Predicting explainable dementia types with LLM-aided feature engineering.

Journal: Bioinformatics (Oxford, England)
PMID: 40199828

Abstract

MOTIVATION: The integration of Machine Learning and Artificial Intelligence (AI) into healthcare has immense potential due to the rapidly growing volume of clinical data. However, existing AI models, particularly Large Language Models (LLMs) like GPT-4, face significant challenges in terms of explainability and reliability, particularly in high-stakes domains like healthcare.

Authors

  • Aditya M Kashyap
    Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104, United States.
  • Delip Rao
    Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104, United States.
  • Mary Regina Boland
    Department of Mathematics and Data Science, Saint Vincent College, Latrobe, PA 15650, United States.
  • Li Shen
    Department of Clinical Pharmacy, Children's Hospital of Fudan University, National Children's Medical Center, Shanghai, China.
  • Chris Callison-Burch
    Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104, United States.

Keywords

External Resources

Popular Topics
Recent Journals