ARTICLE   Open Access    

Advanced prompting as a catalyst: Empowering large language models in the management of gastrointestinal cancers

    Show all affliationsShow less
More Information
    1. Prompt engineering affects large language models' performance in GI oncology.

      Prompts with templates and in-context learning enhance large language models' output.

      Multi-round interaction helps large language models to reach the best performance.

      Such performance meets the need of senior GI oncologists for effective AI agents.

  • Large Language Models' (LLMs) performance in healthcare can be significantly impacted by prompt engineering. However, the area of study remains relatively uncharted in gastrointestinal oncology until now. Our research delves into this unexplored territory, investigating the efficacy of varied prompting strategies, including simple prompts, templated prompts, in-context learning (ICL), and multi-round iterative questioning, for optimizing the performance of LLMs within a medical setting. We develop a comprehensive evaluation system to assess the performance of LLMs across multiple dimensions. This robust evaluation system ensures a thorough assessment of the LLMs' capabilities in the field of medicine. Our findings suggest a positive relationship between the comprehensiveness of the prompts and the LLMs' performance. Notably, the multi-round strategy, which is characterized by iterative question-and-answer rounds, consistently yields the best results. ICL, a strategy that capitalizes on interrelated contextual learning, also displays significant promise, surpassing the outcomes achieved with simpler prompts. The research underscores the potential of advanced prompt engineering and iterative learning approaches for boosting the applicability of LLMs in healthcare. We recommend that additional research be conducted to refine these strategies and investigate their potential integration, to truly harness the full potential of LLMs in medical applications.
  • 加载中
  • [1] OpenAI, R. (2023). GPT-4 technical report. arXiv 2303.08774.

    View in Article Google Scholar

    [2] Lee, P., Bubeck, S., and Petro, J. (2023). Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N. Engl. J. Med. 388, 1233-1239.

    View in Article CrossRef Google Scholar

    [3] Lee, P., Goldberg, C., and Kohane, I. (2023). The AI revolution in medicine: GPT-4 and beyond (Pearson Education, Limited).

    View in Article Google Scholar

    [4] Xu, Y., Liu, X., Cao, X., et al. (2021). Artificial intelligence: a powerful paradigm for scientific research. The Innovation 2, 100179.

    View in Article Google Scholar

    [5] Nori, H., King, N., McKinney, S.M., et al. (2023). Capabilities of GPT-4 on medical challenge problems. arXiv preprint arXiv:2303.13375.

    View in Article Google Scholar

    [6] Ayers, J.W., Poliak, A., Dredze, M., et al. (2023). Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern. Med. 183, 589-596.

    View in Article CrossRef Google Scholar

    [7] Haver, H.L., Ambinder, E.B., Bahl, M., et al. (2023). Appropriateness of breast cancer prevention and screening recommendations provided by ChatGPT. Radiology 307, e230424.

    View in Article CrossRef Google Scholar

    [8] Zhu, L., Mou, W., and Chen, R. (2023). Can the ChatGPT and other large language models with internet-connected database solve the questions and concerns of patient with prostate cancer and help democratize medical knowledge? J. Transl. Med. 21, 1-4.

    View in Article CrossRef Google Scholar

    [9] Uprety, D., Zhu, D., and West, H.J. (2023). ChatGPT-a promising generative AI tool and its implications for cancer care. Cancer 129, 2284-2289.

    View in Article CrossRef Google Scholar

    [10] Zhong, Y., Chen, Y.J., Zhou, Y., et al. (2023). The artificial intelligence large language models and neuropsychiatry practice and research ethic. Asian J. Psychiatr. 84, 103577.

    View in Article CrossRef Google Scholar

    [11] Young, J.N., Ross, O.H., Poplausky, D., et al. (2023). The utility of ChatGPT in generating patient-facing and clinical responses for melanoma. J. Am. Acad. Dermatol., 1-3.

    View in Article Google Scholar

    [12] Xie, Y., Seth, I., Hunter-Smith, D.J., et al. (2023). Aesthetic surgery advice and counseling from artificial intelligence: a rhinoplasty consultation with ChatGPT. Aesth. Plast. Surg., 1-9.

    View in Article Google Scholar

    [13] Buzzaccarini, G., Degliuomini, R.S., and Borin, M. (2023). The artificial intelligence application in aesthetic medicine: how ChatGPT can revolutionize the aesthetic world. Aesth. Plast. Surg., 1-2.

    View in Article Google Scholar

    [14] Radford, A., Wu, J., Child, R., et al. (2019). Language models are unsupervised multitask learners. OpenAI blog 1, 9.

    View in Article Google Scholar

    [15] Brown, T., Mann, B., Ryder, N., et al. (2020). Language models are few-shot learners. NeurIPS 33, 1877-1901.

    View in Article Google Scholar

    [16] Lewis, P., Perez, E., Piktus, A., et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. NeurIPS 33, 9459-9474.

    View in Article Google Scholar

    [17] Wei, J., Wang, X., Schuurmans, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. NeurIPS 35, 24824-24837.

    View in Article Google Scholar

    [18] Zhou, D., Schärli, N., Hou, L., et al. (2022). Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:2205.10625.

    View in Article Google Scholar

    [19] Yao, S., Yu, D., Zhao, J., et al. (2023). Tree of thoughts: deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601.

    View in Article Google Scholar

    [20] Fu, Y., Peng, H., Sabharwal, A., et al. (2022). Complexity-based prompting for multi-step reasoning. arXiv preprint arXiv:2210.00720.

    View in Article Google Scholar

    [21] Khot, T., Trivedi, H., Finlayson, M., et al. (2022). Decomposed prompting: a modular approach for solving complex tasks. arXiv preprint arXiv:2210.02406.

    View in Article Google Scholar

    [22] White, J., Fu, Q., Hays, S., et al. (2023). A prompt pattern catalog to enhance prompt engineering with ChatGPT. arXiv preprint arXiv:2302.11382.

    View in Article Google Scholar

    [23] Suzgun, M., Scales, N., Schärli, N., et al. (2022). Challenging big-bench tasks and whether chain-of-thought can solve them. arXiv preprint arXiv:2210.09261.

    View in Article Google Scholar

  • Cite this article:

    Yuan J., Bao P., Chen Z.,  et al., (2023). Advanced prompting as a catalyst: Empowering large language models in the management of gastrointestinal cancers. The Innovation Medicine 1(2), 100019. https://doi.org/10.59717/j.xinn-med.2023.100019
    Yuan J., Bao P., Chen Z.,  et al., (2023). Advanced prompting as a catalyst: Empowering large language models in the management of gastrointestinal cancers. The Innovation Medicine 1(2), 100019. https://doi.org/10.59717/j.xinn-med.2023.100019

Figures(4)     Tables(4)

Share

  • Share the QR code with wechat scanning code to friends and circle of friends.

Article Metrics

Article views(2477) PDF downloads(768) Cited by(0)

Relative Articles

Article Contents

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint