Modeling Mistrust in End-of-Life Care

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.

[1]  A. Whaley,et al.  Cultural Mistrust: An Important Psychological Construct for Diagnosis and Treatment of African Americans , 2001 .

[2]  Arlene S Ash,et al.  Racial and ethnic differences in end-of-life costs: why do minorities cost more than whites? , 2009, Archives of internal medicine.

[3]  S. Lemeshow,et al.  A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. , 1993, JAMA.

[4]  J. Ware,et al.  Linking primary care performance to outcomes of care. , 1998, The Journal of family practice.

[5]  F. Hopp,et al.  Racial Variations in End‐of‐Life Care , 2000, Journal of the American Geriatrics Society.

[6]  Astha Singhal,et al.  Racial-Ethnic Disparities in Opioid Prescriptions at Emergency Department Visits for Conditions Commonly Associated with Prescription Drug Abuse , 2016, PloS one.

[7]  Danae Dotolo,et al.  The influence of race/ethnicity and socioeconomic status on end-of-life care in the ICU. , 2011, Chest.

[8]  Gari D. Clifford,et al.  A New Severity of Illness Scale Using a Subset of Acute Physiology and Chronic Health Evaluation Data Elements Shows Comparable Predictive Accuracy* , 2013, Critical care medicine.

[9]  Peter Tanuseputro,et al.  Association Between Immigrant Status and End-of-Life Care in Ontario, Canada , 2017, JAMA.

[10]  Viju Raghupathi,et al.  Big data analytics in healthcare: promise and potential , 2014, Health Information Science and Systems.

[11]  T. Brennan,et al.  Minority Populations and Advance Directives: Insights from a Focus Group Methodology , 1997, Cambridge Quarterly of Healthcare Ethics.

[12]  Derek C. Angus,et al.  Three-year outcomes for Medicare beneficiaries who survive intensive care. , 2010, JAMA.

[13]  Roger G. Mark,et al.  Reproducibility in critical care: a mortality prediction case study , 2017, MLHC.

[14]  William Boag,et al.  Quantifying racial disparities in end-of-life care , 2018 .

[15]  J. Chamberlain,et al.  Racial Disparities in Pain Management of Children With Appendicitis in Emergency Departments. , 2015, JAMA pediatrics.

[16]  Sabrina Cipolletta,et al.  What is a Good Death? Health Care Professionals’ Narrations on End-of-Life Care , 2014, Death studies.

[17]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[18]  Suresh Venkatasubramanian,et al.  Runaway Feedback Loops in Predictive Policing , 2017, FAT.

[19]  Helen P. Hazuda,et al.  Cross-cultural similarities and differences in attitudes about advance care planning , 2007, Journal of General Internal Medicine.

[20]  Kadija Ferryman,et al.  Fairness in precision medicine , 2018 .

[21]  D L Patrick,et al.  Life-sustaining treatments during terminal illness: who wants what? , 1993, Journal of general internal medicine.

[22]  C. Kruse,et al.  Challenges and Opportunities of Big Data in Health Care: A Systematic Review , 2016, JMIR medical informatics.

[23]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[24]  C. Spigner,et al.  Medical Apartheid: The Dark History of Medical Experimentation on Black Americans from Colonial Times to the Present , 2007 .

[25]  Walter Daelemans,et al.  Pattern for Python , 2012, J. Mach. Learn. Res..

[26]  Isaac S. Kohane,et al.  Sentiment Measured in Hospital Discharge Notes Is Associated with Readmission and Mortality Risk: An Electronic Health Record Study , 2015, PloS one.

[27]  J. Curtis,et al.  The Influence of Race/Ethnicity and Education on Family Ratings of the Quality of Dying in the ICU. , 2016, Journal of pain and symptom management.