From Clinical Intent to Clinical Model: Autonomous Coding-Agents for Clinician-driven AI Development
Not on the map. Why?
Abstract (arXiv)
Developing AI models that are useful in clinical practice, requires efficient collaboration between clinicians and AI developers. This poses a practical challenge: clinicians must repeatedly communicate and refine their requirements with AI developers before those requirements can be translated into executable model development. This iterative process is time-consuming, and even after repeated discussion, misalignment may still exist because the two sides do not fully share each other's expertise. Coding agents may help close this gap. They can write and refine code on their own, and they carry working knowledge of both medicine and AI to understand commands formulated by both medical experts and developers. We present a prototype that lets clinicians drive AI development directly. A clinician describes the task in plain language, and the system turns the description into a working pipeline, refines it through repeated experiments together with the clinician, and returns a model that meets the stated clinical objective. Across five clinical tasks, the system reliably produces models that matched the clinician's request and reached competitive performance. Most notably, on chest radiographs the system sharply reduced the model's reliance on chest drains, a well-known shortcut for pneumothorax classification, from 60% to 31% on one dataset and from 50% to 18% on another. Our results suggest that coding agents can shift clinical AI development toward a more clinician-driven mode, allowing domain experts to shape models directly instead of relaying requirements through specialized AI teams.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 61 references that are in the map. First posted on arXiv 18 Apr 2026.
Builds on
34 of 61 references.
References · 34
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2022A ConvNet for the 2020scited by 3,579
- 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
- 2020Shortcut Learning in Deep Neural Networkscited by 1,969
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
- 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
- 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
- 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
- 2025Accelerating scientific discovery with Co-Scientistcited by 401
- 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 238
- 2019Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imagingcited by 216
- 2026Towards End-to-End Automation of AI Researchcited by 159
22 more
- 2021Reading Race: AI Recognises Patient's Racial Identity In Medical Imagescited by 156
- 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 74
- 2018A Review of Challenges and Opportunities in Machine Learning for Healthcited by 68
- 2020AutoML to Date and Beyond: Challenges and Opportunitiescited by 63
- 2025An AI system to help scientists write expert-level empirical softwarecited by 60
- 2024Number Cookbook: Number Understanding of Language Models and How to Improve Itcited by 42
- 2023Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosiscited by 30
- 2019Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detectioncited by 28
- 2025SciSciGPT: Advancing Human-AI Collaboration in the Science of Sciencecited by 27
- 2023Large Language Models Streamline Automated Machine Learning for Clinical Studiescited by 24
- 2024A Review of Pseudo-Labeling for Computer Visioncited by 16
- 2022Assessing the communication gap between AI models and healthcare professionals: explainability, utility and trust in AI-driven clinical decision-makingcited by 14
- 2025Artificial Intelligence Should Genuinely Support Clinical Reasoning and Decision Making To Bridge the Translational Gapcited by 14
- 2020Teach me to segment with mixed supervision: Confident students become masterscited by 8
- 2024A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challengescited by 8
- 2026Towards a Medical AI Scientistcited by 7
- 2021Segmentation with mixed supervision: Confidence maximization helps knowledge distillationcited by 6
- 2023Augmenting Chest X-ray Datasets with Non-Expert Annotationscited by 6
- 2024Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screeningcited by 3
- 2025Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Modelscited by 3
- 2025Effect of Reporting Mode and Clinical Experience on Radiologists' Gaze and Image Analysis Behavior in Chest Radiographycited by 1
- 2026Can Agents Distinguish Visually Hard-to-Separate Diseases in a Zero-Shot Setting? A Pilot Studycited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy
- 2026Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation
- 2025An Agentic AI System for Multi-Framework Communication Coding
- 2026DoctorAgents: an agentic framework to iteratively refine AutoML pipeline for small clinical temporal data
- 2025Learning to Be A Doctor: Searching for Effective Medical Agent Architectures
- 2025Code Like Humans: A Multi-Agent Solution for Medical Coding
- 2026Human-Guided Agentic AI for Multimodal Clinical Prediction: Lessons from the AgentDS Healthcare Benchmark
- 2025A Field Guide to Deploying AI Agents in Clinical Practice