(RS19) Machine Learning Predictions on Outpatient No-Show Appointments In A Malaysia Major Tertiary Hospital

Introduction:

A no-show appointment occurs when a patient does not attend a previously  booked appointment. This situation can cause various other problems such as discontinuity of  patient treatments, waste of human and financial resources. Predicting no-shows using machine  learning techniques is one of the latest approaches used to address this issue. This study’s  objective is to propose a predictive analytical approach for the development of a patient no show appointment model in Hospital Kuala Lumpur using machine learning algorithms .

Results:

Based on the descriptive analysis, the no-show rate was 28% and attributes such as  the month of the appointment and the gender of the patient were seen to influence the patient’s  no-show. Evaluation of the predictive model found that the GB model had the highest accuracy  of 78%, F1 score of 0.76, and AUC value of 0.65. 

Discussion/Conclusion:

The predictive model could be used to formulate intervention steps  to reduce the no-shows which will improve the quality of patient care.