Ziqing Su, Guozhang Tang, Rui Huang, Yang Qiao, Zheng Zhang, Xingliang Dai
{"title":"Based on Medicine, The Now and Future of Large Language Models","authors":"Ziqing Su, Guozhang Tang, Rui Huang, Yang Qiao, Zheng Zhang, Xingliang Dai","doi":"10.1007/s12195-024-00820-3","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Objectives</h3><p>This review explores the potential applications of large language models (LLMs) such as ChatGPT, GPT-3.5, and GPT-4 in the medical field, aiming to encourage their prudent use, provide professional support, and develop accessible medical AI tools that adhere to healthcare standards.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>This paper examines the impact of technologies such as OpenAI's Generative Pre-trained Transformers (GPT) series, including GPT-3.5 and GPT-4, and other large language models (LLMs) in medical education, scientific research, clinical practice, and nursing. Specifically, it includes supporting curriculum design, acting as personalized learning assistants, creating standardized simulated patient scenarios in education; assisting with writing papers, data analysis, and optimizing experimental designs in scientific research; aiding in medical imaging analysis, decision-making, patient education, and communication in clinical practice; and reducing repetitive tasks, promoting personalized care and self-care, providing psychological support, and enhancing management efficiency in nursing.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>LLMs, including ChatGPT, have demonstrated significant potential and effectiveness in the aforementioned areas, yet their deployment in healthcare settings is fraught with ethical complexities, potential lack of empathy, and risks of biased responses.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Despite these challenges, significant medical advancements can be expected through the proper use of LLMs and appropriate policy guidance. Future research should focus on overcoming these barriers to ensure the effective and ethical application of LLMs in the medical field.</p>","PeriodicalId":9687,"journal":{"name":"Cellular and molecular bioengineering","volume":"16 1","pages":""},"PeriodicalIF":2.3000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cellular and molecular bioengineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s12195-024-00820-3","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOPHYSICS","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives
This review explores the potential applications of large language models (LLMs) such as ChatGPT, GPT-3.5, and GPT-4 in the medical field, aiming to encourage their prudent use, provide professional support, and develop accessible medical AI tools that adhere to healthcare standards.
Methods
This paper examines the impact of technologies such as OpenAI's Generative Pre-trained Transformers (GPT) series, including GPT-3.5 and GPT-4, and other large language models (LLMs) in medical education, scientific research, clinical practice, and nursing. Specifically, it includes supporting curriculum design, acting as personalized learning assistants, creating standardized simulated patient scenarios in education; assisting with writing papers, data analysis, and optimizing experimental designs in scientific research; aiding in medical imaging analysis, decision-making, patient education, and communication in clinical practice; and reducing repetitive tasks, promoting personalized care and self-care, providing psychological support, and enhancing management efficiency in nursing.
Results
LLMs, including ChatGPT, have demonstrated significant potential and effectiveness in the aforementioned areas, yet their deployment in healthcare settings is fraught with ethical complexities, potential lack of empathy, and risks of biased responses.
Conclusion
Despite these challenges, significant medical advancements can be expected through the proper use of LLMs and appropriate policy guidance. Future research should focus on overcoming these barriers to ensure the effective and ethical application of LLMs in the medical field.
期刊介绍:
The field of cellular and molecular bioengineering seeks to understand, so that we may ultimately control, the mechanical, chemical, and electrical processes of the cell. A key challenge in improving human health is to understand how cellular behavior arises from molecular-level interactions. CMBE, an official journal of the Biomedical Engineering Society, publishes original research and review papers in the following seven general areas:
Molecular: DNA-protein/RNA-protein interactions, protein folding and function, protein-protein and receptor-ligand interactions, lipids, polysaccharides, molecular motors, and the biophysics of macromolecules that function as therapeutics or engineered matrices, for example.
Cellular: Studies of how cells sense physicochemical events surrounding and within cells, and how cells transduce these events into biological responses. Specific cell processes of interest include cell growth, differentiation, migration, signal transduction, protein secretion and transport, gene expression and regulation, and cell-matrix interactions.
Mechanobiology: The mechanical properties of cells and biomolecules, cellular/molecular force generation and adhesion, the response of cells to their mechanical microenvironment, and mechanotransduction in response to various physical forces such as fluid shear stress.
Nanomedicine: The engineering of nanoparticles for advanced drug delivery and molecular imaging applications, with particular focus on the interaction of such particles with living cells. Also, the application of nanostructured materials to control the behavior of cells and biomolecules.