The Impact of Large Language Models on Health and Medical Informatics


Erdem Demir R., Kalaycı M. E., Özdemir S., Turhan K.

16. Tıp Bilişimi Kongresi, Ankara, Türkiye, 22 - 23 Mayıs 2025, ss.148-154, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Ankara
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.148-154
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

In recent years, Large Language Models (LLMs) such as GPT, PaLM, and LLaMA have begun to reshape the landscape of health and medical informatics. With their ability to understand and generate human language at an advanced level, these models are being increasingly explored for applications like clinical documentation, decision support systems, and biomedical literature analysis. Their potential to ease clinicians' workload and enhance patient care is significant. However, their adoption also brings important concerns—especially around accuracy, bias, privacy, and explainability. Ethical and legal questions remain, particularly when it comes to aligning these systems with evidence-based medical practices and determining responsibility in clinical use cases. The aim of this study is to comprehensively examine the transformative impact of LLMs on health and medical informatics by reviewing current applications, ethical concerns, limitations, and future prospects. Looking ahead, future research is likely to focus on fine-tuning LLMs for specific medical domains, integrating them with multimodal data sources, and designing tools that can be used directly by patients. While the promise of LLMs is clear, realizing their full potential will require careful validation, close collaboration between disciplines, and adaptive regulatory approaches.