Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19
Artificial intelligence (AI) technologies have been applied in various medical domains to predict patient outcomes with high accuracy. As AI becomes more widely adopted, the problem of model bias is increasingly apparent. In this study, we investigate the model bias that can occur when training a mo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-11-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2021.778720/full |
| _version_ | 1818734644790558720 |
|---|---|
| author | Heewon Chung Chul Park Wu Seong Kang Jinseok Lee |
| author_facet | Heewon Chung Chul Park Wu Seong Kang Jinseok Lee |
| author_sort | Heewon Chung |
| collection | DOAJ |
| description | Artificial intelligence (AI) technologies have been applied in various medical domains to predict patient outcomes with high accuracy. As AI becomes more widely adopted, the problem of model bias is increasingly apparent. In this study, we investigate the model bias that can occur when training a model using datasets for only one particular gender and aim to present new insights into the bias issue. For the investigation, we considered an AI model that predicts severity at an early stage based on the medical records of coronavirus disease (COVID-19) patients. For 5,601 confirmed COVID-19 patients, we used 37 medical records, namely, basic patient information, physical index, initial examination findings, clinical findings, comorbidity diseases, and general blood test results at an early stage. To investigate the gender-based AI model bias, we trained and evaluated two separate models—one that was trained using only the male group, and the other using only the female group. When the model trained by the male-group data was applied to the female testing data, the overall accuracy decreased—sensitivity from 0.93 to 0.86, specificity from 0.92 to 0.86, accuracy from 0.92 to 0.86, balanced accuracy from 0.93 to 0.86, and area under the curve (AUC) from 0.97 to 0.94. Similarly, when the model trained by the female-group data was applied to the male testing data, once again, the overall accuracy decreased—sensitivity from 0.97 to 0.90, specificity from 0.96 to 0.91, accuracy from 0.96 to 0.91, balanced accuracy from 0.96 to 0.90, and AUC from 0.97 to 0.95. Furthermore, when we evaluated each gender-dependent model with the test data from the same gender used for training, the resultant accuracy was also lower than that from the unbiased model. |
| first_indexed | 2024-12-18T00:08:39Z |
| format | Article |
| id | doaj.art-5504b15f398e44e289120b0e28e27089 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-12-18T00:08:39Z |
| publishDate | 2021-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-5504b15f398e44e289120b0e28e270892022-12-21T21:27:45ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2021-11-011210.3389/fphys.2021.778720778720Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19Heewon Chung0Chul Park1Wu Seong Kang2Jinseok Lee3Department of Biomedical Engineering, College of Electronics and Information, Kyung Hee University, Yongin-si, South KoreaDepartment of Internal Medicine, Wonkwang University School of Medicine, Iksan, South KoreaDepartment of Trauma Surgery, Cheju Halla General Hospital, Jeju-si, South KoreaDepartment of Biomedical Engineering, College of Electronics and Information, Kyung Hee University, Yongin-si, South KoreaArtificial intelligence (AI) technologies have been applied in various medical domains to predict patient outcomes with high accuracy. As AI becomes more widely adopted, the problem of model bias is increasingly apparent. In this study, we investigate the model bias that can occur when training a model using datasets for only one particular gender and aim to present new insights into the bias issue. For the investigation, we considered an AI model that predicts severity at an early stage based on the medical records of coronavirus disease (COVID-19) patients. For 5,601 confirmed COVID-19 patients, we used 37 medical records, namely, basic patient information, physical index, initial examination findings, clinical findings, comorbidity diseases, and general blood test results at an early stage. To investigate the gender-based AI model bias, we trained and evaluated two separate models—one that was trained using only the male group, and the other using only the female group. When the model trained by the male-group data was applied to the female testing data, the overall accuracy decreased—sensitivity from 0.93 to 0.86, specificity from 0.92 to 0.86, accuracy from 0.92 to 0.86, balanced accuracy from 0.93 to 0.86, and area under the curve (AUC) from 0.97 to 0.94. Similarly, when the model trained by the female-group data was applied to the male testing data, once again, the overall accuracy decreased—sensitivity from 0.97 to 0.90, specificity from 0.96 to 0.91, accuracy from 0.96 to 0.91, balanced accuracy from 0.96 to 0.90, and AUC from 0.97 to 0.95. Furthermore, when we evaluated each gender-dependent model with the test data from the same gender used for training, the resultant accuracy was also lower than that from the unbiased model.https://www.frontiersin.org/articles/10.3389/fphys.2021.778720/fullCOVID-19severity predictionartificial intelligence biasgender dependent biasfeature importance |
| spellingShingle | Heewon Chung Chul Park Wu Seong Kang Jinseok Lee Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19 Frontiers in Physiology COVID-19 severity prediction artificial intelligence bias gender dependent bias feature importance |
| title | Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19 |
| title_full | Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19 |
| title_fullStr | Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19 |
| title_full_unstemmed | Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19 |
| title_short | Gender Bias in Artificial Intelligence: Severity Prediction at an Early Stage of COVID-19 |
| title_sort | gender bias in artificial intelligence severity prediction at an early stage of covid 19 |
| topic | COVID-19 severity prediction artificial intelligence bias gender dependent bias feature importance |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2021.778720/full |
| work_keys_str_mv | AT heewonchung genderbiasinartificialintelligenceseveritypredictionatanearlystageofcovid19 AT chulpark genderbiasinartificialintelligenceseveritypredictionatanearlystageofcovid19 AT wuseongkang genderbiasinartificialintelligenceseveritypredictionatanearlystageofcovid19 AT jinseoklee genderbiasinartificialintelligenceseveritypredictionatanearlystageofcovid19 |