sam Qiu, Hao Schettini, Leonardo Tuan, Frank Yim, Wen-wai Saligrama, Smitha Öz, Mert Jain, Shrey Lungren, Matthew P. Osborne, Thomas |
| author_facet | Blondeel, Matthias Codella, Noel Preston, Sam Qiu, Hao Schettini, Leonardo Tuan, Frank Yim, Wen-wai Saligrama, Smitha Öz, Mert Jain, Shrey Lungren, Matthew P. Osborne, Thomas |
| contents | Molecular Tumor Boards (MTBs) are multidisciplinary forums where oncology specialists collaboratively assess complex patient cases to determine optimal treatment strategies. A central element of this process is the patient summary, typically compiled by a medical oncologist, radiation oncologist, or surgeon, or their trained medical assistant, who distills heterogeneous medical records into a concise narrative to facilitate discussion. This manual approach is often labor-intensive, subjective, and prone to omissions of critical information. To address these limitations, we introduce the Healthcare Agent Orchestrator (HAO), a Large Language Model (LLM)-driven AI agent that coordinates a multi-agent clinical workflow to generate accurate and comprehensive patient summaries for MTBs. Evaluating predicted patient summaries against ground truth presents additional challenges due to stylistic variation, ordering, synonym usage, and phrasing differences, which complicate the measurement of both succinctness and completeness. To overcome these evaluation hurdles, we propose TBFact, a ``model-as-a-judge'' framework designed to assess the comprehensiveness and succinctness of generated summaries. Using a benchmark dataset derived from de-identified tumor board discussions, we applied TBFact to evaluate our Patient History agent. Results show that the agent captured 94% of high-importance information (including partial entailments) and achieved a TBFact recall of 0.84 under strict entailment criteria. We further demonstrate that TBFact enables a data-free evaluation framework that institutions can deploy locally without sharing sensitive clinical data. Together, HAO and TBFact establish a robust foundation for delivering reliable and scalable support to MTBs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Demo: Healthcare Agent Orchestrator (HAO) for Patient Summarization in Molecular Tumor Boards Blondeel, Matthias Codella, Noel Preston, Sam Qiu, Hao Schettini, Leonardo Tuan, Frank Yim, Wen-wai Saligrama, Smitha Öz, Mert Jain, Shrey Lungren, Matthew P. Osborne, Thomas Machine Learning Artificial Intelligence Molecular Tumor Boards (MTBs) are multidisciplinary forums where oncology specialists collaboratively assess complex patient cases to determine optimal treatment strategies. A central element of this process is the patient summary, typically compiled by a medical oncologist, radiation oncologist, or surgeon, or their trained medical assistant, who distills heterogeneous medical records into a concise narrative to facilitate discussion. This manual approach is often labor-intensive, subjective, and prone to omissions of critical information. To address these limitations, we introduce the Healthcare Agent Orchestrator (HAO), a Large Language Model (LLM)-driven AI agent that coordinates a multi-agent clinical workflow to generate accurate and comprehensive patient summaries for MTBs. Evaluating predicted patient summaries against ground truth presents additional challenges due to stylistic variation, ordering, synonym usage, and phrasing differences, which complicate the measurement of both succinctness and completeness. To overcome these evaluation hurdles, we propose TBFact, a ``model-as-a-judge'' framework designed to assess the comprehensiveness and succinctness of generated summaries. Using a benchmark dataset derived from de-identified tumor board discussions, we applied TBFact to evaluate our Patient History agent. Results show that the agent captured 94% of high-importance information (including partial entailments) and achieved a TBFact recall of 0.84 under strict entailment criteria. We further demonstrate that TBFact enables a data-free evaluation framework that institutions can deploy locally without sharing sensitive clinical data. Together, HAO and TBFact establish a robust foundation for delivering reliable and scalable support to MTBs. |
| title | Demo: Healthcare Agent Orchestrator (HAO) for Patient Summarization in Molecular Tumor Boards |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.06602 |