Biomimicry in Radiation Therapy: Optimizing Patient Scheduling for Improved Treatment Outcomes
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916551605616640 |
|---|---|
| author | K., Keshav Kumar Narasimham, NVSL |
| author_facet | K., Keshav Kumar Narasimham, NVSL |
| contents | In the realm of medical science, the pursuit of enhancing treatment efficacy and patient outcomes continues to drive innovation. This study delves into the integration of biomimicry principles within the domain of Radiation Therapy (RT) to optimize patient scheduling, ultimately aiming to augment treatment results. RT stands as a vital medical technique for eradicating cancer cells and diminishing tumor sizes. Yet, the manual scheduling of patients for RT proves both laborious and intricate. In this research, the focus is on automating patient scheduling for RT through the application of optimization methodologies. Three bio-inspired algorithms are employed for optimization to tackle the complex online stochastic scheduling problem. These algorithms include the Genetic Algorithm (GA), Firefly Optimization (FFO), and Wolf Optimization (WO). These algorithms are harnessed to address the intricate challenges of online stochastic scheduling. Through rigorous evaluation, involving the scrutiny of convergence time, runtime, and objective values, the comparative performance of these algorithms is determined. The results of this study unveil the effectiveness of the applied bio-inspired algorithms in optimizing patient scheduling for RT. Among the algorithms examined, WO emerges as the frontrunner, consistently delivering superior outcomes across various evaluation criteria. The optimization approach showcased in this study holds the potential to streamline processes, reduce manual intervention, and ultimately improve treatment outcomes for patients undergoing RT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09996 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Biomimicry in Radiation Therapy: Optimizing Patient Scheduling for Improved Treatment Outcomes K., Keshav Kumar Narasimham, NVSL Neural and Evolutionary Computing Optimization and Control In the realm of medical science, the pursuit of enhancing treatment efficacy and patient outcomes continues to drive innovation. This study delves into the integration of biomimicry principles within the domain of Radiation Therapy (RT) to optimize patient scheduling, ultimately aiming to augment treatment results. RT stands as a vital medical technique for eradicating cancer cells and diminishing tumor sizes. Yet, the manual scheduling of patients for RT proves both laborious and intricate. In this research, the focus is on automating patient scheduling for RT through the application of optimization methodologies. Three bio-inspired algorithms are employed for optimization to tackle the complex online stochastic scheduling problem. These algorithms include the Genetic Algorithm (GA), Firefly Optimization (FFO), and Wolf Optimization (WO). These algorithms are harnessed to address the intricate challenges of online stochastic scheduling. Through rigorous evaluation, involving the scrutiny of convergence time, runtime, and objective values, the comparative performance of these algorithms is determined. The results of this study unveil the effectiveness of the applied bio-inspired algorithms in optimizing patient scheduling for RT. Among the algorithms examined, WO emerges as the frontrunner, consistently delivering superior outcomes across various evaluation criteria. The optimization approach showcased in this study holds the potential to streamline processes, reduce manual intervention, and ultimately improve treatment outcomes for patients undergoing RT. |
| title | Biomimicry in Radiation Therapy: Optimizing Patient Scheduling for Improved Treatment Outcomes |
| topic | Neural and Evolutionary Computing Optimization and Control |
| url | https://arxiv.org/abs/2404.09996 |