FairEHR-CLP: Towards Fairness-Aware Clinical Predictions with Contrastive Learning in Multimodal Electronic Health Records
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911976106491904 |
|---|---|
| author | Wang, Yuqing Pillai, Malvika Zhao, Yun Curtin, Catherine Hernandez-Boussard, Tina |
| author_facet | Wang, Yuqing Pillai, Malvika Zhao, Yun Curtin, Catherine Hernandez-Boussard, Tina |
| contents | In the high-stakes realm of healthcare, ensuring fairness in predictive models is crucial. Electronic Health Records (EHRs) have become integral to medical decision-making, yet existing methods for enhancing model fairness restrict themselves to unimodal data and fail to address the multifaceted social biases intertwined with demographic factors in EHRs. To mitigate these biases, we present FairEHR-CLP: a general framework for Fairness-aware Clinical Predictions with Contrastive Learning in EHRs. FairEHR-CLP operates through a two-stage process, utilizing patient demographics, longitudinal data, and clinical notes. First, synthetic counterparts are generated for each patient, allowing for diverse demographic identities while preserving essential health information. Second, fairness-aware predictions employ contrastive learning to align patient representations across sensitive attributes, jointly optimized with an MLP classifier with a softmax layer for clinical classification tasks. Acknowledging the unique challenges in EHRs, such as varying group sizes and class imbalance, we introduce a novel fairness metric to effectively measure error rate disparities across subgroups. Extensive experiments on three diverse EHR datasets on three tasks demonstrate the effectiveness of FairEHR-CLP in terms of fairness and utility compared with competitive baselines. FairEHR-CLP represents an advancement towards ensuring both accuracy and equity in predictive healthcare models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_00955 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FairEHR-CLP: Towards Fairness-Aware Clinical Predictions with Contrastive Learning in Multimodal Electronic Health Records Wang, Yuqing Pillai, Malvika Zhao, Yun Curtin, Catherine Hernandez-Boussard, Tina Machine Learning Computers and Society In the high-stakes realm of healthcare, ensuring fairness in predictive models is crucial. Electronic Health Records (EHRs) have become integral to medical decision-making, yet existing methods for enhancing model fairness restrict themselves to unimodal data and fail to address the multifaceted social biases intertwined with demographic factors in EHRs. To mitigate these biases, we present FairEHR-CLP: a general framework for Fairness-aware Clinical Predictions with Contrastive Learning in EHRs. FairEHR-CLP operates through a two-stage process, utilizing patient demographics, longitudinal data, and clinical notes. First, synthetic counterparts are generated for each patient, allowing for diverse demographic identities while preserving essential health information. Second, fairness-aware predictions employ contrastive learning to align patient representations across sensitive attributes, jointly optimized with an MLP classifier with a softmax layer for clinical classification tasks. Acknowledging the unique challenges in EHRs, such as varying group sizes and class imbalance, we introduce a novel fairness metric to effectively measure error rate disparities across subgroups. Extensive experiments on three diverse EHR datasets on three tasks demonstrate the effectiveness of FairEHR-CLP in terms of fairness and utility compared with competitive baselines. FairEHR-CLP represents an advancement towards ensuring both accuracy and equity in predictive healthcare models. |
| title | FairEHR-CLP: Towards Fairness-Aware Clinical Predictions with Contrastive Learning in Multimodal Electronic Health Records |
| topic | Machine Learning Computers and Society |
| url | https://arxiv.org/abs/2402.00955 |