Learn R Programming

AIscreenR (version 0.1.1)

AI Screening Tools in R for Systematic Reviewing

Description

Provides functions to conduct title and abstract screening in systematic reviews using large language models, such as the Generative Pre-trained Transformer (GPT) models from 'OpenAI' . These functions can enhance the quality of title and abstract screenings while reducing the total screening time significantly. In addition, the package includes tools for quality assessment of title and abstract screenings, as described in Vembye, Christensen, Mølgaard, and Schytt (2024) .

Copy Link

Version

Install

install.packages('AIscreenR')

Monthly Downloads

199

Version

0.1.1

License

GPL (>= 3)

Issues

Pull Requests

Stars

Forks

Maintainer

Mikkel H. Vembye

Last Published

November 26th, 2024

Functions in AIscreenR (0.1.1)

tabscreen_gpt.original

Title and abstract screening with GPT API models using function calls via the original function call arguments
tabscreen_gpt.tools

Title and abstract screening with GPT API models using function calls via the tools argument
print.gpt

Print methods for 'gpt' objects
is_chatgpt

Test if the object is a 'chatgpt' object
filges2015_dat

RIS file data from Functional Family Therapy (FFT) systematic review
is_gpt_agg_tbl

Test if the object is a 'gpt_agg_tbl' object
is_gpt

Test if the object is a 'gpt' object
approximate_price_gpt

Approximate price estimation for title and abstract screening using OpenAI's GPT API models
is_gpt_tbl

Test if the object is a 'gpt_tbl' object
is_chatgpt_tbl

Test if the object is a 'chatgpt_tbl' object
get_api_key

Get API key from R environment variable.
print.gpt_price

Print methods for 'gpt_price' objects
print.chatgpt

Print methods for 'chatgpt' objects
screen_errors

Generic function to re-screen failed title and abstract requests.
screen_errors.chatgpt

Re-screen failed requests.
rate_limits_per_minute

Find updated rate limits for API models
screen_errors.gpt

Re-screen failed requests.
sample_references

Random sample references
screen_analyzer

Analyze performance between the human and AI screening.
AIscreenR-package

AIscreenR: AI Screening Tools in R for Systematic Reviewing
model_prizes

Model prize data (last updated November 5, 2024)
set_api_key

Creating a temporary R environment API key variable