Multi-objective particle swarm optimisation for phase specific cancer drug scheduling

Muhammad Alam, Saleh Algoul, Alamgir Hossain, Azim Majumder

    Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

    2 Citations (Scopus)

    Abstract

    An effective chemotherapy drug scheduling requires adequate balancing of administration of anti-cancer drugs to reduce the tumour size as well as toxic side effects. Conventional clinical methods very often fail to balance between these two parameters due to their inherent conflicting nature. This paper presents a method of phase specific drug scheduling using a close-loop control method and multi-objective particle swarm optimisation algorithm (MOPSO) that can provide solutions for trading-off between the cell killing and toxic side effects. A close-loop control method, namely Integral-Proportional-Derivative (I-PD) is designed to control the drug to be infused to the patient’s body and MOPSO is used to find suitable parameters of the controller. A phase specific cancer tumour model is used for this work to show the effects of drug on tumour. Results show that the proposed method can generate very efficient drug scheduling that trade-off between cell killing and toxic side effects and satisfy associated design goals, for example lower drug doses and lower drug concentration. Moreover, our approach can reduce the number of proliferating and quiescent cells up to 72% and 60% respectively; maximum reduction with phase-specific model compared to reported work available so far.
    Original languageEnglish
    Title of host publicationInternational Conference on Computational Systems Biology and Bioinformatics (CSBio 2010)
    EditorsJonathan H. Chan, Yew-Soon Ong, Sung-Bae Cho
    Place of PublicationLondon
    PublisherSpringer
    Pages180-192
    Volume115, 5
    ISBN (Print)978-3642167492
    DOIs
    Publication statusPublished - 2010

    Fingerprint

    Dive into the research topics of 'Multi-objective particle swarm optimisation for phase specific cancer drug scheduling'. Together they form a unique fingerprint.

    Cite this