Modeling Mistrust in End-of-Life Care
This work addresses fairness in healthcare by providing a novel metric to quantify mistrust, which could help identify and mitigate disparities in end-of-life care for patients.
The researchers tackled the problem of measuring trust in doctor-patient relationships by developing a machine learning-derived trust score, finding it reveals stronger racial disparities in end-of-life care than race-based stratification and correlates with worse patient outcomes and experiences.
In this work, we characterize the doctor-patient relationship using a machine learning-derived trust score. We show that this score has statistically significant racial associations, and that by modeling trust directly we find stronger disparities in care than by stratifying on race. We further demonstrate that mistrust is indicative of worse outcomes, but is only weakly associated with physiologically-created severity scores. Finally, we describe sentiment analysis experiments indicating patients with higher levels of mistrust have worse experiences and interactions with their caregivers. This work is a step towards measuring fairer machine learning in the healthcare domain.