Data-driven analytics to support scheduling of multi-priority multi-class patients with wait time targets

Abstract

Magnetic Resonance Image (MRI) uses powerful magnetic forces and radio frequencies to create detailed images of the organs and tissues within the body. In this paper, we first conduct descriptive analytics on MRI data of over 3.7 million patient records and determine the main factors affecting the waiting time and conduct predictive analytics to forecast the daily arrivals and the number of procedures performed at each hospital. It is the hospital’s goal to serve 90% of patients within their wait time targets. Therefore, we prescribe two simple scheduling policies based on a balance between the FIFO (First-In First-Out) and strict priority policies; namely, weight accumulation and priority promotion to improve the wait time management. Under the weight accumulation policy, patients from different priority levels start with varying initial weights, which then accumulates as a linear function of their waiting time. Under the priority promotion policy, a strict priority policy is applied to priority levels where patients are promoted to a higher priority level after waiting for a predetermined threshold of time. We evaluate the proposed policies against two performance measures: total exceeding time (the number of days by which patients exceed their wait target), and overflow proportion (the percentage of patients that exceed the wait target). To investigate the value of information, we schedule patients at different points of time from their day of arrival. The results show that hospitals can enhance their wait time management by delaying patient scheduling. We demonstrate that effective scheduling policies may result in significant reduction in patient waiting time without any costly capacity expansion.