AIr - Artificial Intelligence Risk of bias tool (AIr)

<ns3:p>Background The use of artificial intelligence or machine learning in the development of prediction models is increasing exponentially but the present model is associated with a high degree of heterogeneity and associated bias. The present model is associated with a difficult learning curve and we aimed to develop a tool evaluating risk of bias in cardiology research which was succinct and effective. Methods Our tool (AIr) consists of 10 questions and can be utilised to assess the risk of bias in model development, external validation, and the combination of the two in machine-learned or artificial intelligence models. Results AIr was as effective as the current risk of bias tool, PROBAST, however, was significantly more succinct and had a greater inter-rater reliability than PROBAST. Conclusion We propose that our tool maintains validity regarding the assessment of the risk of bias in cardiology publications whilst increasing reliability when compared with PROBAST.</ns3:p>

Authors

Institutions

Publication Details

Journal
F1000Research
Published
2025-11-03
DOI
https://doi.org/10.12688/f1000research.169545.1
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

AIr - Artificial Intelligence Risk of bias tool (AIr)

Sakshi Roy, Yuzhi Phuah, Arjun Ahluwalia, Mahmood Ahmad et al.
F1000Research
Artificial Intelligence in Healthcare and Education
article

AIr - Artificial Intelligence Risk of bias tool (AIr)

Sakshi Roy, Yuzhi Phuah, Arjun Ahluwalia, Mahmood Ahmad, Niraj S Kumar, Muhammad Hamza Shah, Hannah Glatzel, Lily Snell, Solange Bramer, Kevin Malone, Ranu Baral, Karish Thavabalan, R Ahmad, G Sivakumar, Joanne Lac, Kirshun Suvendiran, Cecilia Maria Morcillo Perez
article en

Abstract

<ns3:p>Background The use of artificial intelligence or machine learning in the development of prediction models is increasing exponentially but the present model is associated with a high degree of heterogeneity and associated bias. The present model is associated with a difficult learning curve and we aimed to develop a tool evaluating risk of bias in cardiology research which was succinct and effective. Methods Our tool (AIr) consists of 10 questions and can be utilised to assess the risk of bias in model development, external validation, and the combination of the two in machine-learned or artificial intelligence models. Results AIr was as effective as the current risk of bias tool, PROBAST, however, was significantly more succinct and had a greater inter-rater reliability than PROBAST. Conclusion We propose that our tool maintains validity regarding the assessment of the risk of bias in cardiology publications whilst increasing reliability when compared with PROBAST.</ns3:p>

F1000ResearchVol. 14
Brighton and Sussex Medical School (GB), Queen's University Belfast (GB), University College London Hospitals NHS Foundation Trust (GB), University of Leicester (GB), Royal Free London NHS Foundation Trust (GB), Baba Raghav Das Medical College (IN), Barnet Hospital (GB), Whipps Cross University Hospital (GB), King's College Hospital NHS Foundation Trust (GB), National Medical Association (US), Great Western Hospitals NHS Foundation Trust (GB), University College London (GB)
Openalex Percentile: Top 75%
Artificial Intelligence in Healthcare and Education
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.