The modern directions of implementation of the large models of artificial intelligence in health care. Review
DOI:
https://doi.org/10.32782/2786-7684/2024-2-30Keywords:
artificial intelligence, models, health care, biology, improvementAbstract
Introduction. Large models of artificial intelligence (or as «base models») are relatively new cloud software complexes and solutions that specialize in working with large arrays of data and parameters. After conducting preliminary training, such models demonstrate impressive performance in performing a variety of applied and theoretical tasks. In health care, the emergence of large-scale artificial intelligence (AI) models has prompted the development of a new paradigm for the improvement and development of methodological approaches in data evaluation and the development of decision-making systems. Research methodology and methods. The purpose of the study is to analyze the available sources of scientific and medical information devoted to the application of large models of artificial intelligence in health care. An information search of available information was carried out in open databases of medical publications – «PubMed», «Researchgate», «Google Scholar» and electronic depositories of texts of scientific and educational institutions. The search depth was 10 years. Presentation of the main research material. A prime example of large AI models are «ChatGPT», «Microsoft Copilot», «Google Gemini», «Claude», «Segment Anything» and «Copy.ai». Large-scale artificial intelligence models are gradually becoming powerful tools for solving various tasks in the field of health care. Today, seven key sectors of health care can be identified, within which the significant impact of large models of artificial intelligence can be determined: 1) bioinformatics; 2) medical diagnosis; 3) medical imaging; 4) medical informatics; 5) medical education; 6) public health; 7) medical robotics. Modern large AI models are relatively "raw" and need to be refined and adapted to each healthcare sector. Conclusions. Over time, large models of artificial intelligence may become mandatory components of the health care system, which will ensure its functioning and further development. It is worth noting the constant changes in the paradigm of the development of artificial intelligence, which contributes to the creation of large models of artificial intelligence for the transformation of various sectors of health care and biology. The further successful development of cooperation between artificial intelligence and health care requires the introduction of certain regulatory approaches to reduce potential risks and prevent conflicts of interest, which will lead the industry to a new stage of development.
References
Alam MZ, Proteek SM, Hoque I. A systematic literature review on mHealth related research during the COVID-19 outbreak. Med Educ. 2023;123(1):19-40. doi: 10.1108/he-08-2022-0067
Gibbons M, Shaikh Y. Introduction to consumer health informatics and digital inclusion. In: Edmunds M, Hass C, Holve E, editors. Consumer Informatics and Digital Health: Solutions for Health and Health Care. Cham, Switzerland: Springer; 2019. р. 25-41.
Briganti G, Le Moine O. Artificial intelligence in medicine: today and tomorrow. Front Med (Lausanne) 2020 Feb 05;7:27. doi: 10.3389/fmed.2020.00027
Qiu J, Li L, Sun J, Peng J, Shi P, Zhang R, Dong Y, Lam K, Lo FP, Xiao B, Yuan W, Wang N, Xu D, Lo B. Large AI Models in Health Informatics: Applications, Challenges, and the Future. IEEE J Biomed Health Inform. 2023 Dec;27(12):6074-6087. doi: 10.1109/JBHI.2023.3316750.
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. arXiv (Cornell University) [Internet]. 2017 Jan 1; Available from: https://arxiv.org/abs/1706.03762
Wang J, Cheng Z, Yao Q, Liu L, Xu D, Hu G. Bioinformatics and biomedical informatics with ChatGPT: Year one review. ArXiv [Preprint]. 2024 Jun 12:arXiv:2403.15274v2.
Qiu J, Yuan W, Lam K. The application of multimodal large language models in medicine. Lancet Reg Health West Pac. 2024 Mar 16;45:101048. doi: 10.1016/j.lanwpc.2024.101048.
Gillani M, Pollastri G. Protein subcellular localization prediction tools. Comput Struct Biotechnol J. 2024 Apr 15;23:1796-1807. doi: 10.1016/j.csbj.2024.04.032.
Zhao H, Du H, Zhao S, Chen Z, Li Y, Xu K, Liu B, Cheng X, Wen W, Li G, Chen G, Zhao Z, Qiu G; Deciphering Disorders Involving Scoliosis & Comorbidities (DISCO) Study; Liu P, Zhang TJ, Wu Z, Wu N. SIGMA leverages protein structural information to predict the pathogenicity of missense variants. Cell Rep Methods. 2024 Jan 22;4(1):100687. doi: 10.1016/j.crmeth.2023.100687.
Wang S, Zhao Z, Ouyang X, Wang Q, Shen D. ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models. arXiv (Cornell University) [Internet]. 2023 Jan 1; Available from: https://arxiv.org/abs/2302.07257
Thawkar O, Shaker A, Mullappilly SS, Cholakkal H, Anwer RM, Khan S, et al. XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models. arXiv (Cornell University) [Internet]. 2023 Jan 1; Available from: https://arxiv.org/abs/2306.07971
Yunxiang L, Zihan L, Kai Z, Ruilong D, You Z. ChatDoctor: A medical chat model Fine-Tuned on a large language model Meta-AI (LLAMA) using medical domain knowledge. arXiv (Cornell University) [Internet]. 2023 Jan 1; Available from: https://arxiv.org/abs/2303.14070
Li Y, Rao S, Solares JRA, Hassaine A, Ramakrishnan R, Canoy D, et al. BEHRT: Transformer for electronic health records. Scientific Reports [Internet]. 2020 Apr 28;10(1). Available from: https://doi.org/10.1038/s41598-020-62922-y
Rasmy L, Xiang Y, Xie Z, Tao C, Zhi D. Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction. NPJ Digit Med. 2021 May 20;4(1):86. doi: 10.1038/s41746-021-00455-y.
