Beyond the Algorithm: A Field Guide to Deploying AI Agents in Clinical Practice

• URL: http://arxiv.org/abs/2509.26153v2
• Date: Wed, 01 Oct 2025 16:11:30 GMT
• Title: Beyond the Algorithm: A Field Guide to Deploying AI Agents in Clinical Practice
• Abstract summary: We present a practitioner-oriented field manual for deploying generative agents that use electronic health record (EHR) data.<n>This guide is informed by our experience deploying the "irAE-Agent", an automated system to detect immune-related adverse events from clinical notes.<n>We distill this effort into five "heavy lifts": data integration, model validation, ensuring economic value, managing system drift, and governance.
• Score: 4.7589523564923395
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language models (LLMs) integrated into agent-driven workflows hold immense promise for healthcare, yet a significant gap exists between their potential and practical implementation within clinical settings. To address this, we present a practitioner-oriented field manual for deploying generative agents that use electronic health record (EHR) data. This guide is informed by our experience deploying the "irAE-Agent", an automated system to detect immune-related adverse events from clinical notes at Mass General Brigham, and by structured interviews with 20 clinicians, engineers, and informatics leaders involved in the project. Our analysis reveals a critical misalignment in clinical AI development: less than 20% of our effort was dedicated to prompt engineering and model development, while over 80% was consumed by the sociotechnical work of implementation. We distill this effort into five "heavy lifts": data integration, model validation, ensuring economic value, managing system drift, and governance. By providing actionable solutions for each of these challenges, this field manual shifts the focus from algorithmic development to the essential infrastructure and implementation work required to bridge the "valley of death" and successfully translate generative AI from pilot projects into routine clinical care.

