Journal article icon

Journal article

PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods

Abstract:
The Prediction model Risk Of Bias ASsessment Tool (PROBAST) is used to assess the quality, risk of bias, and applicability of prediction models or algorithms and of prediction model/algorithm studies. Since PROBAST’s introduction in 2019, much progress has been made in the methodology for prediction modelling and in the use of artificial intelligence, including machine learning, techniques. An update to PROBAST-2019 is thus needed. This article describes the development of PROBAST+AI. PROBAST+AI consists of two distinctive parts: model development and model evaluation. For model development, PROBAST+AI users assess quality and applicability using 16 targeted signalling questions. For model evaluation, PROBAST+AI users assess the risk of bias and applicability using 18 targeted signalling questions. Both parts contain four domains: participants and data sources, predictors, outcome, and analysis. Applicability of the prediction model is rated for the participants and data sources, predictors, and outcome domains. PROBAST+AI may replace the original PROBAST tool and allows all key stakeholders (eg, model developers, AI companies, researchers, editors, reviewers, healthcare professionals, guideline developers, and policy organisations) to examine the quality, risk of bias, and applicability of any type of prediction model in the healthcare sector, irrespective of whether regression modelling or AI techniques are used.
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1136/bmj-2024-082505

Authors

More by this author
Role:
Author
ORCID:
0000-0003-2118-004X
More by this author
Role:
Author
ORCID:
0000-0001-7401-4593
More by this author
Role:
Author
ORCID:
0000-0002-4402-5379
More by this author
Role:
Author
ORCID:
0000-0002-7950-2980
More by this author
Role:
Author
ORCID:
0000-0002-7745-2887


More from this funder
Funder identifier:
https://ror.org/054225q67
Grant:
27294
More from this funder
Funder identifier:
https://ror.org/03x94j517
Grant:
MR/V038168/1
More from this funder
Funder identifier:
https://ror.org/0439y7842
Grant:
EP/Y018516/1
More from this funder
Funder identifier:
https://ror.org/02wnqcb97


Publisher:
BMJ Publishing Group
Journal:
British Medical Journal More from this journal
Volume:
388
Article number:
e082505
Place of publication:
England
Publication date:
2025-03-24
Acceptance date:
2025-01-16
DOI:
EISSN:
0959-8138
ISSN:
1759-2151
Pmid:
40127903


Language:
English
Pubs id:
2100914
Local pid:
pubs:2100914
Deposit date:
2025-05-02
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP