[论文解读] DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models

Jiancheng Ye, Sophie Bronstein+2 more|ArXiv.org|Jun 2, 2025

Artificial Intelligence in Healthcare and Education被引用 3

一句话总结

对 DeepSeek-R1 的开源大语言模型进行综述，涵盖其架构、能力、临床应用、基准测试、风险与治理影响。

ABSTRACT

DeepSeek-R1 is a cutting-edge open-source large language model (LLM) developed by DeepSeek, showcasing advanced reasoning capabilities through a hybrid architecture that integrates mixture of experts (MoE), chain of thought (CoT) reasoning, and reinforcement learning. Released under the permissive MIT license, DeepSeek-R1 offers a transparent and cost-effective alternative to proprietary models like GPT-4o and Claude-3 Opus; it excels in structured problem-solving domains such as mathematics, healthcare diagnostics, code generation, and pharmaceutical research. The model demonstrates competitive performance on benchmarks like the United States Medical Licensing Examination (USMLE) and American Invitational Mathematics Examination (AIME), with strong results in pediatric and ophthalmologic clinical decision support tasks. Its architecture enables efficient inference while preserving reasoning depth, making it suitable for deployment in resource-constrained settings. However, DeepSeek-R1 also exhibits increased vulnerability to bias, misinformation, adversarial manipulation, and safety failures - especially in multilingual and ethically sensitive contexts. This survey highlights the model's strengths, including interpretability, scalability, and adaptability, alongside its limitations in general language fluency and safety alignment. Future research priorities include improving bias mitigation, natural language comprehension, domain-specific validation, and regulatory compliance. Overall, DeepSeek-R1 represents a major advance in open, scalable AI, underscoring the need for collaborative governance to ensure responsible and equitable deployment.

研究动机与目标

• 评估开源大语言模型（DeepSeek-R1）在医疗任务中的能力。
• 表征其架构设计（Mixture of Experts、Chain-of-Thought、RL）及对成本与推理的影响。
• 在医疗与领域基准上评估性能（如 USMLE），并识别临床决策支持的优势。
• 识别安全、偏见、错误信息等风险，尤其在多语言与伦理敏感情境中的挑战。
• 概述面向开放式医疗 LLM 的治理、监管与部署考量。

提出的方法

• 描述 DeepSeek-R1 的混合架构，将专家混合、推理链（Chain-of-Thought）、强化学习结合。
• 分析在标准基准（USMLE、AIME）上的表现，评估领域特定能力。
• 评估资源受限环境中的可解释性、可扩展性与推理效率。
• 评估安全性、偏见、错误信息、对抗风险，以及多语言/伦理挑战。
• 讨论面向开源医疗 LLM 部署的监管合规与治理考量。

实验结果

研究问题

• RQ1 DeepSeek-R1 在医疗任务与结构化问题求解中展现了哪些能力？
• RQ2 DeepSeek-R1 在医学领域与决策支持中的优势与局限性是什么？
• RQ3 DeepSeek-R1 在医学与数学基准（如 USMLE、AIME）上的表现如何？
• RQ4 影响 DeepSeek-R1 的安全、偏见、错误信息与对抗风险在多语言或伦理敏感情境中的表现？
• RQ5 面向开放式医疗 LLM 需要哪些治理、监管与部署方面的考量？

主要发现

• DeepSeek-R1 在 USMLE 与 AIME 等基准测试中展现出具有竞争力的表现。
• 该模型在儿科与眼科临床决策支持任务中显示出显著的结果。
• 它提供可解释性、可扩展性与适合资源受限环境的高效推理。
• 在多语言与敏感语境下，存在偏见、错误信息、对抗操控及安全性失败的风险上升。
• 开源许可（MIT）与混合架构有助于透明度与成本效益，凸显治理需求。