A novel TOPSIS–CBR goal programming approach to sustainable healthcare treatment

Malekpoor, Hanif; Mishra, Nishikant; Kumar, Sameer

Abstract

© 2018, The Author(s). Cancer is one of the most common diseases worldwide and its treatment is a complex and time-consuming process. Specifically, prostate cancer as the most common cancer among male population has received the attentions of many researchers. Oncologists and medical physicists usually rely on their past experience and expertise to prescribe the dose plan for cancer treatment. The main objective of dose planning process is to deliver high dose to the cancerous cells and simultaneously minimize the side effects of the treatment. In this article, a novel TOPSIS case based reasoning goal-programming approach has been proposed to optimize the dose plan for prostate cancer treatment. Firstly, a hybrid retrieval process TOPSIS–CBR [technique for order preference by similarity to ideal solution (TOPSIS) and case based reasoning (CBR)] is used to capture the expertise and experience of oncologists. Thereafter, the dose plans of retrieved cases are adjusted using goal-programming mathematical model. This approach will not only help oncologists to make a better trade-off between different conflicting decision making criteria but will also deliver a high dose to the cancerous cells with minimal and necessary effect on surrounding organs at risk. The efficacy of proposed method is tested on a real data set collected from Nottingham City Hospital using leave-one-out strategy. In most of the cases treatment plans generated by the proposed method is coherent with the dose plan prescribed by an experienced oncologist or even better. Developed decision support system can assist both new and experienced oncologists in the treatment planning process.

Citation

Malekpoor, H., Mishra, N., & Kumar, S. (2018). A novel TOPSIS–CBR goal programming approach to sustainable healthcare treatment. Annals of Operations Research, https://doi.org/10.1007/s10479-018-2992-y

• Journal Article Type: Article
• Acceptance Date: Jul 23, 2018
• Online Publication Date: Aug 3, 2018
• Publication Date: Aug 3, 2018
• Deposit Date: Aug 8, 2018
• Publicly Available Date: Aug 9, 2018
• Journal: Annals of Operations Research
• Print ISSN: 0254-5330
• Electronic ISSN: 1572-9338
• Publisher: Springer Verlag
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1007/s10479-018-2992-y
• Keywords: Management Science and Operations Research; General Decision Sciences
• Public URL: https://hull-repository.worktribe.com/output/972851
• Publisher URL: https://link.springer.com/article/10.1007%2Fs10479-018-2992-y#enumeration