Boston and Yonsein Hospital comes up with AI model to predict no-show patients

Health and Wellness Informatics News

The researchers discuss the analysis of the inclusion of local weather. The information in predicting features improves model accuracy.

Boston Children’s Hospital and Yonsei University researchers developed a machine learning tool. This tool can predict no-shows in pediatric medical appointments. The team created a AI model identifying 83% of no-shows at the time of scheduling.

This was via the adoption of a data imputation method for patients with missing information. It also explains how exploiting local weather information happens. The team wrote in an article published in npj digital medicine that their no-show prediction is potentially more informative. This is basically during appropriate interventions to reduce no-shows.

The researchers pointed out no shows. This is when a patient schedules but does not attend an appointment. This can have negative effects on patient health. This can also have a bad effect on hospital and clinic resource utilization. They wrote, “As continuity of treatment, preventive services, and medical check-ups cannot be delivered when a patient misses an appointment, no-shows at appointments have been associated with poor control of chronic diseases and delayed presentation to care.”

This specifically works for atmospheric pressure. The team potentially identified actionable ways for further studies to explore how to reduce patient no-shows.

They also suggested that their AI model might be helpful when it comes to interventions. These interventions include texting, emailing, or calling patients.

They wrote that it even might be useful to calculate the optimal frequency at which reminders should send to each patient. Also, it will help better to allocate free transportation resources when needed.

They continued that we acknowledge that clinics with limited resources and interventions may not always become available. But with the limitation in mind, it’s easier to explore potentially actionable items.

The items included choosing the day of the week and time of day that will get easier for patients.


  • No comments yet.
  • Add a comment

    Join our Mailing list!

    Get all latest news, exclusive deals and updates.