Artificial intelligence helps cut down on MRI no-shows

Artificial intelligence predictive analytics performs fairly well in solving complex operational problems -- outpatient MRI appointment no-shows, especially -- using a modest amount of data and basic feature engineering, and can help cut down on such no-shows, according to findings published in the American Journal of Roentgenology. What's convenient and beneficial about the data is that in many cases it's readily retrievable from frontline IT systems that are commonly used in hospital radiology departments. It can also be readily incorporated into routine workflows, which the authors said can improve the quality and efficiency of healthcare delivery. Learn on-demand, earn credit, find products and solutions. To train and validate this model, the team of researchers extracted records of 32,957 outpatient MRI appointments scheduled between January 2016 and December 2018 from their institution's radiology information system, while acquiring a further holdout test set of 1,080 records from January 2019.