Adewole Adamson, MD, of the University of Texas, Austin, aims to create more equity in health care by collecting data from more diverse populations using artificial intelligence (AI), a type of learning automatique. Dr. Adamson’s work is funded by the American Cancer Society (ACS), an organization committed to advancing health equity through research priorities, programs and services for marginalized groups.
Melanoma became a particular concern for Dr. Adamson after meeting Avery Smith, who lost his wife – a black woman – to the deadly disease.
Avery Smith (left) and Adamson (sidenote)
This personal encounter, coupled with multiple conversations with black dermatology patients, led Dr. Adamson to a disturbing discovery: as advanced as AI is in detecting possible skin cancers, it is heavily biased.
To understand this bias, it helps to first know how AI works in the early detection of skin cancer, which Dr. Adamson explains in his article for the New England Journal of Medicine (pay wall). The process uses computers that draw on accumulated data sets to learn what healthy or unhealthy skin looks like, then create an algorithm to predict diagnoses based on those data sets.
This process, known as supervised learning, could lead to enormous benefits in preventive care.
After all, early detection is essential for best results. The problem is that the datasets don’t include enough information about darker skin tones. As Adamson said, “everything is seen through a ‘white lens’.”
“If you don’t teach the algorithm with a diverse set of images, then that algorithm won’t work in the audience that is diverse,” Adamson writes in a study he co-authored with Smith (according to a story in Atlantic). “There is therefore a risk that people with colored skin will fall through the cracks.”
Tragically, Smith’s wife was diagnosed with melanoma too late and paid the ultimate price. And she wasn’t an anomaly – although the disease is more common in white patients, black cancer patients are much more likely to be diagnosed at later stages, resulting in a noticeable disparity in rates survival between non-Hispanic whites (90%) and non-Hispanic blacks (66%).
As a computer scientist, Smith suspected this racial bias and contacted Adamson, hoping a black dermatologist would have more diverse data sets. Although Adamson didn’t have what Smith was initially looking for, this realization sparked a personal mission to investigate and reduce the disparities.
Now Adamson is using the insights gained from his years of research to help advance the fight for health equity. For him, that means not only getting a wider range of data sets, but also having more conversations with patients to understand how socioeconomic status affects the level and effectiveness of care.
“At the end of the day, what matters most is how we help patients at the patient level,” Adamson told Upworthy. “And how can you do that without knowing exactly what obstacles they face?”
“What matters most is how we help patients at the patient level.”https://www.kellydavidsonstudio.com/
The American Cancer Society believes that everyone deserves a fair and equitable opportunity to prevent, detect, treat and survive cancer, regardless of income, skin color, sexual orientation, gender identity. , their disability status, or where they live. Inclusive tools and resources in the Health Equity section of their website can be found here. For more information on skin cancer, visit cancer.org/skincancer.
From articles on your site
Related articles on the web