A survey on the applications of transfer learning to enhance the performance of large language models in healthcare systems

被引:0
作者
Anmol Rahujo [1 ]
Daniya Atif [1 ]
Syed Azeem Inam [1 ]
Abdullah Ayub Khan [2 ]
Sajid Ullah [3 ]
机构
[1] Sindh Madressatul Islam University,Department of Artificial Intelligence and Mathematical Sciences
[2] Bahria University Karachi Campus,Department of Computer Science
[3] Nangarhar University,Department of Water Resources and Environmental Engineering
来源
Discover Artificial Intelligence | / 5卷 / 1期
关键词
Transfer learning; Healthcare system; Large language models; Natural language processing; Medical assistance;
D O I
10.1007/s44163-025-00339-0
中图分类号
学科分类号
摘要
The healthcare field experiences significant developments through transfer learning and large language models that boost medical diagnosis accuracy while improving patient services and clinical process automation. This survey investigates the significant impact of Transfer Learning and large language models on medical systems by explaining their applications in imaging procedures, disease identification, and natural language processing functions for electronic health records analysis and medical decision-making assistance. Pre-trained models employed through TL solve the problems caused by scarce labeled datasets, so systems perform effectively despite low data availability. This research analyzes different transfer learning methods, including inductive, transductive, and unsupervised techniques, while demonstrating their effectiveness in detecting COVID-19 from chest X-rays and multi-source disease evaluation. The remarkable progress of transfer learning cannot overcome crucial obstacles involving data protection vulnerabilities, interpretability issues, and unfavorable knowledge transfer scenarios. The study presents avenues for future investigation, including domain-specific training approaches and privacy-preserving federated systems with reduced processing needs. This study demonstrates effective healthcare solutions based on TL and LLMs but urges researchers to work across disciplines to resolve technical and ethical limitations.
引用
收藏
相关论文
共 50 条
  • [31] Large language models based vulnerability detection: How does it enhance performance?Large language models based vulnerability detection: How does it enhance performance?C.D. Xuan et al.
    Cho Do Xuan
    Dat Bui Quang
    Vinh Dang Quang
    International Journal of Information Security, 2025, 24 (1)
  • [32] Privacy issues in Large Language Models: A survey
    Kibriya, Hareem
    Khan, Wazir Zada
    Siddiqa, Ayesha
    Khan, Muhammad Khurrum
    COMPUTERS & ELECTRICAL ENGINEERING, 2024, 120
  • [33] A survey of table reasoning with large language models
    Zhang, Xuanliang
    Wang, Dingzirui
    Dou, Longxu
    Zhu, Qingfu
    Che, Wanxiang
    FRONTIERS OF COMPUTER SCIENCE, 2025, 19 (09)
  • [34] Large Language Models in Healthcare and Medical Domain: A Review
    Nazi, Zabir Al
    Peng, Wei
    INFORMATICS-BASEL, 2024, 11 (03):
  • [35] Knowledge Editing for Large Language Models: A Survey
    Wang, Song
    Zhu, Yaochen
    Liu, Haochen
    Zheng, Zaiyi
    Chen, Chen
    Li, Jundong
    ACM COMPUTING SURVEYS, 2025, 57 (03)
  • [36] A Survey on Hardware Accelerators for Large Language Models
    Kachris, Christoforos
    APPLIED SCIENCES-BASEL, 2025, 15 (02):
  • [37] Application of large language models in healthcare: A bibliometric analysis
    Zhang, Lanping
    Zhao, Qing
    Zhang, Dandan
    Song, Meijuan
    Zhang, Yu
    Wang, Xiufen
    DIGITAL HEALTH, 2025, 11
  • [38] Embracing Large Language Models for Medical Applications: Opportunities and Challenges
    Karabacak, Mert
    Margetis, Konstantinos
    CUREUS JOURNAL OF MEDICAL SCIENCE, 2023, 15 (05)
  • [39] Large Language Models for Clinical Text Cleansing Enhance Medical Concept Normalization
    Abdulnazar, Akhila
    Roller, Roland
    Schulz, Stefan
    Kreuzthaler, Markus
    IEEE ACCESS, 2024, 12 : 147981 - 147990
  • [40] A Survey of Natural Language-Based Editing of Low-Code Applications Using Large Language Models
    Gorissen, Simon Cornelius
    Sauer, Stefan
    Beckmann, Wolf G.
    HUMAN-CENTERED SOFTWARE ENGINEERING, HCSE 2024, 2024, 14793 : 243 - 254