UMD-led Study: Unconscious Bias Contributes to Disproportionate Amputations for Minority Populations

Medical statistics show that rural adults and members of certain racial and ethnic groups with vascular disease get major leg amputations more frequently than other people, but the raw numbers don’t explain why.

A new University of Maryland study published Wednesday in Epidemiology used artificial intelligence (AI) to spot the subtle patterns needed to solve the mystery, finding biased decision-making that can result in lifelong consequences. The study was supported by funding from the National Institutes of Health.

“We found that, after accounting for everything else, people’s unconscious biases are likely behind why some groups receive amputation instead of alternative treatment that preserves their limb,” said Paula Strassle, lead author and assistant professor of epidemiology at UMD’s School of Public Health.

More than 12 million U.S. adults live with peripheral artery disease (PAD), a chronic circulation condition that restricts blood flow to the limbs. It results in leg pain, numbness and in severe cases, limb loss. About 10% of people with PAD develop chronic limb-threatening ischemia (CLTI), which requires either a surgical procedure to restore blood flow to their lower leg or amputation. One procedure, revascularization, can save the limb, but also requires intensive follow-up and is relatively expensive. Vascular surgeons are also in short supply.

After accounting for known differences in clinical presentation as well as for differences in hospital and neighborhood resources, higher-than-expected amputation rates persisted among Black, Hispanic and Native American patients in rural areas, and Black and Native American patients in urban areas. Taking into account hospital and neighborhood resources, however, fully explained initially higher-than-expected rates of amputation observed in white rural patients.

The study examined over 1.5 million hospitalizations of people over 40 with PAD or CLTI in Florida, Georgia, Maryland, Mississippi and New York between 2017 and 2019 using State Inpatient Databases from the Healthcare Cost and Utilization Project.

Researchers programmed an AI model to consider more than 70 variables that contribute to reasons for differences in deciding to amputate limbs of people with PAD. Those included clinical factors such as age and other health conditions, health care system capacity to perform revascularization and limb amputations, legal and regulatory climates, and environmental factors such as a person’s distance from the nearest emergency room and ZIP code median income.

“This AI model will allow us to easily assess intersectionality across race, sex, income and rurality, and offers us the ability to indirectly study hard-to-measure causes of disparities, like implicit bias and stereotyping,” said Strassle.

Limb-threatening conditions are often the result of decades of difficult-to-control diseases like diabetes, high cholesterol and nicotine dependence. For surgeons, who know these conditions lead to worse surgical outcomes, this can make the decision to pursue a complex limb-saving surgery even trickier.

“As vascular surgeons we have surgical guidelines, but we don’t have detailed guidelines to help us make the decision between amputating someone’s leg and limb-saving surgery in patients who are not medically ready,” said Katharine McGinigle, a vascular surgeon, associate professor of surgery at the University of North Carolina and senior author of the paper.

A bewildering array of medical, surgical and social factors contribute to disease progression, limb loss and even death, meaning medical professionals must sometimes rely on instincts that can be subject to implicit bias.

“Surgeons and others making treatment recommendations deserve evidence-based guidance that will help us avoid unconscious biases and make the right decision at the right time for each person based on their unique clinical and social needs. AI methods, similar to the one used in this research, can help us achieve that goal,” said McGinigle.