Mitigating bias in AI mortality predictions for minority populations: a transfer learning approach

Abstract Background The COVID-19 pandemic has highlighted the crucial role of artificial intelligence (AI) in predicting mortality and guiding healthcare decisions. However, AI models may perpetuate or exacerbate existing health disparities due to demographic biases, particularly affecting racial an...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianshu Gu, Wensen Pan, Jing Yu, Guang Ji, Xia Meng, Yongjun Wang, Minghui Li
Format: Article
Language:English
Published: BMC 2025-01-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-025-02862-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832594672089825280
author Tianshu Gu
Wensen Pan
Jing Yu
Guang Ji
Xia Meng
Yongjun Wang
Minghui Li
author_facet Tianshu Gu
Wensen Pan
Jing Yu
Guang Ji
Xia Meng
Yongjun Wang
Minghui Li
author_sort Tianshu Gu
collection DOAJ
description Abstract Background The COVID-19 pandemic has highlighted the crucial role of artificial intelligence (AI) in predicting mortality and guiding healthcare decisions. However, AI models may perpetuate or exacerbate existing health disparities due to demographic biases, particularly affecting racial and ethnic minorities. The objective of this study is to investigate the demographic biases in AI models predicting COVID-19 mortality and to assess the effectiveness of transfer learning in improving model fairness across diverse demographic groups. Methods This retrospective cohort study used a population-based dataset of COVID-19 cases from the Centers for Disease Control and Prevention (CDC), spanning the years 2020–2024. The study analyzed AI model performance across different racial and ethnic groups and employed transfer learning techniques to improve model fairness by adapting pre-trained models to the specific demographic and clinical characteristics of the population. Results Decision Tree (DT) and Random Forest (RF) models consistently showed improvements in accuracy, precision, and ROC-AUC scores for Non-Hispanic Black, Hispanic/Latino, and Asian populations. The most significant precision improvement was observed in the DT model for Hispanic/Latino individuals, which increased from 0.3805 to 0.5265. The precision for Asians or Pacific Islanders in the DT model increased from 0.4727 to 0.6071, and for Non-Hispanic Blacks, it rose from 0.5492 to 0.6657. Gradient Boosting Machines (GBM) produced mixed results, showing accuracy and precision improvements for Non-Hispanic Black and Asian groups, but declines for the Hispanic/Latino and American Indian groups, with the most significant decline in precision, which dropped from 0.4612 to 0.2406 in the American Indian group. Logistic Regression (LR) demonstrated minimal changes across all metrics and groups. For the Non-Hispanic American Indian group, most models showed limited benefits, with several performance metrics either remaining stable or declining. Conclusions This study demonstrates the potential of AI in predicting COVID-19 mortality while also underscoring the critical need to address demographic biases. The application of transfer learning significantly improved the predictive performance of models across various racial and ethnic groups, suggesting these techniques are effective in mitigating biases and promoting fairness in AI models.
