Predicting Wait Times in Pediatric Ophthalmology Outpatient Clinic Using Machine Learning

Area of Science:

• Health Informatics
• Clinical Operations Research
• Artificial Intelligence in Medicine

Background:

• Patient satisfaction is significantly impacted by perceived wait times in outpatient settings.
• Accurate wait time predictions can mitigate patient uncertainty and enhance satisfaction.
• Efficient methods for predicting clinical wait times are currently limited.

Purpose of the Study:

• To evaluate the efficacy of supervised machine learning algorithms in predicting patient wait times within a pediatric ophthalmology outpatient clinic.
• To compare the predictive accuracy of various machine learning models using historical electronic health record (EHR) data.
• To identify key predictors influencing patient wait times through machine learning analysis.

Main Methods:

• Secondary EHR data from a pediatric ophthalmology clinic were utilized.
• Several supervised machine learning algorithms were compared, including Random Forest, Elastic Net, Gradient Boosting Machine, Support Vector Machine, and Multiple Linear Regression.
• Model performance was assessed to determine the most accurate predictive model for wait times.

Main Results:

• Machine learning models demonstrated potential for accurate wait time prediction using EHR data.
• The comparative analysis identified the most effective algorithms for this predictive task.
• Key predictors influencing patient wait times were identified, offering insights into operational bottlenecks.

Conclusions:

• Supervised machine learning offers a viable approach to predict patient wait times in specialized outpatient clinics.
• Accurate wait time prediction can be achieved by leveraging existing EHR data.
• Future integration with real-time EHR data could provide dynamic, accurate wait time estimates for patients.