A Multi-Stage predictive model for missed appointments at outpatient primary care settings serving rural areas
Laith Abu Lekham, Yong Wang, Ellen Hey, Sarah S. Lam, Mohammad T. Khasawneh
Abstract
ABSTRATMissed appointments are a significant cause of inefficiency in the healthcare industry. Many researchers have studied this problem in various healthcare settings. However, a few studies are concerned with predicting missed appointments at outpatient primary care settings serving rural areas. This study holistically investigates the factors behind two types of missed appointments - no shows and cancelations - at an outpatient primary care medical center serving rural areas and develops a predictive model to reduce their incidence. The study was carried out in three main phases. First, exploratory data analysis was conducted to discover the patterns related to missed appointments. Second, the association between some of the attributes and appointment status was analyzed. Third, three prediction models – binary, multi-class, multi-stage chain - were considered for missed appointments. The third model is a new proposed multi-stage chain model to predict missed appointments. Machine learning classifiers including logistic regression, decision tree, and tree-based ensemble classifiers were used in the three models. It was found that appointment lead time is a key driver for missed appointments. The multi-stage chain model produced the best results with 73.0% precision, 73.3% recall, 73.0% F1-score, and 73.3% accuracy. Based on this analysis, several interventions were proposed to reduce missed appointments.