Vaid A, Jiang J, Sawant A, Lerakis S, Argulian E, Ahuja Y, Lampert J, Charney A, Greenspan H, Narula J, Glicksberg B, Nadkarni GN. A foundational vision transformer improves diagnostic performance for electrocardiograms. NPJ Digit Med. 2023 Jun 6;6(1):108. doi: 10.1038/s41746-023-00840-9.
Hughes JW, Olgin JE, Avram R, Abreau SA, Sittler T, Radia K, Hsia H, Walters T, Lee B, Gonzalez JE, Tison GH. Performance of a Convolutional Neural Network and Explainability Technique for 12-Lead Electrocardiogram Interpretation. JAMA Cardiol. 2021 Nov 1;6(11):1285-1295. doi: 10.1001/jamacardio.2021.2746.
Wang Z, Wu Z, Agarwal D, Sun J. MedCLIP: Contrastive Learning from Unpaired Medical Images and Text. Proc Conf Empir Methods Nat Lang Process. 2022 Dec;2022:3876-3887. doi: 10.18653/v1/2022.emnlp-main.256
Huang Z, Bianchi F, Yuksekgonul M, Montine TJ, Zou J. A visual-language foundation model for pathology image analysis using medical Twitter. Nat Med. 2023 Sep;29(9):2307-2316. doi: 10.1038/s41591-023-02504-3.
Chambon P, Bluethgen C, Langlotz CP, Chaudhari A. Adapting pretrained Vision-Language foundational models to medical imaging domains. arXiv (Cornell University) [Internet]. 2022 Jan 1; Available from: https://arxiv.org/abs/2210.04133
Huang Z, Wang H, Deng Z, Ye J, Su Y, Sun H, et al. STU-NET: Scalable and transferable medical image segmentation models empowered by Large-Scale Supervised Pre-training. arXiv (Cornell University) [Internet]. 2023 Jan 1; Available from: https://arxiv.org/abs/2304.06716
Abdelkader W, Navarro T, Parrish R, Cotoi C, Germini F, Linkins LA, Iorio A, Haynes RB, Ananiadou S, Chu L, Lokker C. A Deep Learning Approach to Refine the Identification of High-Quality Clinical Research Articles From the Biomedical Literature: Protocol for Algorithm Development and Validation. JMIR Res Protoc. 2021 Nov 29;10(11):e29398. doi: 10.2196/29398.
Lokker C, McKibbon KA, Afzal M, Navarro T, Linkins LA, Haynes RB, Iorio A. The McMaster Health Information Research Unit: Over a Quarter-Century of Health Informatics Supporting Evidence-Based Medicine. J Med Internet Res. 2024 Jul 31;26:e58764. doi: 10.2196/58764.
Harris E. Large Language Models Answer Medical Questions Accurately, but Can't Match Clinicians' Knowledge. JAMA. 2023 Sep 5;330(9):792-794. doi: 10.1001/jama.2023.14311.
Zhui L, Yhap N, Liping L, Zhengjie W, Zhonghao X, Xiaoshu Y, Hong C, Xuexiu L, Wei R. Impact of Large Language Models on Medical Education and Teaching Adaptations. JMIR Med Inform. 2024 Jul 25;12:e55933. doi: 10.2196/55933.
Wójcik S, Rulkiewicz A, Pruszczyk P, Lisik W, Poboży M, Domienik-Karłowicz J. Beyond ChatGPT: What does GPT-4 add to healthcare? The dawn of a new era. Cardiol J. 2023;30(6):1018-1025. doi: 10.5603/cj.97515.
Hao Y, Li B, Huang D, Wu S, Wang T, Fu L, Liu X. Developing a Semi-Supervised Approach Using a PU-Learning-Based Data Augmentation Strategy for Multitarget Drug Discovery. Int J Mol Sci. 2024 Jul 28;25(15):8239. doi: 10.3390/ijms25158239.
Korngiebel DM, Mooney SD. Considering the possibilities and pitfalls of Generative Pre-trained Transformer 3 (GPT-3) in healthcare delivery. NPJ Digit Med. 2021 Jun 3;4(1):93. doi: 10.1038/s41746-021-00464-x.
Sun J, Huang L, Wang H, Zheng C, Qiu J, Islam MT, Xie E, Zhou B, Xing L, Chandrasekaran A, Black MJ. Localization and recognition of human action in 3D using transformers. Commun Eng. 2024 Sep 3;3(1):125. doi: 10.1038/s44172-024-00272-7.
Gilbert S, Harvey H, Melvin T, Vollebregt E, Wicks P. Large language model AI chatbots require approval as medical devices. Nat Med. 2023 Oct;29(10):2396-2398. doi: 10.1038/s41591-023-02412-6.
Knudsen JE, Ghaffar U, Ma R, Hung AJ. Clinical applications of artificial intelligence in robotic surgery. J Robot Surg. 2024 Mar 1;18(1):102. doi: 10.1007/s11701-024-01867-0.
Guni A, Varma P, Zhang J, Fehervari M, Ashrafian H. Artificial Intelligence in Surgery: The Future is Now. European Surgical Research [Internet]. 2024 Jan 22; Available from: https://doi.org/10.1159/000536393
