While current machine learning models are attempting to achieve the goal that physicians could be alerted when a patient's condition rapidly deteriorates or shows vitals in highly abnormal ranges, a study recently published in Communications Medicine shows that they are falling short with models for in-hospital mortality prediction.
The Virginia Tech team developed multiple medical testing approaches and systematically assessed machine learning models' ability to respond to serious medical conditions.
In addition to models failing to recognize 66 percent of injuries for in-hospital mortality prediction, the models failed to generate, in some instances, adequate mortality risk scores for all test cases. The study identified similar deficiencies in the responsiveness of five-year breast and lung cancer prognosis models.
A more fundamental design is to incorporate medical knowledge deeply into clinical machine learning models which required a interdisciplinary team with both computing and medical expertise.
【MORE】