1. UKM Learning and Research Repository
2. PHD Thesis / Tesis PHD
3. Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Title:	Model and solution approaches for patient admission scheduling problems
Authors:	Saif Kifah Jihad (P60049)
Supervisor:	Salwani Abdullah, Prof. Dr.
Keywords:	Computer algorithms
Issue Date:	Jan-2017
Description:	Patient admission scheduling is a combinatorial optimisation problem that is attaining raising concern in health care practice. It deals in assigning a patient to bed in a hospital that fulfils the medical urgency subject to several restrictions. Patient admission is, nonetheless, a very complex task. This is because of the involvement of several resources in the hospital, such as oxygen or telemetry, that is either necessary or not to the patients. Assigning a patient to a bed, which is located in the department that specialised to treat patient’s condition is a critical requirement. In addition, there is uncertainty in the health condition of the patient and changes do often occur, that necessitate the provision of patients’ needed medical equipment or properties. These challenges will prompt the healthcare system to offer a higher quality treatment in terms of patients’ comfort with limited resources. The research work presented in this thesis aims to build upon the state of the art in search methodologies for patient admission scheduling problems. The research first highlights an investigation on an adaptive non-linear Great Deluge algorithm to tackle a standard static patient admission scheduling problem. Due to the fact that unpredictable changes might occur during the course of an ongoing scheduling process. Thus, the research next highlights an extension to the static patient admission scheduling problem that is modelled in a dynamic fashion to represent a real world scenario. Three dynamic models are introduced i.e., (i) dynamic duration, (ii) dynamic properties, and (iii) dynamic duration and properties. In solving the dynamic patient admission scheduling problem, the solution approach should be able to monitor the movement of the optimal point and the changes in the landscape solutions. In real-world scenario, patients have multiple objectives that are conflicting to each other. Thus, the research proposes a solution approach to multi-objective patient admission scheduling problem where six conflicting objectives are considered i.e., room should be occupied by the same gender, minimised a patient transfer, assign patients to wards specialised in the treatment, satisfy the mandatory/preferred properties, satisfy the specialism of the pathology and satisfy room preferences. A set of non-dominating solutions known as the Pareto optimal (rather than a single solution as in static and dynamic patient admission problems) is generated, which later helps the decision maker in the hospital to make the right decision. In this work, the performance of the adaptive non-linear algorithm is tested on three different natures of the patient admission scheduling problems where the non-linear decay rate of the water level in the Great Deluge algorithm is adaptively updating during the optimisation course. Computational results based on standard benchmark instances are reported to demonstrate the effectiveness of the approach studied here on static, dynamic and multi-objective patient admission scheduling problems. Comparison with other approaches in the scientific literature shows that the proposed approaches are able to obtain competitive results and would be a highly appropriate methodology to employ.,Certification of Master's/Doctoral Thesis" is not available
Pages:	144
Call Number:	QA76.9.A43J535 2017 3 tesis
Publisher:	UKM, Bangi
Appears in Collections:	Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.