诊断人工智能手术决策支持中的幻觉风险：一种用于序列验证的连续框架
Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential Validation
AI总结：
本文提出了一种用于评估人工智能手术决策支持系统幻觉风险的连续框架，通过多维度测试揭示模型在复杂性下的脆弱性，并强调了增强推理能力的必要性。
摘要：
大型语言模型（LLMs）在脊柱手术临床决策支持中具有变革性潜力，但通过幻觉（事实不一致或上下文不匹配的输出）带来了显著风险，可能危及患者安全。本研究引入了一个以临床医生为中心的框架，通过评估诊断精度、推荐质量、推理稳健性、输出连贯性和知识对齐性来量化幻觉风险。我们评估了六个领先的LLMs在30个由专家验证的脊柱病例中的表现。DeepSeek-R1在总体表现上表现出色（总分：86.03±2.08），特别是在高风险领域如创伤和感染方面。关键发现表明，增强推理能力的模型变体并未普遍优于标准版本：Claude-3.7-Sonnet的扩展思维模式相对于其标准版本表现较差（80.79±1.83 vs. 81.56±1.92），表明仅扩展推理链不足以保证临床可靠性。多维压力测试揭示了模型特定的弱点，推荐质量在复杂性放大时下降了7.4%。这种下降与理性（+2.0%）、可读性（+1.7%）和诊断（+4.7%）的微小改进形成对比，突显了感知连贯性与可操作指导之间的令人担忧的分歧。我们的发现倡导将可解释性机制（如推理链可视化）整合到临床工作流程中，并建立了用于手术LLM部署的安全意识验证框架。
英文摘要：
Large language models (LLMs) offer transformative potential for clinical decision support in spine surgery but pose significant risks through hallucinations, which are factually inconsistent or contextually misaligned outputs that may compromise patient safety. This study introduces a clinician-centered framework to quantify hallucination risks by evaluating diagnostic precision, recommendation quality, reasoning robustness, output coherence, and knowledge alignment. We assessed six leading LLMs across 30 expert-validated spinal cases. DeepSeek-R1 demonstrated superior overall performance (total score: 86.03 $\pm$ 2.08), particularly in high-stakes domains such as trauma and infection. A critical finding reveals that reasoning-enhanced model variants did not uniformly outperform standard counterparts: Claude-3.7-Sonnet's extended thinking mode underperformed relative to its standard version (80.79 $\pm$ 1.83 vs. 81.56 $\pm$ 1.92), indicating extended chain-of-thought reasoning alone is insufficient for clinical reliability. Multidimensional stress-testing exposed model-specific vulnerabilities, with recommendation quality degrading by 7.4% under amplified complexity. This decline contrasted with marginal improvements in rationality (+2.0%), readability (+1.7%) and diagnosis (+4.7%), highlighting a concerning divergence between perceived coherence and actionable guidance. Our findings advocate integrating interpretability mechanisms (e.g., reasoning chain visualization) into clinical workflows and establish a safety-aware validation framework for surgical LLM deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
