PROBAST assesses computational models that predict the likelihood of disease or death
19 February 2019
The Julius Center of the University Medical Center (UMC) Utrecht is part of a large international research group that has developed a checklist to assess the quality and effectiveness of computational models that predict the likelihood of illness or death and often form the basis of medical apps or websites.
There are currently more than one hundred thousand medical apps, and it is not clear to users and healthcare professionals which prediction models and apps are reliable. The checklist "PROBAST" was published on January 1st in the medical science journal Annals of Internal Medicine.
Many medical computational models predict the likelihood of illness and death based on various characteristics such as age, gender, symptoms and test results. For example, there is a model that estimates the probability of a pregnant woman suffering complications during her...