Utilizing online stochastic optimization on scheduling of intensity-modulate radiotherapy therapy (IMRT)

Area of Science:

• Medical Physics
• Operations Research
• Health Informatics

Background:

• Cancer is a leading cause of death in Taiwan, with radiotherapy being a critical treatment modality.
• Intensive-Modulated Radiation Therapy (IMRT) is vital for treating various cancers, including nasopharyngeal, digestive, and cervical cancers.
• Efficient patient scheduling is crucial for timely cancer treatment and improved survival rates, yet remains under-explored.

Purpose of the Study:

• To develop and validate a mathematical model for optimizing IMRT patient scheduling.
• To reduce patient waiting times for cancer radiotherapy.
• To enhance the efficiency of radiotherapy scheduling in medical institutions.

Main Methods:

• Proposed a two-stage approach: an online stochastic algorithm and a genetic algorithm (GA).
• Developed a mathematical model to improve the efficiency of patient scheduling systems.
• Validated the proposed model using real-world data from a medical institute.

Main Results:

• The proposed model demonstrated improved performance in scheduling Intensive-Modulated Radiation Therapy patients.
• The genetic algorithm effectively addressed the online stochastic scheduling problem.
• The study provided a practical solution for reducing patient waiting times in radiotherapy.

Conclusions:

• The developed mathematical model and genetic algorithm offer a practical approach to enhance IMRT patient scheduling efficiency.
• Implementing this model can significantly decrease patient wait times, leading to earlier cancer treatment.
• This research contributes valuable insights for medical institutions seeking to optimize radiotherapy resource allocation.