Package: AIscreenR 0.4.0

AIscreenR: AI Screening Tools in R for Systematic Reviewing

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' <https://developers.openai.com/>. 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 (2025) <doi:10.1037/met0000769>.

Authors:Mikkel H. Vembye [aut, cre], Thomas Olsen [aut]

AIscreenR_0.4.0.tar.gz
AIscreenR_0.4.0.zip(r-4.7)AIscreenR_0.4.0.zip(r-4.6)AIscreenR_0.4.0.zip(r-4.5)
AIscreenR_0.4.0.tgz(r-4.6-any)AIscreenR_0.4.0.tgz(r-4.5-any)
AIscreenR_0.4.0.tar.gz(r-4.7-any)AIscreenR_0.4.0.tar.gz(r-4.6-any)
AIscreenR_0.4.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
AIscreenR/json (API)
NEWS

# Install 'AIscreenR' in R:
install.packages('AIscreenR', repos = c('https://mikkelvembye.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/mikkelvembye/aiscreenr/issues

Pkgdown/docs site:https://mikkelvembye.github.io

Datasets:
  • claude_model_prizes - Claude model prices (last updated May 13, 2026) Data set containing input and output prizes for all Claude's API models.
  • disagreements - Disagreement sample data
  • filges2015_dat - RIS file data from Functional Family Therapy (FFT) systematic review
  • gemini_model_prizes - Gemini model prices (last updated May 7, 2026) Data set containing input and output prizes for all Gemini's API models.
  • groq_model_prizes - Groq model prices
  • mistral_model_prizes - Mistral model prices (last updated May 7, 2026) Data set containing input and output prizes for all Mistral's API models.
  • model_prizes - Model prize data

On CRAN:

Conda:

gptopenaiscreeningsystematic-reviewquarto

6.65 score 17 stars 33 scripts 625 downloads 31 exports 38 dependencies

Last updated from:09e124d18b. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK181
source / vignettesOK221
linux-release-x86_64OK181
macos-release-arm64OK136
macos-oldrel-arm64OK174
windows-develOK120
windows-releaseOK164
windows-oldrelOK261
wasm-releaseOK123

Exports:approximate_price_gptcreate_fine_tune_dataget_api_keyget_api_key_anthropicget_api_key_geminiget_api_key_groqget_api_key_mistralis_chatgptis_chatgpt_tblis_gptis_gpt_agg_tblis_gpt_tblrate_limits_per_minuteread_ris_to_dataframereportsample_referencessave_dataframe_to_rissave_fine_tune_datascreen_analyzerscreen_errorsscreen_errors.chatgptscreen_errors.gptset_api_keytabscreen_claudetabscreen_geminitabscreen_gpttabscreen_gpt.originaltabscreen_gpt.toolstabscreen_groqtabscreen_mistraltabscreen_ollama

Dependencies:askpassbase64encclicodetoolscpp11curldigestdplyrfastmapfurrrfuturegenericsglobalsgluehtmltoolshttr2jsonlitelifecyclelistenvmagrittropensslparallellypillarpkgconfigpurrrR6rappdirsrlangstringistringrsystibbletictoctidyrtidyselectutf8vctrswithr

Using GPT API Models For Screening

Rendered fromUsing-GPT-API-Models-For-Screening.qmdusingquarto::htmlon Jun 02 2026.

Last update: 2026-06-02
Started: 2026-04-10

Readme and manuals

Help Manual

Help pageTopics
Approximate price estimation for title and abstract screening using OpenAI's GPT API modelsapproximate_price_gpt
Claude model prices (last updated May 13, 2026) Data set containing input and output prizes for all Claude's API models.claude_model_prizes
Function to generate dataset to be used for fine-tuning modelscreate_fine_tune_data
Disagreement sample datadisagreements
RIS file data from Functional Family Therapy (FFT) systematic reviewfilges2015_dat
Gemini model prices (last updated May 7, 2026) Data set containing input and output prizes for all Gemini's API models.gemini_model_prizes
Get API key from R environment variable.get_api_key
Get Anthropic API key from R environment variable.get_api_key_anthropic
Get Gemini API key from R environment variable.get_api_key_gemini
Get GROQ API key from R environment variable.get_api_key_groq
Get Mistral API key from R environment variable.get_api_key_mistral
Groq model prices (last updated March 18, 2026)groq_model_prizes
Test if the object is a ''chatgpt'' objectis_chatgpt
Test if the object is a ''chatgpt_tbl'' objectis_chatgpt_tbl
Test if the object is a ''gpt'' objectis_gpt
Test if the object is a ''gpt_agg_tbl'' objectis_gpt_agg_tbl
Test if the object is a ''gpt_tbl'' objectis_gpt_tbl
Mistral model prices (last updated May 7, 2026) Data set containing input and output prizes for all Mistral's API models.mistral_model_prizes
Model prize data (last updated March 18, 2026)model_prizes
Print methods for ''chatgpt'' objectsprint.chatgpt
Print methods for ''gpt'' objectsprint.gpt
Print methods for ''gpt_price'' objectsprint.gpt_price
Print method for 'groq' objectsprint.groq
Find updated rate limits for API modelsrate_limits_per_minute
Read an RIS file into a data frameread_ris_to_dataframe
Generate a report for screening disagreements between human and AI decisionsreport
Random sample referencessample_references
Write a data frame to a RIS filesave_dataframe_to_ris
Function to write/save fine tune dataset in required jsonl formatsave_fine_tune_data
Analyze performance between the human and AI screening.screen_analyzer
Generic function to re-screen failed title and abstract requests.screen_errors
Re-screen failed requests.screen_errors.chatgpt
Re-screen failed requests.screen_errors.gpt
Creating a temporary R environment API key variableset_api_key
Title and abstract screening with Anthropic's API modelstabscreen_claude
Title and abstract screening with Gemini API models using function callstabscreen_gemini
Title and abstract screening with GPT API models using function calls via the original function call argumentstabscreen_gpt.original
Title and abstract screening with GPT API models using function calls via the tools argumenttabscreen_gpt.tools
Title and abstract screening with GPT API models using function calls via the tools argument and the responses endpointtabscreen_gpt tabscreen_gpt.tools_responses
Title and abstract screening with GROQ API models using function calls via the tools argumenttabscreen_groq
Title and abstract screening with mistral's API modelstabscreen_mistral
Title and abstract screening with OLLAMA API models using function calls via the tools argumenttabscreen_ollama