Cyber Physical System for Pre-operative Patient Prehabilitation
| aut.embargo | No | en_NZ |
| aut.thirdpc.contains | No | en_NZ |
| dc.contributor.advisor | Al-Anbuky, Adnan | |
| dc.contributor.advisor | Mawston, Grant | |
| dc.contributor.author | Al-Naime, Khalid Abdulrazak Mahmood | |
| dc.date.accessioned | 2022-07-12T22:24:58Z | |
| dc.date.available | 2022-07-12T22:24:58Z | |
| dc.date.copyright | 2022 | |
| dc.date.issued | 2022 | |
| dc.date.updated | 2022-07-12T21:00:37Z | |
| dc.description.abstract | Abdominal cancer is the one of the most frequent and dangerous cancers in the world, particularly among the elderly, and is considered one of the leading causes of death in New Zealand and throughout the world. Major surgery is associated with a significant deterioration in quality of life, as well as a 20%-40% reduction in postoperative physical function. Physical fitness and level of activity are considered important factors for patients with cancer undergoing major abdominal surgery. These patients are often given exercise programmes prior to surgery (prehabilitation), aimed at improving fitness to reduce perioperative risk. Even though the number of prehabilitation programmes has increased over the last decade, there are many obstacles preventing large numbers of patients being involved in such programmes. One key problem is access to prehabilitation facilities and resources. The long-distance travel to vital cancer services can have a significant impact on a patient’s quality of life and survival. Furthermore, limited numbers of healthcare centres and staff impact on the number of patients who can participate in supervised prehabilitation programmes. Unsupervised prehabilitation programmes have problems such as uncertainty of compliance with home-based exercises. Also lacking are measurements for the movements that are performed in relation to the intended frequency and intensity. Patient safety is also an issue with an unsupervised programme. To minimise the above barriers, a model for a mixed mode prehabilitation programme has been designed. An environment for hosting the prehabilitation tracking model has also been developed. The end result proposes an end-to-end solution that provides patients and healthcare staff with a real-time remote monitoring and visualisation system. Furthermore, architectural features were recruited for this work to balance the computational load between the IoT device, gateway and cloud. This has facilitated better usage of the available environment through fewer messages, and the sharing of resources has reflected positively on overall system performance, such as: a. The system showed high performance with activity recognition percentages ranging from 70%-94% when using the personalised database. b. Different logical methods (M1, M2, M3, and M4) for activity recognition were implemented and embedded at the gateway level. c. Using a mixed mode enabled detecting both casual and formal activities relevant to the prehabilitation programme. Also, the system offers real-time feedback on patients’ progress during the prehabilitation period. On the other hand, many challenging areas require additional research to provide better system performance, such as using artificial intelligence (AI) techniques in various embedded IoT devices and differentiating between the different weights credited to different types of movement and activities. This thesis is divided into seven different chapters, each accounting for a specific element of the overall work. The motivational background for the rising demand for healthcare monitoring is presented in the first chapter. The second chapter accounts for a critical review of the existing literature pertaining to the various key elements and boundaries associated with constructing a mixed mode prehabilitation model. The third chapter provides information related to the tools used for the implementation of hardware and software in the testing and verification of concepts. Chapter 4 proposes a conceptual mixed mode prehabilitation model based on existing rules and health programmes. Chapter 5 examines the various components of CPS in terms of data collection, data analysis, activity recognition, data visualisation, and short- and long-term data storage. Chapter 6 presents the clearly defined validation output data of the developed mixed mode prehabilitation model. The conclusions of this thesis, as well as the future path of the work, are presented in Chapter 7. Finally, this work has delivered four articles that have been published in international journals and conferences, and two proposed papers are under development to state the research outcome. | en_NZ |
| dc.identifier.uri | https://hdl.handle.net/10292/15292 | |
| dc.language.iso | en | en_NZ |
| dc.publisher | Auckland University of Technology | |
| dc.rights.accessrights | OpenAccess | |
| dc.title | Cyber Physical System for Pre-operative Patient Prehabilitation | en_NZ |
| dc.type | Thesis | en_NZ |
| thesis.degree.grantor | Auckland University of Technology | |
| thesis.degree.level | Doctoral Theses | |
| thesis.degree.name | Doctor of Philosophy | en_NZ |