Text

Introduction: Patient transportation within the departments (i.e., Intra-Hospital) is one of the complex and frequent secondary activities in hospitals. Each transporter performs a non-continuous sequence of transport jobs in the shifts. Emergency situations like the pandemic can cause difficulty in maintaining employee relations (e.g., fairness) due to uncertainties like delays and unforeseen circumstances [1]. Optimization algorithms use cost effective, evidence-based synthesis in different situations for high-quality continuous healthcare. Intervention mechanisms strategize algorithms (e.g., Metaheuristics, decision trees using Mixed Integer Programming (MIP)) for better performance [2]. Discrete Event Simulation (DES) suits behavioral analysis of hospital systems at different situations or timestamps to improve healthcare processes. Related works to patient transportation considered multi-objectives solved using heuristics, exact methods or combination of both. The problem variants are tackled by classifying patient groups and their characteristics, DES of Just-in-time patient arrivals for computationally efficient solutions. However, minimally addressed aspects in literature are uncertainties, time window constraints, historical data sets analysis and DES to improve service quality in emergency situations [3], [4].

Methods: Our work uses retrospective data sets of transport jobs in real process within an 8-hour shift on different days during the pandemic from hospital. The primary objective is to determine the number of transporters to assign all available jobs. The secondary objective is to optimize operations flow among all transporters by using features (i.e., total travel time, total idle time and their statistical measures like standard deviation). Our previous work used Iterated Local Search (ILS) Metaheuristic with MIP linear constraint to satisfy primary objective and compatibility (i.e., no time overlaps between jobs) [5]. Our algorithm considers DES within ILS incorporated with distinct interventions. This extends our previous work for improved optimization (i.e., fair or balanced workload, optimizing resources). DES identifies available jobs and transporters at each time stamp and different MIP constraints identifies compatible transporters and scrutinize them for each job. Our formulation of mathematical equations are distinct intervention to calculate parameter estimates using the features for each job among scrutinized transporters. The best choice is a transporter with the least value parameter estimate for job assignments.

Results: Our work involves multi-phase empirical study of considered algorithm using different data sets (n=7) of varied size (520<no. jobs="" of="").

Discussion: Considered algorithm is 50%-55% more computationally efficient than our previous method by obtaining solution in below 15 seconds. As job assignments are based on timestamps, considered algorithm can be applicable for real-time settings to handle delays. Our distinct interventions construct a statistical model for each data set of unique scenarios (i.e., spatial and temporal information of available jobs).

Conclusion: Our distinct interventions improve DES within ILS strategically for better optimization by assessments from different data sets. Our future work will consider multiple features and department-specific requirements to plan the routes effectively.

The authors declare that they have no competing interests.

The authors declare that an ethics committee vote is not required.

Literatur

[1] Kropp T, Faeghi S, Lennerts K. Evaluation of patient transport service in hospitals using process mining methods: Patient’s perspective. Int J Health Plann Mgmt. 2023;38:430-56.
[2] Goodman D, Ogrinc G, Davies L, Baker GR, Barnsteiner J, Foster TC, Gali K, Hilden J, Horwitz L, Kaplan HC, Leis J, Matulis JC, Michie S, Miltner R, Neily J, Nelson WA, Niedner M, Oliver B, Rutman L, Thomson R, Thor J. Explanation and elaboration of SQUIRE (Standards for Quality Improvement Reporting Excellence) Guidelines, V.2.0: examples of SQUIRE elements in the healthcare improvement literature. BMJ Qual Saf. 2016;25(12):e7.
[3] Elmbach AF, Scholl A, Walter R. Minimizing the maximal ergonomic burden in intra-hospital patient transportation. European Journal of Operational Research. 2019 Aug;276(3):840-54.
[4] Melman GJ, Parlikad AK, Cameron EAB. Balancing scarce hospital resources during the COVID-19 pandemic using discrete-event simulation. Health Care Manag Sci. 2021;24:356-74.
[5] Karthikeyan S, Potluri S. Route Planning for Intra-Hospital Patient Transportation Using Metaheuristics and Mixed Integer Linear Programming. In: Mantas J, et al, editors. Digital Health and Informatics Innovations for Sustainable Health Care Systems. Proceedings of the 34th Medical Informatics Europe Conference; 2024 Aug 25-29; Athens, Greece. IOS; 2024. (Studies in Health Technology and Informatics; 316). p. 993-97. DOI: 10.3233/SHTI240577