Machine learning based integrated scheduling and rescheduling for elective and emergency patients in the operating theatre

Abstract

As the only largest source of revenue and cost in a hospital, the operation room (OR) scheduling problem is a hot research topic. Nonetheless, an integrated model is the missing key to managing and improving the efficiency of ORs. This paper presents a fully integrated model regarding three concepts: meditating elective patients and emergency patients together, considering ORs and downstream units, and proposing hierarchical weekly, daily, and rescheduling models. Due to the inherent randomness in emergency patient arrival, a random forest machine learning model and geographical information systems are used to obtain the emergency patient surgery duration and arrival time, respectively. According to the machine learning model in weekly and daily scheduling, initially, fixed capacity is reserved for emergency patients. When an emergency patient arrives, the surgery starts if a reserved OR is available. Otherwise, the first available OR will be dedicated to the patient due to an emergency patient's higher priority than an elective patient. In this case, it is needed to reschedule the OT schedule for the remaining patient. Moreover, the three-phase model guarantees that an emergency patient assigns to an OR within a specific time limit. To solve the models, genetic algorithm and particle swarm optimization are developed and compared. In addition, a real-world case study is undertaken at a hospital. The results of comparing the proposed approach to the hospital's current scheduling show that the three-phase model had a considerable positive effect on the ORs schedule.

Keywords: Elective and emergency patients; Machine learning; Operating room planning; Operating theater scheduling; Rescheduling.

Fig. 1

Flowchart of the scheduling process

Fig. 2

Chromosome structure of the problem

Fig. 3

The pseudo-code of GA steps

Fig. 4

The pseudo-code of PSO steps

Fig. 5

Travel absorbed by different districts and different types of accidents used for emergency surgery arrivals

Fig. 6

Average TCI index for Tehran interpolated by cubic spline

Fig. 7

Different scenarios generated by expected maximizing clustering on surgery duration

Fig. 8

Prediction accuracy of the random forest model

Fig. 9

Patients’ daily scheduling

Fig. 10

Remaining patients’ scheduling when EMERGENCY1 arrives

Fig. 11

Patients’ rescheduling. (Color figure online)