Predicting Patient No-shows in Medical Appointments Using Demographic and Health Data

Abstract

Non-attendance at scheduled medical appointments, or "no-shows," significantly disrupts healthcare delivery and resource allocation. This study utilizes demographic and healthrelated data to predict and analyze patient no-shows, employing machine learning techniques to identify the most influential predictors. Using a dataset encompassing various patient characteristics—age, gender, scholarship status, and medical conditions such as hypertension and diabetes, the study applies different predictive models. The goal was to discern patterns and factors contributing to patient absenteeism. The research not only enhances understanding of factors influencing no-shows but also proposes actionable strategies to mitigate their occurrence, thereby optimizing healthcare resources and improving patient care management. The findings suggest that targeted interventions based on predictive analytics can effectively reduce no-show rates, providing a valuable tool for healthcare providers in improving operational efficiency and patient outcomes.

Topics & Concepts