An AI model can help identify those patients who are at greatest risk for not appearing for their appointment -- and therefore help radiology departments better address the problem, wrote a team led by Dr. Le Roy Chong of Changi General Hospital in Singapore.
"[AI] data may be readily retrievable from frontline information technology systems commonly used in most hospital radiology departments, and they can be readily incorporated into routine workflow practice to improve the efficiency and quality of health care delivery," the group wrote.
Chong's group developed an AI model that they trained with data from 32,957 outpatient MRI appointments scheduled between January 2016 and December 2018. The overall no-show rate for MRI appointments was 17.4%.
In response to this finding, Chong's team put a telephone call reminder intervention into place for the top 25% of patients at highest risk of not appearing for their scheduled appointment as predicted by the model. The group implemented the measure for six months.
At the end of the intervention period, the no-show rate had decreased to 15.9%, compared with 19.3% in the preceding 12-month period. Chong and colleagues also found that no-show rates between contactable and non-contactable patients varied widely, at 17.5% and 40.3%.
"Machine learning predictive analytics perform moderately well in predicting complex problems involving human behavior using a modest amount of data with basic feature engineering, and they can be incorporated into routine workflow to improve healthcare delivery," the group concluded.
Copyright © 2020 AuntMinnie.com