Health systems rely on commercial prediction algorithms to identify and help patients with complex health needs. We show that a widely used algorithm, typical of this industry-wide approach and affecting millions of patients, exhibits significant racial bias: At a given risk score, Black patients are considerably sicker than White patients, as evidenced by signs of uncontrolled illnesses. Remedying this disparity would increase the percentage of Black patients receiving additional help from 17.7 to 46.5%. The bias arises because the algorithm predicts health care costs rather than illness, but unequal access to care means that we spend less money caring for Black patients than for White patients. Thus, despite health care cost appearing to be an effective proxy for health by some measures of predictive accuracy, large racial biases arise. We suggest that the choice of convenient, seemingly effective proxies for ground truth can be an important source of algorithmic bias in many contexts.

Persons with multiple chronic conditions are a large and growing segment of the US population. However, little is known about how chronic conditions cluster, and the ramifications of having specific combinations of chronic conditions. Clinical guidelines and disease management programs focus on single conditions, and clinical research often excludes persons with multiple chronic conditions. Understanding how conditions in combination impact the burden of disease and the costs and quality of care received is critical to improving care for the 1 in 5 Americans with multiple chronic conditions. This Medline review of publications examining somatic chronic conditions co-occurring with 1 or more additional specific chronic illness between January 2000 and March 2007 summarizes the state of our understanding of the prevalence and health challenges of multiple chronic conditions and the implications for quality, care management, and costs.KEY WORDS: chronic disease; comorbidity; prevalence; quality of health care.