Check It Before You Wreck It: A Guide to STAR-ML for Screening Machine Learning Reporting in Research DOI Creative Commons
Ryan G. L. Koh, Md Asif Khan, Sajjad Rashidiani

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 101567 - 101579

Published: Jan. 1, 2023

Machine learning (ML) is a technique that learns to detect patterns and trends in data. However, the quality of reporting ML research often suboptimal, leading inaccurate conclusions hindering progress field, especially if disseminated literature reviews provide researchers with an overview current knowledge gaps, future directions. While various tools are available assess risk-of-bias studies, there currently no generalized tool for assessing literature. To address this, this study presents new screening called STAR-ML (Screening Tool Assessing Reporting Learning), accompanied by guide using it. A pilot scoping review looking at chronic pain was used investigate tool. The time it took screen papers how selection threshold affected included were explored. provides reliable systematic way evaluate studies make informed decisions about inclusion or reviews. In addition, recommendations authors on choose use proficiently. Lastly, can serve as checklist seeking develop implement techniques effectively.

Language: Английский

Check It Before You Wreck It: A Guide to STAR-ML for Screening Machine Learning Reporting in Research DOI Creative Commons
Ryan G. L. Koh, Md Asif Khan, Sajjad Rashidiani

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 101567 - 101579

Published: Jan. 1, 2023

Machine learning (ML) is a technique that learns to detect patterns and trends in data. However, the quality of reporting ML research often suboptimal, leading inaccurate conclusions hindering progress field, especially if disseminated literature reviews provide researchers with an overview current knowledge gaps, future directions. While various tools are available assess risk-of-bias studies, there currently no generalized tool for assessing literature. To address this, this study presents new screening called STAR-ML (Screening Tool Assessing Reporting Learning), accompanied by guide using it. A pilot scoping review looking at chronic pain was used investigate tool. The time it took screen papers how selection threshold affected included were explored. provides reliable systematic way evaluate studies make informed decisions about inclusion or reviews. In addition, recommendations authors on choose use proficiently. Lastly, can serve as checklist seeking develop implement techniques effectively.

Language: Английский

Citations

1