Multi-objective genetic algorithms for scheduling of radiotherapy treatments for categorised cancer patients

Dobrila Petrovic, M. Morshed, S. Petrovic

    Research output: Contribution to journalArticle

    25 Citations (Scopus)
    99 Downloads (Pure)

    Abstract

    This paper presents a multi-objective optimisation model and algorithms for scheduling of radiotherapy treatments for categorised cancer patients. The model is developed considering real life radiotherapy treatment processes at Arden Cancer Centre, in the UK. The scheduling model considers various real life constraints, such as doctors’ rota, machine availability, patient’s category, waiting time targets (i.e., the time when a patient should receive the first treatment fraction), and so on. Two objectives are defined: minimisation of the Average patient’s waiting time and minimisation of Average length of breaches of waiting time targets. Three genetic algorithms (GAs) are developed and implemented which treat radiotherapy patient categories, namely emergency, palliative and radical patients in different ways: (1) Standard-GA, which considers all patient categories equally, (2) KB-GA, which has an embedded knowledge on the scheduling of emergency patient category and (3) Weighted-GA, which operates with different weights given to the patient categories. The performance of schedules generated by using the three GAs is compared using the statistical analyses. The results show that KB-GA generated the schedules with best performance considering emergency patients and slightly outperforms the other two GAs when all patient categories are considered simultaneously. KB-GA and Weighted-GA generated better performance schedules for emergency and palliative patients than Standard-GA.
    Original languageEnglish
    Pages (from-to)6994–7002
    JournalExpert Systems with Applications
    Volume38
    Issue number6
    DOIs
    Publication statusPublished - Jun 2011

    Fingerprint

    Radiotherapy
    Genetic algorithms
    Scheduling
    Multiobjective optimization
    Availability

    Keywords

    • scheduling
    • genetic algorithms
    • radiotherapy
    • waiting times

    Cite this

    Multi-objective genetic algorithms for scheduling of radiotherapy treatments for categorised cancer patients. / Petrovic, Dobrila; Morshed, M.; Petrovic, S.

    In: Expert Systems with Applications, Vol. 38, No. 6, 06.2011, p. 6994–7002.

    Research output: Contribution to journalArticle

    @article{ce79563fa7b1452e973cccc386a4170c,
    title = "Multi-objective genetic algorithms for scheduling of radiotherapy treatments for categorised cancer patients",
    abstract = "This paper presents a multi-objective optimisation model and algorithms for scheduling of radiotherapy treatments for categorised cancer patients. The model is developed considering real life radiotherapy treatment processes at Arden Cancer Centre, in the UK. The scheduling model considers various real life constraints, such as doctors’ rota, machine availability, patient’s category, waiting time targets (i.e., the time when a patient should receive the first treatment fraction), and so on. Two objectives are defined: minimisation of the Average patient’s waiting time and minimisation of Average length of breaches of waiting time targets. Three genetic algorithms (GAs) are developed and implemented which treat radiotherapy patient categories, namely emergency, palliative and radical patients in different ways: (1) Standard-GA, which considers all patient categories equally, (2) KB-GA, which has an embedded knowledge on the scheduling of emergency patient category and (3) Weighted-GA, which operates with different weights given to the patient categories. The performance of schedules generated by using the three GAs is compared using the statistical analyses. The results show that KB-GA generated the schedules with best performance considering emergency patients and slightly outperforms the other two GAs when all patient categories are considered simultaneously. KB-GA and Weighted-GA generated better performance schedules for emergency and palliative patients than Standard-GA.",
    keywords = "scheduling, genetic algorithms, radiotherapy, waiting times",
    author = "Dobrila Petrovic and M. Morshed and S. Petrovic",
    year = "2011",
    month = "6",
    doi = "10.1016/j.eswa.2010.12.015",
    language = "English",
    volume = "38",
    pages = "6994–7002",
    journal = "Expert Systems with Applications",
    issn = "0957-4174",
    publisher = "Permagon Press",
    number = "6",

    }

    TY - JOUR

    T1 - Multi-objective genetic algorithms for scheduling of radiotherapy treatments for categorised cancer patients

    AU - Petrovic, Dobrila

    AU - Morshed, M.

    AU - Petrovic, S.

    PY - 2011/6

    Y1 - 2011/6

    N2 - This paper presents a multi-objective optimisation model and algorithms for scheduling of radiotherapy treatments for categorised cancer patients. The model is developed considering real life radiotherapy treatment processes at Arden Cancer Centre, in the UK. The scheduling model considers various real life constraints, such as doctors’ rota, machine availability, patient’s category, waiting time targets (i.e., the time when a patient should receive the first treatment fraction), and so on. Two objectives are defined: minimisation of the Average patient’s waiting time and minimisation of Average length of breaches of waiting time targets. Three genetic algorithms (GAs) are developed and implemented which treat radiotherapy patient categories, namely emergency, palliative and radical patients in different ways: (1) Standard-GA, which considers all patient categories equally, (2) KB-GA, which has an embedded knowledge on the scheduling of emergency patient category and (3) Weighted-GA, which operates with different weights given to the patient categories. The performance of schedules generated by using the three GAs is compared using the statistical analyses. The results show that KB-GA generated the schedules with best performance considering emergency patients and slightly outperforms the other two GAs when all patient categories are considered simultaneously. KB-GA and Weighted-GA generated better performance schedules for emergency and palliative patients than Standard-GA.

    AB - This paper presents a multi-objective optimisation model and algorithms for scheduling of radiotherapy treatments for categorised cancer patients. The model is developed considering real life radiotherapy treatment processes at Arden Cancer Centre, in the UK. The scheduling model considers various real life constraints, such as doctors’ rota, machine availability, patient’s category, waiting time targets (i.e., the time when a patient should receive the first treatment fraction), and so on. Two objectives are defined: minimisation of the Average patient’s waiting time and minimisation of Average length of breaches of waiting time targets. Three genetic algorithms (GAs) are developed and implemented which treat radiotherapy patient categories, namely emergency, palliative and radical patients in different ways: (1) Standard-GA, which considers all patient categories equally, (2) KB-GA, which has an embedded knowledge on the scheduling of emergency patient category and (3) Weighted-GA, which operates with different weights given to the patient categories. The performance of schedules generated by using the three GAs is compared using the statistical analyses. The results show that KB-GA generated the schedules with best performance considering emergency patients and slightly outperforms the other two GAs when all patient categories are considered simultaneously. KB-GA and Weighted-GA generated better performance schedules for emergency and palliative patients than Standard-GA.

    KW - scheduling

    KW - genetic algorithms

    KW - radiotherapy

    KW - waiting times

    U2 - 10.1016/j.eswa.2010.12.015

    DO - 10.1016/j.eswa.2010.12.015

    M3 - Article

    VL - 38

    SP - 6994

    EP - 7002

    JO - Expert Systems with Applications

    JF - Expert Systems with Applications

    SN - 0957-4174

    IS - 6

    ER -