PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods
Moons, Karel G M Damen, Johanna A A Kaul, Tabea Hooft, Lotty Andaur Navarro, Constanza Dhiman, Paula Beam, Andrew L Van Calster, Ben Celi, Leo Anthony Denaxas, Spiros
Moons, Karel G M
Damen, Johanna A A
Kaul, Tabea
Hooft, Lotty
Andaur Navarro, Constanza
Dhiman, Paula
Beam, Andrew L
Van Calster, Ben
Celi, Leo Anthony
Denaxas, Spiros
Affiliation
University Medical Centre Utrecht; University of Oxford; Harvard T H Chan School of Public Health; KU Leuven; Leuven Unit for Health Technology Assessment Research; Massachusetts Institute of Technology; University College London; Health Data Research Centre UK; University of Birmingham; Medical University of Vienna; University of Cape Town; German Cancer Research Centre; National Centre for Tumour Diseases (NCT) Heidelberg; University Hospitals Birmingham NHS Foundation Trust; NIHR Birmingham Biomedical Research Centre; The Hospital for Sick Children; Duke-NUS Medical School; University of Adelaide; University of Michigan Medical School; Maastricht University
Other Contributors
Publication date
2025-03-24
Collections
Research Projects
Organizational Units
Journal Issue
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.
Citation
Moons KGM, Damen JAA, Kaul T, Hooft L, Andaur Navarro C, Dhiman P, Beam AL, Van Calster B, Celi LA, Denaxas S, Denniston AK, Ghassemi M, Heinze G, Kengne AP, Maier-Hein L, Liu X, Logullo P, McCradden MD, Liu N, Oakden-Rayner L, Singh K, Ting DS, Wynants L, Yang B, Reitsma JB, Riley RD, Collins GS, van Smeden M. PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods. BMJ. 2025 Mar 24;388:e082505. doi: 10.1136/bmj-2024-082505.
Type
Article