Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Dong, Wei, Yanzhe, He, Zonglin, Kuang, Guan-Ming, Ye, Canhua, An, Meiru, Peng, Huili, Hu, Yong, Tao, Huiren, Cheung, Kenneth MC
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.00588
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917095193706496
author Chen, Dong
Wei, Yanzhe
He, Zonglin
Kuang, Guan-Ming
Ye, Canhua
An, Meiru
Peng, Huili
Hu, Yong
Tao, Huiren
Cheung, Kenneth MC
author_facet Chen, Dong
Wei, Yanzhe
He, Zonglin
Kuang, Guan-Ming
Ye, Canhua
An, Meiru
Peng, Huili
Hu, Yong
Tao, Huiren
Cheung, Kenneth MC
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00588
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential Validation
Chen, Dong
Wei, Yanzhe
He, Zonglin
Kuang, Guan-Ming
Ye, Canhua
An, Meiru
Peng, Huili
Hu, Yong
Tao, Huiren
Cheung, Kenneth MC
Machine Learning
Artificial Intelligence
Computers and Society
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.
title Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential Validation
topic Machine Learning
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2511.00588