Large language models are few-shot clinical information extractors

A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes. However, roadblocks have included dataset shift from the general domain and a lack of public clinical corpora and annotations. In this work, we show that large language models, such as InstructGPT (Ouyang et al., 2022), perform well at zero- and few-shot information extraction from clinical text despite not being trained specifically for the clinical domain. Whereas text classification and generation performance have already been studied extensively in such models, here we additionally demonstrate how to leverage them to tackle a diverse set of NLP tasks which require more structured outputs,…

• NS
  National Science Foundation

  Award: 1723344
• CS
  Cisco Systems
• MS
  Memorial Sloan-Kettering Cancer Center
• N
  Nvidia
• DA
  Deutscher Akademischer Austauschdienst
• DC
  Deshpande Center for Technological Innovation, Massachusetts Institute of Technology