Large Language Models in Medicine: Clinical Applications, Technical Challenges, and Ethical Considerations
3
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: This study presents a comprehensive review of the clinical applications, technical challenges, and ethical considerationsassociated with using large language models (LLMs) in medicine. Methods: A literature survey of peer-reviewed articles,technical reports, and expert commentary from relevant medical and artificial intelligence journals was conducted. Keyclinical application areas, technical limitations (e.g., accuracy, validation, transparency), and ethical issues (e.g., bias, safety,accountability, privacy) were identified and analyzed. Results: LLMs have potential in clinical documentation assistance, decisionsupport, patient communication, and workflow optimization. The level of supporting evidence varies; documentationsupport applications are relatively mature, whereas autonomous diagnostics continue to face notable limitations regardingaccuracy and validation. Key technical challenges include model hallucination, lack of robust clinical validation, integrationissues, and limited transparency. Ethical concerns involve algorithmic bias risking health inequities, threats to patient safetyfrom inaccuracies, unclear accountability, data privacy, and impacts on clinician-patient interactions. Conclusions: LLMspossess transformative potential for clinical medicine, particularly by augmenting clinician capabilities. However, substantialtechnical and ethical hurdles necessitate rigorous research, validation, clearly defined guidelines, and human oversight. Existingevidence supports an assistive rather than autonomous role, mandating careful, evidence-based integration that prioritizespatient safety and equity.
Abstract
Objectives: This study presents a comprehensive review of the clinical applications, technical challenges, and ethical considerationsassociated with using large language models (LLMs) in medicine. Methods: A literature survey of peer-reviewed articles,technical reports, and expert commentary from relevant medical and artificial intelligence journals was conducted. Keyclinical application areas, technical limitations (e.g., accuracy, validation, transparency), and ethical issues (e.g., bias, safety,accountability, privacy) were identified and analyzed. Results: LLMs have potential in clinical documentation assistance, decisionsupport, patient communication, and workflow optimization. The level of supporting evidence varies; documentationsupport applications are relatively mature, whereas autonomous diagnostics continue to face notable limitations regardingaccuracy and validation. Key technical challenges include model hallucination, lack of robust clinical validation, integrationissues, and limited transparency. Ethical concerns involve algorithmic bias risking health inequities, threats to patient safetyfrom inaccuracies, unclear accountability, data privacy, and impacts on clinician-patient interactions. Conclusions: LLMspossess transformative potential for clinical medicine, particularly by augmenting clinician capabilities. However, substantialtechnical and ethical hurdles necessitate rigorous research, validation, clearly defined guidelines, and human oversight. Existingevidence supports an assistive rather than autonomous role, mandating careful, evidence-based integration that prioritizespatient safety and equity.