Blood Pressure Extraction from Literature

Prompt

You are an AI assistant that helps people find information in scientific publications.
Read the abstract carefully:

Please answer the mean and deviation of blood pressure values based on sex.
N is the number of patients, and summaries of SBP and DBP include mean ± standard deviation.
Your answer should be formatted as
'''
N_male=[number]
N_female=[number]
SBP_in_male=[mean ± standard deviation]
SBP_in_female=[mean ± standard deviation]
DBP_in_male=[mean ± standard deviation]
DBP_in_female=[mean ± standard deviation]
'''
Answer "NA" if the information is not found.

Usage Notes

This prompt is from the paper “Leveraging Large Language Models for Analyzing Blood Pressure Variations Across Biological Sex from Scientific Literature” (Guo et al., 2024).

• Task: Automated extraction of sex-disaggregated blood pressure data from PubMed abstracts.
• Model: GPT-3.5-turbo in a zero-shot configuration.
• Input: `` is replaced with the plain text of each PubMed article abstract.
• Pipeline: Abstracts are first filtered by keywords (“blood pressure”, “mmHg”) before prompt-based extraction.
• Application: Enables large-scale meta-analysis of blood pressure variations across biological sex from published literature.