Abstract
Advancements in artificial intelligence (AI) provide many helpful tools for healthcare, one of which includes AI chatbots that use natural language processing to create humanlike, conversational dialog. These chatbots have general cognitive skills and are able to engage with clinicians and patients to discuss patients’ health conditions and what they may be at risk for. While chatbot engines have access to a wide range of medical texts and research papers, they currently provide high-level, generic responses and are limited in their ability to provide diagnostic guidance and clinical advice to patients on an individual level. The essay discusses the use of retrieval-augmented generation (RAG), which can be used to improve the specificity of user-entered prompts and thereby enhance the detail in AI chatbot responses. By embedding more recent clinical data and trusted medical sources, such as clinical guidelines, into the chatbot models, AI chatbots can provide more patient-specific guidance, faster diagnoses and treatment recommendations, and greater improvement of patient outcomes.
References
Ker, J., L. Wang, J. Rao, and T. Lim. Deep learning applications in medical image analysis. IEEE Access. 6:9375–9389, 2018.
Milosevic, N., and W. Thielemann. Comparison of biomedical relationship extraction methods and models for knowledge graph creation. J. Web Semant. 2022. https://doi.org/10.1016/j.websem.2022.100756.
Beaulieu-Jones, B. K., W. Yuan, G. A. Brat, et al. Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians? NPJ Digit. Med. 4:62–62, 2021.
Waisberg, E., J. Ong, M. Masalkhi, et al. GPT-4: a new era of artificial intelligence in medicine. Ir J. Med. Sci. 2023. https://doi.org/10.1007/s11845-023-03377-8.
Lee, P., S. Bubeck, and J. Petro. Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N. Engl. J. Med. 388(13):1233–1239, 2023. https://doi.org/10.1056/nejmsr2214184.
Nori, H., N. King, S. M. McKinney, D. Carignan, and E. Horvitz. Capabilities of GPT-4 on medical challenge problems. arXiv: https://arxiv.org/abs/2303.13375, 2023.
Hanna, T. P., W. D. King, S. Thibodeau, M. Jalink, G. A. Paulin, E. Harvey-Jones, D. E. O’Sullivan, C. M. Booth, R. Sullivan, and A. Aggarwal. Mortality due to cancer treatment delay: systematic review and meta-analysis. BMJ. 2020. https://doi.org/10.1136/bmj.m4087.
Homolak, J. Opportunities and risks of chatgpt in medicine, Science, and Academic Publishing: a modern promethean dilemma. Croat. Med. J. 64(1):1–3, 2023. https://doi.org/10.3325/cmj.2023.64.1.
Lewis, P., E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W. Yih, T. Rocktäschel, S. Riedel, and D. Kiela. Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural Inf. Process. Syst. 33:9459–9474, 2021.
Mishra, A. Machine Learning in the AWS Cloud: Add Intellegence to Applications with Amazon Sagemaker and Amazon Rekognition. Amazon, 2019. https://docs.aws.amazon.com/sagemaker/latest/dg/jumpstart-foundation-models-customize-rag.html.
Funding
Not applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
This submission does not contain any conflicts of interest or competing interests with prior submitted papers.
Additional information
Associate Editor Stefan M. Duma oversaw the review of this article.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wang, C., Ong, J., Wang, C. et al. Potential for GPT Technology to Optimize Future Clinical Decision-Making Using Retrieval-Augmented Generation. Ann Biomed Eng 52, 1115–1118 (2024). https://doi.org/10.1007/s10439-023-03327-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10439-023-03327-6