Norori, Natalia; Hu, Qiyang; Aellen, Florence Marcelle; Faraci, Francesca Dalia; Tzovara, Athina (2021). Addressing bias in big data and AI for health care: A call for open science. Patterns, 2(10), p. 100347. Cell Press 10.1016/j.patter.2021.100347
|
Text
Norori__2021__Addressing_bias_in_big_data.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (916kB) | Preview |
Artificial intelligence (AI) has an astonishing potential in assisting clinical decision making and revolutionizing the field of health care. A major open challenge that AI will need to address before its integration in the clinical routine is that of algorithmic bias. Most AI algorithms need big datasets to learn from, but several groups of the human population have a long history of being absent or misrepresented in existing biomedical datasets. If the training data is misrepresentative of the population variability, AI is prone to reinforcing bias, which can lead to fatal outcomes, misdiagnoses, and lack of generalization. Here, we describe the challenges in rendering AI algorithms fairer, and we propose concrete steps for addressing bias using tools from the field of open science.
Item Type: |
Journal Article (Review Article) |
|---|---|
Division/Institute: |
08 Faculty of Science > Institute of Computer Science (INF) > Cognitive Computational Neuroscience (CCN) 04 Faculty of Medicine > Department of Head Organs and Neurology (DKNS) > Clinic of Neurology 08 Faculty of Science > Institute of Computer Science (INF) |
UniBE Contributor: |
Hu, Qiyang, Aellen, Florence Marcelle, Tzovara, Athina |
Subjects: |
000 Computer science, knowledge & systems 600 Technology > 610 Medicine & health 500 Science > 510 Mathematics |
ISSN: |
2666-3899 |
Publisher: |
Cell Press |
Language: |
English |
Submitter: |
Chantal Kottler |
Date Deposited: |
08 Dec 2021 16:40 |
Last Modified: |
13 Mar 2024 13:19 |
Publisher DOI: |
10.1016/j.patter.2021.100347 |
PubMed ID: |
34693373 |
Additional Information: |
Doppelaffliation Tzovara: INF - Neurology |
Uncontrolled Keywords: |
artificial intelligence bias data standards deep learning health care open science participatory science |
BORIS DOI: |
10.48350/161897 |
URI: |
https://boris.unibe.ch/id/eprint/161897 |
Actions (login required)
 |
Edit item |