Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12188/30789
Title: | Investigating Presence of Ethnoracial Bias in Clinical Data using Machine Learning | Authors: | Velichkovska, Bojana Gjoreski, Hristijan Denkovski, Daniel Kalendar, Marija Celi, Leo Anthony Osmani, Venet |
Keywords: | Ethnoracial Bias Clinical Data Vital Signs Machine Learning |
Issue Date: | Sep-2021 | Project: | WideHealth project - Horizon 2020, under grant agreement No 95227 | Conference: | 15th International Online Conference ETAI 2021 | Abstract: | An important target for machine learning research is obtaining unbiased results, which require addressing bias that might be present in the data as well as the methodology. This is of utmost importance in medical applications of machine learning, where trained models should be unbiased so as to result in systems that are widely applicable, reliable and fair. Since bias can sometimes be introduced through the data itself, in this paper we investigate the presence of ethnoracial bias in patients’ clinical data. We focus primarily on vital signs and demographic information and classify patient ethnoraces in subsets of two from the three ethnoracial groups (African Americans, Caucasians, and Hispanics). Our results show that ethnorace can be identified in two out of three patients, setting the initial base for further investigation of the complex issue of ehtnoracial bias. | URI: | http://hdl.handle.net/20.500.12188/30789 |
Appears in Collections: | Faculty of Electrical Engineering and Information Technologies: Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
03_Investigating Presence of Ethnoracial Bias in Clinical Data using Machine Learning (ETAI 2021) final.pdf | An important target for machine learning research is obtaining unbiased results, which require addressing bias that might be present in the data as well as the methodology. This is of utmost importance in medical applications of machine learning, where trained models should be unbiased so as to result in systems that are widely applicable, reliable and fair. Since bias can sometimes be introduced through the data itself, in this paper we investigate the presence of ethnoracial bias in patients’ clinical data. We focus primarily on vital signs and demographic information and classify patient ethnoraces in subsets of two from the three ethnoracial groups (African Americans, Caucasians, and Hispanics). Our results show that ethnorace can be identified in two out of three patients, setting the initial base for further investigation of the complex issue of ehtnoracial bias. | 476.86 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.