Page 32 - AIH-1-2

Artificial Intelligence in Health LLMs-Healthcare: Application and challenges

rare medical cases. As LLMs become more integrated into A survey. ACM Comput Surv. 2023;56:1-40.
patient care, research addressing the ethical implications, doi: 10.1145/3605943
including data privacy, the balance between automation
and human intervention, and informed patient consent, 2. Wei J, Tay Y, Bommasani R, et al. Emergent Abilities of Large
will be paramount. Collaborative research exploring the Language Models. arXiv:2206.07682 [arXiv Preprint]; 2022.
fusion of LLMs with other emerging technologies, such as 3. Brown T, Mann B, Ryder N, et al. Language models
augmented reality or wearable health devices, can open new are few-shot learners. Adv Neural Inform Process Syst.
avenues for patient care and remote monitoring. Enhancing 2020;33:1877-1901.
the LLM’s contextual understanding is crucial. Future work 4. Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L,
should focus on the model’s ability to consider a patient’s Tan TF, Ting DSW. Large language models in medicine. Nat
medical history and present conditions before offering Med. 2023;29:1930-1940.
recommendations. In summary, the horizon of LLMs in doi: 10.1038/s41591-023-02448-8
healthcare is expansive and promising. As we continue to 5. Cascella M, Montomoli J, Bellini V, Bignami E. Evaluating the
witness the convergence of technology and medicine, the feasibility of ChatGPT in healthcare: An analysis of multiple
collaboration of multidisciplinary teams expertise from AI, clinical and research scenarios. J Med Syst. 2023;47:33.
medicine, ethics, and other domains – will be integral to
harnessing the full potential of LLMs in healthcare. doi: 10.1007/s10916-023-01925-4
6. Sorin V, Klang E, Sklair-Levy M, et al. Large language model
Acknowledgments (ChatGPT) as a support tool for breast tumor board. NPJ
Breast Cancer. 2023;9:44.
None.
doi: 10.1038/s41523-023-00557-8
Funding 7. Lukac S, Dayan D, Fink V, et al. Evaluating ChatGPT as an

None. adjunct for the multidisciplinary tumor board decision-
making in primary breast cancer cases. Arch Gynecol Obstet.
Conflict of interest 2023;308:1831-1844.

The authors declare that they have no competing interest. doi: 10.1007/s00404-023-07130-5
8. Gebrael G, Sahu KK, Chigarira B, et al. Enhancing triage
Author contributions efficiency and accuracy in emergency rooms for patients

Conceptualization: All authors with metastatic prostate cancer: A retrospective analysis
of artificial intelligence-assisted triage using ChatGPT 4.0.
Writing – original draft: All authors Cancers (Basel). 2023;15:3717.
Writing – review & editing: All authors
All authors contributed equally. doi: 10.3390/cancers15143717
9. Rao A, Kim J, Kamineni M, et al. Evaluating GPT as an
Ethics approval and consent to participate adjunct for radiologic decision making: GPT-4 Versus
Not applicable. GPT-3.5 in a breast imaging pilot. J Am Coll Radiol.
2023;20:990-997.
Consent for publication doi: 10.1016/j.jacr.2023.05.003
Not applicable. 10. Haver HL, Ambinder EB, Bahl M, Oluyemi ET, Jeudy J,
Yi PH. Appropriateness of breast cancer prevention and
Availability of data screening recommendations provided by ChatGPT.
Radiology. 2023;307:e230424.
Not applicable
doi: 10.1148/radiol.230424
Further disclosure 11. Sarraju A, Bruemmer D, Van Iterson E, Cho L, Rodriguez F,
The paper has been uploaded to or deposited in a preprint Laffin L. Appropriateness of cardiovascular disease
server (Cornell University Arxiv https://doi.org/10.48550/ prevention recommendations obtained from a popular
arXiv.2311.12882). online chat-based artificial intelligence model. JAMA.
2023;329:842-844.
References doi: 10.1001/jama.2023.1044

1. Min B, Ross H, Sulem E, et al. Recent advances in natural 12. Schulte B. capacity of ChatGPT to identify guideline-
language processing via large pre-trained language models: based treatments for advanced solid tumors. Cureus.

Volume 1 Issue 2 (2024) 26 doi: 10.36922/aih.2558