Mitigating the risk of artificial intelligence bias in cardiovascular care.
| Autor: | Mihan A; Department of Medicine, Faculty of Health Sciences, McMaster University, Hamilton, ON, Canada., Pandey A; Cardiology Division, University of Texas Southwestern Medical Center, Dallas, TX, USA., Van Spall HG; Department of Medicine, Faculty of Health Sciences, McMaster University, Hamilton, ON, Canada; Baim Institute for Clinical Research, Boston, MA, USA. Electronic address: harriette.vanspall@phri.ca. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | The Lancet. Digital health [Lancet Digit Health] 2024 Oct; Vol. 6 (10), pp. e749-e754. Date of Electronic Publication: 2024 Aug 29. |
| DOI: | 10.1016/S2589-7500(24)00155-9 |
| Abstrakt: | Digital health technologies can generate data that can be used to train artificial intelligence (AI) algorithms, which have been particularly transformative in cardiovascular health-care delivery. However, digital and health-care data repositories that are used to train AI algorithms can introduce bias when data are homogeneous and health-care processes are inequitable. AI bias can also be introduced during algorithm development, testing, implementation, and post-implementation processes. The consequences of AI algorithmic bias can be considerable, including missed diagnoses, misclassification of disease, incorrect risk prediction, and inappropriate treatment recommendations. This bias can disproportionately affect marginalised demographic groups. In this Series paper, we provide a brief overview of AI applications in cardiovascular health care, discuss stages of algorithm development and associated sources of bias, and provide examples of harm from biased algorithms. We propose strategies that can be applied during the training, testing, and implementation of AI algorithms to mitigate bias so that all those at risk for or living with cardiovascular disease might benefit equally from AI. Competing Interests: Declaration of interests AP has received research support from the National Institutes of Health; received grant funding from Applied Therapeutics and Gilead Sciences; received consulting fees for Tricog, Novo Nordisk, Bayer, Medtronic, Edward Lifesciences, Cytokinetics, Roche, Sarfez Pharma, Science37, Rivus, Axon Therapies, Alleviant, and Lilly; received non-financial support from Pfizer and Merck; participated on data and safety monitoring boards for Bayer, Cytokinetics, Novo Nordisk, and Medtronic; and is a consultant for Palomarin with stocks compensation. HCGV and AM declare no competing interests. (Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC 4.0 license. Published by Elsevier Ltd.. All rights reserved.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|