Development, Evaluation, and Deployment of a Multi-Agent System for Thoracic Tumor Board

• URL: http://arxiv.org/abs/2604.12161v1
• Date: Tue, 14 Apr 2026 00:35:40 GMT
• Title: Development, Evaluation, and Deployment of a Multi-Agent System for Thoracic Tumor Board
• Abstract summary: Tumor boards are multidisciplinary conferences dedicated to producing actionable patient care recommendations.<n>We developed a manual AI-based workflow to generate patient summaries to display live at the Stanford Thoracic Tumor board.<n>We developed several automated AI chart summarization methods and evaluated them against physician gold standard summaries and fact-based scoring rubrics.
• Score: 2.9838803937327474
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Tumor boards are multidisciplinary conferences dedicated to producing actionable patient care recommendations with live review of primary radiology and pathology data. Succinct patient case summaries are needed to drive efficient and accurate case discussions. We developed a manual AI-based workflow to generate patient summaries to display live at the Stanford Thoracic Tumor board. To improve on this manually intensive process, we developed several automated AI chart summarization methods and evaluated them against physician gold standard summaries and fact-based scoring rubrics. We report these comparative evaluations as well as our deployment of the final state automated AI chart summarization tool along with post-deployment monitoring. We also validate the use of an LLM as a judge evaluation strategy for fact-based scoring. This work is an example of integrating AI-based workflows into routine clinical practice.

Related papers

• Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training [10.948633957490221]
  We developed a scaffolding-oriented multi-agent Large Language Model (LLM) AI Standardized Patient (AI-SP) training platform.<n>The system includes a patient agent for simulated dialog, a tutor agent providing Socratic prompts without disclosing diagnostic information, and a turn-level evaluator agent that monitors clinical progress.<n>The most substantial and consistent improvements were observed in communication, the expression of empathy, and specific history-taking behaviors.
  arXiv  Detail & Related papers  (2026-09-10T00:56:03Z)
• Can Physician Expertise Improve Machine Learning Identification of Delirium? [3.023141540283701]
  Delirium is common in hospitalized patients and is often missed in routine care.<n>We present a user-centered interactive machine learning (UC-iML) framework for delirium detection support.
  arXiv  Detail & Related papers  (2026-06-16T01:12:47Z)
• Demo: Healthcare Agent Orchestrator (HAO) for Patient Summarization in Molecular Tumor Boards [7.69748973216707]
  We introduce the Healthcare Agent Orchestrator (HAO) to generate accurate and comprehensive patient summaries for Molecular Tumor Boards (MTBs)<n> evaluating predicted patient summaries against ground truth presents additional challenges due to stylistic variation, ordering, synonym usage, and phrasing differences.<n>We propose TBFact, a model-as-a-judge'' framework designed to assess the comprehensiveness and succinctness of generated summaries.
  arXiv  Detail & Related papers  (2025-09-08T12:15:53Z)
• Comparing representations of long clinical texts for the task of patient note-identification [4.552065156611815]
  Patient-note identification involves accurately matching an anonymized clinical note to its corresponding patient, represented by a set of related notes.<n>We explore various embedding methods, including BERT-based models, to process mediumto-long clinical texts effectively.<n>Our results indicate that BERT-based embeddings outperform traditional and hierarchical models, particularly in processing lengthy clinical notes.
  arXiv  Detail & Related papers  (2025-03-31T12:31:44Z)
• Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions [26.167030665482184]
  We introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents.<n>Unlike prior approaches, our framework requires doctor agents to actively engage with patients through multi-turn conversations.<n>We incorporate self improvement mechanisms that allow models to iteratively refine their diagnostic strategies.
  arXiv  Detail & Related papers  (2025-03-28T17:59:53Z)
• TAMA: A Human-AI Collaborative Thematic Analysis Framework Using Multi-Agent LLMs for Clinical Interviews [54.35097932763878]
  Thematic analysis (TA) is a widely used qualitative approach for uncovering latent meanings in unstructured text data.<n>Here, we propose TAMA: A Human-AI Collaborative Thematic Analysis framework using Multi-Agent LLMs for clinical interviews.<n>We demonstrate that TAMA outperforms existing LLM-assisted TA approaches, achieving higher thematic hit rate, coverage, and distinctiveness.
  arXiv  Detail & Related papers  (2025-03-26T15:58:16Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Towards Unifying Anatomy Segmentation: Automated Generation of a Full-body CT Dataset via Knowledge Aggregation and Anatomical Guidelines [113.08940153125616]
  We generate a dataset of whole-body CT scans with $142$ voxel-level labels for 533 volumes providing comprehensive anatomical coverage. Our proposed procedure does not rely on manual annotation during the label aggregation stage. We release our trained unified anatomical segmentation model capable of predicting $142$ anatomical structures on CT data.
  arXiv  Detail & Related papers  (2023-07-25T09:48:13Z)
• RECAP-KG: Mining Knowledge Graphs from Raw GP Notes for Remote COVID-19 Assessment in Primary Care [45.43645878061283]
  We present a framework that performs knowledge graph construction from raw GP medical notes written during or after patient consultations. Our knowledge graphs include information about existing patient symptoms, their duration, and their severity. We apply our framework to consultation notes of COVID-19 patients in the UK.
  arXiv  Detail & Related papers  (2023-06-17T23:35:51Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)
• BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes [53.163089893876645]
  We propose a novel self-attention mechanism that captures the contextual dependency and temporal relationships within a patient's healthcare journey. An end-to-end bidirectional temporal encoder network (BiteNet) then learns representations of the patient's journeys. We have evaluated the effectiveness of our methods on two supervised prediction and two unsupervised clustering tasks with a real-world EHR dataset.
  arXiv  Detail & Related papers  (2020-09-24T00:42:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.