Addressing Medicine's Dark Matter

Abstract

In the 20th century, the models used to predict the motion of heavenly bodies did not match observation. Investigating this incongruity led to the discovery of dark matter-the most abundant substance in the universe. In medicine, despite years of using a data-hungry approach, our models have been limited in their ability to predict population health outcomes-that is, our observations also do not meet our expectations. We believe this phenomenon represents medicine's "dark matter"- the features with have a tremendous effect on clinical outcomes that we cannot directly observe yet. Advancing the information science of health care systems will thus require unique solutions and a humble approach that acknowledges its limitations. Dark matter changed the way the scientific community understood the universe; what might medicine learn from what it cannot yet see?

Keywords: AI; artificial intelligence; big data; data collection; equity; health care; model; predict; prediction; representative; unrepresented.