Login / Signup

Enhancing Early Detection of Cognitive Decline in the Elderly: A Comparative Study Utilizing Large Language Models in Clinical Notes.

Xinsong DuJohn Novoa-LaurentievJoseph M PlasaekYa-Wen ChuangLiqin WangGad MarshallStephanie K MuellerFrank ChangSurabhi DattaHunki PaekBin LinQiang WeiXiaoyan WangJingqi WangHao DingFrank J ManionJingcheng DuDavid W BatesLi Zhou
Published in: medRxiv : the preprint server for health sciences (2024)
LLMs and traditional machine learning models trained using local EHR data exhibited diverse error profiles. The ensemble of these models was found to be complementary, enhancing diagnostic performance. Future research should investigate integrating LLMs with smaller, localized models and incorporating medical data and domain knowledge to enhance performance on specific tasks.
Keyphrases
  • cognitive decline
  • machine learning
  • electronic health record
  • mild cognitive impairment
  • healthcare
  • big data
  • artificial intelligence
  • working memory
  • deep learning
  • current status
  • body composition
  • community dwelling