Genetic Algorithm-Based Optimization for Nurse Scheduling Problem

Abstract

The nursing workforce problem is essentially a scheduling problem. Scheduling problems involve the efficient planning and sequencing of specific resources, aiming to find the best time schedule that meets all constraints. Genetic Algorithm can be utilized to solve scheduling problems effectively. In this study, taking into account the success of the Genetic Algorithm in scheduling problems, a software has been developed in the Python environment to ensure the optimal assignment of nurses in clinics. The Genetic Algorithm-based software operates on a population basis, seeking to find the best schedule that satisfies various tasks and constraints. During the study, the planning of nursing staff considered the possibility of different clinics within the hospital, each dealing with patients requiring different care durations. It was assumed that a nurse works according to legal restrictions. Furthermore, a 4-week period was taken into consideration during the scheduling process, and the program was executed for a total of 28 days (a total working time of 160 hours). As a result, a software solution was presented that can successfully achieve an optimal nurse assignment, enabling the complete fulfillment of patients' care requirements in a given clinic.

Keywords

• genetic algorithm
• nurse scheduling
• optimization

References

1. [1] M. Gradišar, T. Turk, J. P. Hajdinjak and L. Tomat, “Interactive nurse scheduling,” CIN: Computers, Informatics, Nursing, vol. 41, no. 3, pp. 172-182, 2023, doi: 10.1097/cin.0000000000000941.
2. [2] M.D. Bal, “Yataklı Tedavi Kurumlarında Hemşire İnsan Gücü Planlama Yaklaşımları,” Sağlık ve Hemşirelik Yönetim Dergisi, vol. 3, no. 1, pp. 148-154, 2015, doi: 10.5222/shyd.2014.148.
3. [3] C. Lin, J. Kang, D. Chiang, and C. Chen, “Nurse scheduling with joint normalized shift and day-off preference satisfaction using a genetic algorithm with immigrant scheme,” International Journal of Distributed Sensor Networks, vol. 11, no. 7, pp. 1-10, 2015.
4. [4] M. Mohammadian, M. Babaei, M.A. Jarrahi and E. Anjomrouz, “Scheduling nurse shifts using goal programming based on nurse preferences: a case study in an emergency department,” International Journal of Engineering, vol. 32, no. 7, pp. 954-963, 2019.
5. [5] A. Hofler, B. Terzić, M. Krämer, A. Zvezdin, V. Morozov, Y. Roblin, F. Lin and C. Jarvis, “Innovative applications of genetic algorithms to problems in accelerator physics,” Physical Review Special Topics - Accelerators and Beams, vol. 16, no. 1, pp. 1-25, 2013.
6. [6] K. Leksakul and S. Phetsawat, “Nurse scheduling using genetic algorithm,” Mathematical Problems in Engineering, pp. 1-16, 2014, doi: 10.1155/2014/246543.
7. [7] B. Maenhout and M. Vanhoucke, “Comparison and hybridization of crossover operators for the nurse scheduling problem,” Annals of Operations Research, vol. 159, no. 1, pp. 333-353, 2007.
8. [8] A. Wibowo, and Y. Lianawati, “A multi-objective genetic algorithm for optimizing the nurse scheduling problem,” International Journal of Recent Technology and Engineering (IJRTE), vol. 8, no. 3, pp. 5409-5414, 2019.

9. [9] D. Yıldırım, “Hemşire İnsan Gücü Planlaması,” Hemşirelik Dergisi, vol. 12, pp. 57-70, 2002.
10. [10] G. Bozkurt, E. Türkmen, N. Zengin, “Work Load Related To Independent Functions of Intensive Care Nurses,” Yoğun Bakım Hemşireliği Dergisi, vol. 21, no. 2, pp. 36-41, 2017.
11. [11] T. Bäck, U. Hammel, and H. Schwefel, “Evolutionary computation: comments on the history and current state,” IEEE Transactions on Evolutionary Computation, vol. 1, no. 1, pp. 3-17, 1997.