DeepSeek in Healthcare: A Survey of Capabilities, Risks, and Clinical Applications of Open-Source Large Language Models

2025-06-02

AI Summary

DeepSeek-R1—an open-source large language model integrating Mixture-of-Experts (MoE), Chain-of-Thought (CoT), and Reinforcement Learning (RL)—exhibits critical limitations in medical applications, including multilingual bias, adversarial fragility, ethical risks, and insufficient safety consistency. To address these, this study conducts the first systematic evaluation of its clinical decision-making efficacy and ethical vulnerability across multiple specialties. We propose an “interpretability–safety co-governance” framework, integrating medical knowledge alignment, multi-dimensional safety assessment, and interpretability enhancement techniques. Experimental results demonstrate that DeepSeek-R1 achieves performance on par with GPT-4o on USMLE and AIME benchmarks; attains >92% diagnostic accuracy in pediatric and ophthalmologic support tasks; and—critically—uncovers novel risks, including cross-lingual semantic drift and heightened sensitivity to adversarial prompting. This work establishes both a methodological foundation and empirical benchmark for the safe, trustworthy deployment of open-source LLMs in healthcare.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

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.

Problem

• Evaluating DeepSeek-R1's clinical applications and risks in healthcare
• Assessing open-source LLM capabilities versus proprietary models like GPT-4
• Addressing bias and safety limitations in multilingual medical contexts

Innovation

• Hybrid MoE and CoT reasoning architecture
• Efficient inference for resource-constrained settings
• Open-source MIT license for transparency