Related papers

• From Siloed Algorithms to Compliance-First Agentic Platforms: A Multi-Layered Architecture for Hospital AI Systems [0.18899300124593646]
  An estimated 70-80% of healthcare AI pilots fail to scale due to governance gaps, fragmented data, and missing integration blueprints.<n>This research proposes a hospital-specific, compliance-first, Agentic AI architecture with multiple interoperable layers.<n>Using a synthetic but structurally realistic hospital dataset and an open, ready-to-deploy prototype implementation, this study demonstrates the end-to-end orchestration of triage risk prediction.
  arXiv  Detail & Related papers  (2026-08-06T14:44:31Z)
• Towards Autonomous and Auditable Medical Imaging Model Development [53.326510777116766]
  We introduce AMID, an autonomous multi-agent framework for medical imaging model development.<n>AMID first proposes Data-Conditioned Method Planning, which refines coarse task-level search spaces into executable, parallelizable method lanes.<n>It then develops Verification-Guided Two-Stage Optimization, moving from broad early exploration of diverse method lanes to selective exploitation of promising candidates.
  arXiv  Detail & Related papers  (2026-07-12T00:54:06Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• People-Centred Medical Image Analysis [28.028018247982686]
  People-Centred Medical Image Analysis (PecMan) is a human-AI framework that jointly optimises fairness, diagnostic accuracy, and workflow effectiveness.<n>We introduce the Fairness and Human-Centred AI (FairHAI) benchmark for evaluating trade-offs between accuracy, fairness, and clinician workload.<n>Experiments using this benchmark show that PecMan consistently outperforms existing methods, paving the way for more trustworthy and clinically viable AI systems.
  arXiv  Detail & Related papers  (2026-04-28T22:13:36Z)
• Human-Guided Agentic AI for Multimodal Clinical Prediction: Lessons from the AgentDS Healthcare Benchmark [0.5066646435185324]
  We investigate how human guidance of agentic AI can improve multimodal clinical prediction.<n>We present our approach to three benchmark challenges: 30-day hospital prediction, emergency department cost forecasting, and discharge readiness assessment.<n>Our approach ranked 5th overall in the healthcare domain, with a 3rd-place finish on the discharge readiness task.
  arXiv  Detail & Related papers  (2026-02-23T04:37:45Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization [69.36509281190662]
  Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck.<n>We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design.<n>We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions.
  arXiv  Detail & Related papers  (2025-12-02T18:42:26Z)
• From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening [0.3181700357675698]
  This paper argues that this gap is a translation problem and proposes the Generative Operational Framework.<n>This framework is designed to ingest the raw, technical outputs from diverse XAI tools and synthesize them with clinical guidelines.
  arXiv  Detail & Related papers  (2025-10-10T05:46:39Z)
• Leveraging AI to Accelerate Medical Data Cleaning: A Comparative Study of AI-Assisted vs. Traditional Methods [3.2666593942117688]
  Octozi is an artificial intelligence-assisted platform that combines large language models with domain-specifics to transform medical data review.<n>Economic analysis of a representative Phase III oncology trial reveals potential cost savings of $5.1 million.
  arXiv  Detail & Related papers  (2025-08-07T15:49:32Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• Bridging AI Innovation and Healthcare Needs: Lessons Learned from Incorporating Modern NLP at The BC Cancer Registry [2.0447192404937353]
  deploying Natural Language Processing (NLP) solutions presents practical challenges.<n>We emphasize the critical importance of defining problems based on clear business objectives.<n>We highlight the need for pragmatic model selection, rigorous attention to data quality, and robust error mitigation strategies.
  arXiv  Detail & Related papers  (2025-07-27T15:06:43Z)
• Toward a Human-Centered AI-assisted Colonoscopy System in Australia [12.548421709213379]
  Current development prioritizes machine learning model performance, overlooking essential aspects of user interface design, workflow integration, and overall user experience.<n>To realize AI's full potential, the HCI community must champion user-centered design, ensuring these systems are usable, support endoscopist expertise, and enhance patient outcomes.
  arXiv  Detail & Related papers  (2025-03-15T23:36:48Z)
• Medchain: Bridging the Gap Between LLM Agents and Clinical Practice through Interactive Sequential Benchmarking [58.25862290294702]
  We present MedChain, a dataset of 12,163 clinical cases that covers five key stages of clinical workflow.<n>We also propose MedChain-Agent, an AI system that integrates a feedback mechanism and a MCase-RAG module to learn from previous cases and adapt its responses.
  arXiv  Detail & Related papers  (2024-12-02T15:25:02Z)
• Demystifying Large Language Models for Medicine: A Primer [50.83806796466396]
  Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare. This tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice.
  arXiv  Detail & Related papers  (2024-10-24T15:41:56Z)
• Autonomous Artificial Intelligence Agents for Clinical Decision Making in Oncology [0.6397820821509177]
  We introduce an alternative approach to multimodal medical AI that utilizes the generalist capabilities of a large language model (LLM) as a central reasoning engine. This engine autonomously coordinates and deploys a set of specialized medical AI tools. We show that the system has a high capability in employing appropriate tools (97%), drawing correct conclusions (93.6%), and providing complete (94%), and helpful (89.2%) recommendations for individual patient cases.
  arXiv  Detail & Related papers  (2024-04-06T15:50:19Z)
• End-to-End Breast Cancer Radiotherapy Planning via LMMs with Consistency Embedding [47.360760580820966]
  We present RO-LMM, a comprehensive large multimodal model (LMM) tailored for the field of radiation oncology.<n>This model effectively manages a series of tasks within the clinical workflow, including clinical context summarization, radiation treatment plan suggestion, and plan-guided target volume segmentation.<n>We present a novel Consistency Embedding Fine-Tuning (CEFTune) technique, which boosts LMM's robustness to noisy inputs while preserving the consistency of handling clean inputs.
  arXiv  Detail & Related papers  (2023-11-27T14:49:06Z)
• MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data [37.60056509129154]
  Large language models (LLMs) hold considerable promise for improving medical, diagnostics, patient care, and education.<n>Yet, there is an urgent need for open-source models that can be deployed on-premises to safeguard patient privacy.<n>We present an innovative dataset consisting of over 160,000 entries, specifically crafted to fine-tune LLMs for effective medical applications.
  arXiv  Detail & Related papers  (2023-04-14T11:28:08Z)

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.