Measuring and Reducing Racial Bias in a Pediatric Urinary Tract Infection Model
Anderson, J. W.; Shaikh, N.; Visweswaran, S.
Show abstract
Clinical predictive models that include race as a predictor have the potential to exacerbate disparities in healthcare. Such models can be respecified to exclude race or optimized to reduce racial bias. We investigated the impact of such respecifications in a predictive model - UTICalc - which was designed to reduce catheterizations in young children with suspected urinary tract infections. To reduce racial bias, race was removed from the UTICalc logistic regression model and replaced with two new features. We compared the two versions of UTICalc using fairness and predictive performance metrics to understand the effects on racial bias. In addition, we derived three new models for UTICalc to specifically improve racial fairness. Our results show that, as predicted by previously described impossibility results, fairness cannot be simultaneously improved on all fairness metrics, and model respecification may improve racial fairness but decrease overall predictive performance.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality 95%
- Raising awareness of potential biases in medical machine learning: Experience from a Datathon 93%
- From theoretical models to practical deployment: A perspective and case study of opportunities and challenges in AI-driven healthcare research for low-income settings 93%
Similar papers in this journal
- Modeling physician variability to prioritize relevant medical record information 96%
- Algorithmic Individual Fairness and Healthcare: A Scoping Review 94%
- Characterizing subgroup performance of probabilistic phenotype algorithms within older adults: A case study for dementia, mild cognitive impairment, and Alzheimer’s and Parkinson’s diseases 94%
Similar papers in this journal
- Development and Validation of ‘Patient Optimizer’ (POP) Algorithms for Predicting Surgical Risk with Machine Learning 95%
- Prediction of Sepsis Mortality in ICU Patients Using Machine Learning Methods 94%
- Combining symbolic regression with the Cox proportional hazards model improves prediction of heart failure deaths 94%
Similar papers in this journal
- Identification of high-risk COVID-19 patients using machine learning 94%
- Time-to-event estimation of birth year prevalence trends: a method to enable investigating the etiology of childhood disorders including autism 94%
- A Machine Learning-Based Prediction of Hospital Mortality in Mechanically Ventilated ICU Patients 94%
Similar papers in this journal
- Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models 93%
- A framework for making predictive models useful in practice 93%
- Learning from local to global - an efficient distributed algorithm for modeling time-to-event data 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.