dorsal/arxiv
View SchemaPulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis
| Authors | Jiao Xu, Junwei Liu, Jiangwei Lao, Qi Zhu, Yunpeng Zhao, Congyun Jin, Shinan Liu, Zhihong Lu, Lihe Zhang, Xin Chen, Jian Wang, Ping Wang |
|---|---|
| Categories | |
| ArXiv ID | 2601.07344vv1 |
| URL | https://arxiv.org/abs/2601.07344 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during patient-physician interactions. To bridge this gap, we introduce PulseMind, a new family of multi-modal diagnostic models that integrates a systematically curated dataset, a comprehensive evaluation benchmark, and a tailored training framework. Specifically, we first construct a diagnostic dataset, MediScope, which comprises 98,000 real-world multi-turn consultations and 601,500 medical images, spanning over 10 major clinical departments and more than 200 sub-specialties. Then, to better reflect the requirements of real-world clinical diagnosis, we develop the PulseMind Benchmark, a multi-turn diagnostic consultation benchmark with a four-dimensional evaluation protocol comprising proactiveness, accuracy, usefulness, and language quality. Finally, we design a training framework tailored for multi-modal clinical diagnostics, centered around a core component named Comparison-based Reinforcement Policy Optimization (CRPO). Compared to absolute score rewards, CRPO uses relative preference signals from multi-dimensional com-parisons to provide stable and human-aligned training guidance. Extensive experiments demonstrate that PulseMind achieves competitive performance on both the diagnostic consultation benchmark and public medical benchmarks.
{
"annotation_id": "25affb43-824e-4474-91a3-1b5b12681850",
"date_created": "2026-02-17T05:53:12.586000Z",
"date_modified": "2026-02-17T05:53:12.586000Z",
"file_hash": "d4332e2f7a98d90c871fd03740aa678f2ff5c293b23b8ef6f4b43ac5342098ba",
"private": false,
"record": {
"abstract": "Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during patient-physician interactions. To bridge this gap, we introduce PulseMind, a new family of multi-modal diagnostic models that integrates a systematically curated dataset, a comprehensive evaluation benchmark, and a tailored training framework. Specifically, we first construct a diagnostic dataset, MediScope, which comprises 98,000 real-world multi-turn consultations and 601,500 medical images, spanning over 10 major clinical departments and more than 200 sub-specialties. Then, to better reflect the requirements of real-world clinical diagnosis, we develop the PulseMind Benchmark, a multi-turn diagnostic consultation benchmark with a four-dimensional evaluation protocol comprising proactiveness, accuracy, usefulness, and language quality. Finally, we design a training framework tailored for multi-modal clinical diagnostics, centered around a core component named Comparison-based Reinforcement Policy Optimization (CRPO). Compared to absolute score rewards, CRPO uses relative preference signals from multi-dimensional com-parisons to provide stable and human-aligned training guidance. Extensive experiments demonstrate that PulseMind achieves competitive performance on both the diagnostic consultation benchmark and public medical benchmarks.",
"arxiv_id": "2601.07344",
"authors": [
"Jiao Xu",
"Junwei Liu",
"Jiangwei Lao",
"Qi Zhu",
"Yunpeng Zhao",
"Congyun Jin",
"Shinan Liu",
"Zhihong Lu",
"Lihe Zhang",
"Xin Chen",
"Jian Wang",
"Ping Wang"
],
"categories": [
"cs.CV",
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis",
"url": "https://arxiv.org/abs/2601.07344",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "e5391aaf-764c-4f10-add6-f13fd065aee2",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}