Background and Goals: This study examined whether machine learning could predict risks and contribution factors for no-shows in primary care practices, as well as factors for late cancellation.
Research Approach: Pennsylvania State University researchers integrated previous appointment history from 15 family medicine clinics and linked the corresponding US Census statistics and national weather reporting database. Four different machine learning modeling approaches were applied, including gradient boost, random forest, neural networks, and lassologistic regression, to predict reservation outcomes. The outcome of each appointment was attributed to one of three classes: no shows, late cancellation (cancelled within 24 hours of booking), and the visit was completed.
Key results:
-
The analysis consisted of 109,328 patients and 1,118,236 appointments, including 77,322 (6.9%) no shows and 75,545 (6.8% late cancellation).
-
The gradient boost model achieved optimal performance to classify patients as likely to be no-shows or cancel appointments late (85% for no-shows, 92% for late cancellations).
-
No bias was detected for patient characteristics (gender and race/ethnicity).
-
Schedule lead time (the number of days from patient appointment request to appointment date) was the most important predictor of missed appointments.
-
Patients who missed the appointment tended to be female, younger, sick, uninsured, uninsured, English, and ethnic minority groups. They also experienced longer lead times, higher pre-appointment rates, and more socioeconomic challenges.
Why it matters: The findings of this study provide insight into the underlying barriers that missed appointments and suggest that patients can improve appointment adherence by prioritizing strategies to allow health systems to reduce lead times and enable care teams to design personalized interventions such as text reminders and transportation assistance.
Predicting missed plans in primary care: a personalized machine learning approach
Wen Jiang Thuan, DHA, MS, MPH, etc.
Pennsylvania State School of Medicine, Faculty of Family and Community Medicine, Hershey, Pennsylvania
Temporary link
/Public release. This material of the Organization of Origin/Author is a point-in-time nature and may be edited for clarity, style and length. Mirage.news does not take any institutional position or aspect, and all views, positions and conclusions expressed here are the views of the authors alone.