format Article
id doaj-art-1702f41931014b11ad00c98bd0f46c28
institution Kabale University
issn 1472-6947
language English
publishDate 2025-01-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj-art-1702f41931014b11ad00c98bd0f46c282025-01-19T12:26:08ZengBMCBMC Medical Informatics and Decision Making1472-69472025-01-0125111110.1186/s12911-025-02862-7Mitigating bias in AI mortality predictions for minority populations: a transfer learning approachTianshu Gu0Wensen Pan1Jing Yu2Guang Ji3Xia Meng4Yongjun Wang5Minghui Li6Department of Clinical Pharmacy and Translational Science, The University of Tennessee Health Science CenterDepartment of Respiration and Intensive Care, The Second Hospital of Hebei Medical UniversityDepartment of Respiration and Intensive Care, The Second Hospital of Hebei Medical UniversityDepartment of Neurology, The Second Hospital of Hebei Medical UniversityDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, China National Clinical Research Center for Neurological DiseasesDepartment of Neurology, Beijing Tiantan Hospital, Capital Medical University, China National Clinical Research Center for Neurological DiseasesDepartment of Clinical Pharmacy and Translational Science, The University of Tennessee Health Science CenterAbstract Background The COVID-19 pandemic has highlighted the crucial role of artificial intelligence (AI) in predicting mortality and guiding healthcare decisions. However, AI models may perpetuate or exacerbate existing health disparities due to demographic biases, particularly affecting racial and ethnic minorities. The objective of this study is to investigate the demographic biases in AI models predicting COVID-19 mortality and to assess the effectiveness of transfer learning in improving model fairness across diverse demographic groups. Methods This retrospective cohort study used a population-based dataset of COVID-19 cases from the Centers for Disease Control and Prevention (CDC), spanning the years 2020–2024. The study analyzed AI model performance across different racial and ethnic groups and employed transfer learning techniques to improve model fairness by adapting pre-trained models to the specific demographic and clinical characteristics of the population. Results Decision Tree (DT) and Random Forest (RF) models consistently showed improvements in accuracy, precision, and ROC-AUC scores for Non-Hispanic Black, Hispanic/Latino, and Asian populations. The most significant precision improvement was observed in the DT model for Hispanic/Latino individuals, which increased from 0.3805 to 0.5265. The precision for Asians or Pacific Islanders in the DT model increased from 0.4727 to 0.6071, and for Non-Hispanic Blacks, it rose from 0.5492 to 0.6657. Gradient Boosting Machines (GBM) produced mixed results, showing accuracy and precision improvements for Non-Hispanic Black and Asian groups, but declines for the Hispanic/Latino and American Indian groups, with the most significant decline in precision, which dropped from 0.4612 to 0.2406 in the American Indian group. Logistic Regression (LR) demonstrated minimal changes across all metrics and groups. For the Non-Hispanic American Indian group, most models showed limited benefits, with several performance metrics either remaining stable or declining. Conclusions This study demonstrates the potential of AI in predicting COVID-19 mortality while also underscoring the critical need to address demographic biases. The application of transfer learning significantly improved the predictive performance of models across various racial and ethnic groups, suggesting these techniques are effective in mitigating biases and promoting fairness in AI models.https://doi.org/10.1186/s12911-025-02862-7COVID-19Artificial intelligenceMortality predictionDemographic biasHealth disparitiesTransfer learning
spellingShingle Tianshu Gu
Wensen Pan
Jing Yu
Guang Ji
Xia Meng
Yongjun Wang
Minghui Li
Mitigating bias in AI mortality predictions for minority populations: a transfer learning approach
BMC Medical Informatics and Decision Making
COVID-19
Artificial intelligence
Mortality prediction
Demographic bias
Health disparities
Transfer learning
title Mitigating bias in AI mortality predictions for minority populations: a transfer learning approach
title_full Mitigating bias in AI mortality predictions for minority populations: a transfer learning approach
title_fullStr Mitigating bias in AI mortality predictions for minority populations: a transfer learning approach
title_full_unstemmed Mitigating bias in AI mortality predictions for minority populations: a transfer learning approach
title_short Mitigating bias in AI mortality predictions for minority populations: a transfer learning approach
title_sort mitigating bias in ai mortality predictions for minority populations a transfer learning approach
topic COVID-19
Artificial intelligence
Mortality prediction
Demographic bias
Health disparities
Transfer learning
url https://doi.org/10.1186/s12911-025-02862-7
work_keys_str_mv AT tianshugu mitigatingbiasinaimortalitypredictionsforminoritypopulationsatransferlearningapproach
AT wensenpan mitigatingbiasinaimortalitypredictionsforminoritypopulationsatransferlearningapproach
AT jingyu mitigatingbiasinaimortalitypredictionsforminoritypopulationsatransferlearningapproach
AT guangji mitigatingbiasinaimortalitypredictionsforminoritypopulationsatransferlearningapproach
AT xiameng mitigatingbiasinaimortalitypredictionsforminoritypopulationsatransferlearningapproach
AT yongjunwang mitigatingbiasinaimortalitypredictionsforminoritypopulationsatransferlearningapproach
AT minghuili mitigatingbiasinaimortalitypredictionsforminoritypopulationsatransferlearningapproach