English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large language models (LLMs) have demonstrated exceptional capabilities inplanning and tool utilization as autonomous agents, but few have been developedfor medical problem-solving. We propose EHRAgent1, an LLM agent empowered witha code interface, to autonomously generate and execute code for complexclinical tasks within electronic health records (EHRs). First, we formulate anEHR question-answering task into a tool-use planning process, efficientlydecomposing a complicated task into a sequence of manageable actions. Byintegrating interactive coding and execution feedback, EHRAgent learns fromerror messages and improves the originally generated code through iterations.Furthermore, we enhance the LLM agent by incorporating long-term memory, whichallows EHRAgent to effectively select and build upon the most relevantsuccessful cases from past experiences. Experiments on two real-world EHRdatasets show that EHRAgent outperforms the strongest LLM agent baseline by36.48% and 12.41%, respectively. EHRAgent leverages the emerging few-shotlearning capabilities of LLMs, enabling autonomous code generation andexecution to tackle complex clinical tasks with minimal demonstrations.

EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records