Researchers are constantly trying to improve the healthcare system and much like other fields of innovation, they have begun relying on artificial intelligence. Scientists are subjecting algorithms to a form of machine med school: software learns from doctors by receiving millions of x-rays and data already labeled by doctors and experts. In this process, machines learn to accurately flag problems, including early signs of lungs showing potential COVID-19 infection.

This new system of machine learning programs that are trained for analyzing reports rather than doctor’s input more often than not find problems that doctors have been missing for a while. That means these algorithms are finding ways to reduce racial disparities in healthcare systems. A new study that was published last month has found that radiologists have blind spots when it comes to reading the x-rays of Black patients: “Underserved populations experience higher levels of pain. These disparities persist even after controlling for the objective severity of diseases like osteoarthritis, as graded by human physicians using medical images, raising the possibility that underserved patients’ pain stems from factors external to the knee, such as stress. this approach dramatically reduces unexplained racial disparities in pain.”

It is no surprise that algorithms that are trained on patients’ reports rather than doctors are doing a better job at taking in factors of race, and are better at accounting for the pain experienced by people of color. These algorithms are discovering patterns of diseases that human doctors usually overlook. This is really huge news for people of color at large. We are finally at a point in time where we may be able to use AI for the benefit of underserved communities, and it’s only looking up from here.