Dataset for systematic review on risk of bias of studies on prediction models developed using supervised machine learning techniques

This record includes the dataset collected for the systematic review titled “Risk of bias in studies on prediction models developed using supervised machine learning techniques: systematic review” published in 2021 (doi.org/10.1136/bmj.n2281), and therefore, the dataset is made available after publication of results. The aim of the study was to assess the methodological quality of studies on prediction models developed using machine learning techniques across all medical specialties using PROBAST.

The articles included in this dataset were obtained through a search on PubMed from 1 January 2018 to 31 December 2019 and are a random sample of articles reporting on the development, with or without external validation, of a multivariable prediction model (diagnostic or prognostic) developed using supervised machine learning for individualised predictions. The dataset provides the reviewers judgements on the risk of bias of the articles following the signaling questions of the PROBAST tool.