Table 1

Summary of reporting guidelines for common study types used in radiological research, and their corresponding guideline extensions where these involve artificial intelligence

Study designReporting guidelineLatest versionAI-related extensionDate of AI-extension published
Clinical Trial ProtocolSPIRIT2013SPIRIT-AISeptember 2020
Diagnostic Accuracy StudiesSTARD2015STARD-AIExpected 2021
CLAIMMarch 2020
MINIMARJune 2020
Prediction models for diagnostic or prognostication purposesTRIPOD2015TRIPOD –AI/MLExpected 2021
PROBAST2019PROBAST-MLExpected 2021
Randomised Controlled Trials (Interventional Study Design)CONSORT2010CONSORT-AISeptember 2020
Systematic reviews and meta-analysesPRISMA
None planned or announced
Critical appraisal and data extraction of publications relating to prediction modelsCHARMS2014Applicable to machine learning
Evaluation of human factors in early algorithm deploymentNot applicableDECIDE-AIExpected 2021/2022
  • AI, artificial intelligence; CHARMS, Checklist for critical appraisal and data extraction for systematic reviews of prediction modelling studies; CLAIM, Checklist for Artificial Intelligence in Medical Imaging; CONSORT, Consolidated Standards of Reporting Trials; DECIDE-AI, Developmental and Exploratory Clinical Investigation of Decision-support systems driven by Artificial Intelligence; DTA, Diagnostic Trials of Accuracy; MINIMAR, Minimum Information for Medical AI Reporting; ML, machine learning; PRISMA, Preferred Reporting Items for Systematic Review and Meta-analysis; PROBAST, Prediction model Risk Of Bias Assessment Tool; SPIRIT, Standard Protocol Items: Recommendations for Interventional Trials; STARD, Standards for Reporting of Diagnostic Accuracy Studies; TRIPOD, Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis.