Scholarlink

Background <p>Pancreatic cancer requires nuanced, multidisciplinary treatment planning typically conducted within tumor boards. While Large Language Models (LLMs) have shown capabilities in medical reasoning, their ability to approximate complex, integrative decision-making in oncology remains underexplored.</p> Methods <p>This study evaluated the performance of LLaMA 3.3 (70b) in predicting tumor board decisions for newly diagnosed pancreatic cancer patients. Clinical documentation (including free-text imaging reports, pathology findings, and patient history) from 42 first-diagnosis cases discussed in a real-world tumor board was collected. The model was tasked with predicting one of three treatment options: surgical resection (SURG), neoadjuvant chemotherapy (NEO), or palliative therapy (PALL). Four prompting strategies were evaluated: zero-shot, advanced (adv.) zero-shot, Chain-of-Thought (CoT), and few-shot prompting. Performance was assessed using accuracy, micro- and macro-averaged F1 scores, and category-specific recall.</p> Results <p>The advanced zero-shot and CoT strategies achieved the highest overall accuracy of 78.6% and a micro-averaged F1 score of 0.786. However, this performance was driven primarily by the correct classification of majority classes (SURG and PALL). Crucially, both high-accuracy strategies failed to identify any of the neoadjuvant therapy candidates (Recall NEO = 0.00; 0/7 cases), systematically misclassifying them as palliative or surgical. While few-shot prompting improved the detection of neoadjuvant cases (Recall NEO = 1.00), it introduced substantial noise, reducing overall accuracy to 56.7%. LLaMA 3.3 (70b) demonstrates high concordance with tumor board decisions for clear-cut surgical or palliative cases but exhibits a critical systematic failure in identifying candidates for neoadjuvant therapy. The high global accuracy masks a significant safety limitation regarding the recognition of complex, intermediate-stage patients.</p> Conclusion <p>These findings suggest that current LLMs may approximate majority-class decisions but risk overlooking curative treatment pathways in nuanced scenarios, necessitating rigorous oversight and specific adaptation before clinical consideration</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-assisted tumor board decision-making in pancreatic oncology

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月20日

查看全文
  • Markus Mergen,
  • Felix Busch,
  • Benjamin Schwarberg,
  • Pia Koldeweihe,
  • David Jungwirth,
  • Jonas Sydlik,
  • H. Carlo Maurer,
  • Marcus R. Makowski,
  • Daniel Spitzl,
  • Florian T. Gassert

摘要

Background

Pancreatic cancer requires nuanced, multidisciplinary treatment planning typically conducted within tumor boards. While Large Language Models (LLMs) have shown capabilities in medical reasoning, their ability to approximate complex, integrative decision-making in oncology remains underexplored.

Methods

This study evaluated the performance of LLaMA 3.3 (70b) in predicting tumor board decisions for newly diagnosed pancreatic cancer patients. Clinical documentation (including free-text imaging reports, pathology findings, and patient history) from 42 first-diagnosis cases discussed in a real-world tumor board was collected. The model was tasked with predicting one of three treatment options: surgical resection (SURG), neoadjuvant chemotherapy (NEO), or palliative therapy (PALL). Four prompting strategies were evaluated: zero-shot, advanced (adv.) zero-shot, Chain-of-Thought (CoT), and few-shot prompting. Performance was assessed using accuracy, micro- and macro-averaged F1 scores, and category-specific recall.

Results

The advanced zero-shot and CoT strategies achieved the highest overall accuracy of 78.6% and a micro-averaged F1 score of 0.786. However, this performance was driven primarily by the correct classification of majority classes (SURG and PALL). Crucially, both high-accuracy strategies failed to identify any of the neoadjuvant therapy candidates (Recall NEO = 0.00; 0/7 cases), systematically misclassifying them as palliative or surgical. While few-shot prompting improved the detection of neoadjuvant cases (Recall NEO = 1.00), it introduced substantial noise, reducing overall accuracy to 56.7%. LLaMA 3.3 (70b) demonstrates high concordance with tumor board decisions for clear-cut surgical or palliative cases but exhibits a critical systematic failure in identifying candidates for neoadjuvant therapy. The high global accuracy masks a significant safety limitation regarding the recognition of complex, intermediate-stage patients.

Conclusion

These findings suggest that current LLMs may approximate majority-class decisions but risk overlooking curative treatment pathways in nuanced scenarios, necessitating rigorous oversight and specific adaptation before clinical consideration